提交

Co-authored-by: Cursor <cursoragent@cursor.com>

.agents/skills/brainstorming/SKILL.md

@@ -0,0 +1,164 @@
+---
+name: brainstorming
+description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
+---
+
+# Brainstorming Ideas Into Designs
+
+Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
+
+Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
+
+<HARD-GATE>
+Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
+</HARD-GATE>
+
+## Anti-Pattern: "This Is Too Simple To Need A Design"
+
+Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
+
+## Checklist
+
+You MUST create a task for each of these items and complete them in order:
+
+1. **Explore project context** — check files, docs, recent commits
+2. **Offer visual companion** (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.
+3. **Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
+4. **Propose 2-3 approaches** — with trade-offs and your recommendation
+5. **Present design** — in sections scaled to their complexity, get user approval after each section
+6. **Write design doc** — save to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` and commit
+7. **Spec self-review** — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
+8. **User reviews written spec** — ask user to review the spec file before proceeding
+9. **Transition to implementation** — invoke writing-plans skill to create implementation plan
+
+## Process Flow
+
+```dot
+digraph brainstorming {
+    "Explore project context" [shape=box];
+    "Visual questions ahead?" [shape=diamond];
+    "Offer Visual Companion\n(own message, no other content)" [shape=box];
+    "Ask clarifying questions" [shape=box];
+    "Propose 2-3 approaches" [shape=box];
+    "Present design sections" [shape=box];
+    "User approves design?" [shape=diamond];
+    "Write design doc" [shape=box];
+    "Spec self-review\n(fix inline)" [shape=box];
+    "User reviews spec?" [shape=diamond];
+    "Invoke writing-plans skill" [shape=doublecircle];
+
+    "Explore project context" -> "Visual questions ahead?";
+    "Visual questions ahead?" -> "Offer Visual Companion\n(own message, no other content)" [label="yes"];
+    "Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
+    "Offer Visual Companion\n(own message, no other content)" -> "Ask clarifying questions";
+    "Ask clarifying questions" -> "Propose 2-3 approaches";
+    "Propose 2-3 approaches" -> "Present design sections";
+    "Present design sections" -> "User approves design?";
+    "User approves design?" -> "Present design sections" [label="no, revise"];
+    "User approves design?" -> "Write design doc" [label="yes"];
+    "Write design doc" -> "Spec self-review\n(fix inline)";
+    "Spec self-review\n(fix inline)" -> "User reviews spec?";
+    "User reviews spec?" -> "Write design doc" [label="changes requested"];
+    "User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];
+}
+```
+
+**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.
+
+## The Process
+
+**Understanding the idea:**
+
+- Check out the current project state first (files, docs, recent commits)
+- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
+- If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
+- For appropriately-scoped projects, ask questions one at a time to refine the idea
+- Prefer multiple choice questions when possible, but open-ended is fine too
+- Only one question per message - if a topic needs more exploration, break it into multiple questions
+- Focus on understanding: purpose, constraints, success criteria
+
+**Exploring approaches:**
+
+- Propose 2-3 different approaches with trade-offs
+- Present options conversationally with your recommendation and reasoning
+- Lead with your recommended option and explain why
+
+**Presenting the design:**
+
+- Once you believe you understand what you're building, present the design
+- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
+- Ask after each section whether it looks right so far
+- Cover: architecture, components, data flow, error handling, testing
+- Be ready to go back and clarify if something doesn't make sense
+
+**Design for isolation and clarity:**
+
+- Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
+- For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
+- Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
+- Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.
+
+**Working in existing codebases:**
+
+- Explore the current structure before proposing changes. Follow existing patterns.
+- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
+- Don't propose unrelated refactoring. Stay focused on what serves the current goal.
+
+## After the Design
+
+**Documentation:**
+
+- Write the validated design (spec) to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md`
+  - (User preferences for spec location override this default)
+- Use elements-of-style:writing-clearly-and-concisely skill if available
+- Commit the design document to git
+
+**Spec Self-Review:**
+After writing the spec document, look at it with fresh eyes:
+
+1. **Placeholder scan:** Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.
+2. **Internal consistency:** Do any sections contradict each other? Does the architecture match the feature descriptions?
+3. **Scope check:** Is this focused enough for a single implementation plan, or does it need decomposition?
+4. **Ambiguity check:** Could any requirement be interpreted two different ways? If so, pick one and make it explicit.
+
+Fix any issues inline. No need to re-review — just fix and move on.
+
+**User Review Gate:**
+After the spec review loop passes, ask the user to review the written spec before proceeding:
+
+> "Spec written and committed to `<path>`. Please review it and let me know if you want to make any changes before we start writing out the implementation plan."
+
+Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.
+
+**Implementation:**
+
+- Invoke the writing-plans skill to create a detailed implementation plan
+- Do NOT invoke any other skill. writing-plans is the next step.
+
+## Key Principles
+
+- **One question at a time** - Don't overwhelm with multiple questions
+- **Multiple choice preferred** - Easier to answer than open-ended when possible
+- **YAGNI ruthlessly** - Remove unnecessary features from all designs
+- **Explore alternatives** - Always propose 2-3 approaches before settling
+- **Incremental validation** - Present design, get approval before moving on
+- **Be flexible** - Go back and clarify when something doesn't make sense
+
+## Visual Companion
+
+A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.
+
+**Offering the companion:** When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:
+> "Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)"
+
+**This offer MUST be its own message.** Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.
+
+**Per-question decision:** Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: **would the user understand this better by seeing it than reading it?**
+
+- **Use the browser** for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs
+- **Use the terminal** for content that is text — requirements questions, conceptual choices, tradeoff lists, A/B/C/D text options, scope decisions
+
+A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question — use the terminal. "Which wizard layout works better?" is a visual question — use the browser.
+
+If they agree to the companion, read the detailed guide before proceeding:
+`skills/brainstorming/visual-companion.md`

.agents/skills/brainstorming/scripts/frame-template.html

@@ -0,0 +1,214 @@
+<!DOCTYPE html>
+<html>
+<head>
+  <meta charset="utf-8">
+  <title>Superpowers Brainstorming</title>
+  <style>
+    /*
+     * BRAINSTORM COMPANION FRAME TEMPLATE
+     *
+     * This template provides a consistent frame with:
+     * - OS-aware light/dark theming
+     * - Fixed header and selection indicator bar
+     * - Scrollable main content area
+     * - CSS helpers for common UI patterns
+     *
+     * Content is injected via placeholder comment in #claude-content.
+     */
+
+    * { box-sizing: border-box; margin: 0; padding: 0; }
+    html, body { height: 100%; overflow: hidden; }
+
+    /* ===== THEME VARIABLES ===== */
+    :root {
+      --bg-primary: #f5f5f7;
+      --bg-secondary: #ffffff;
+      --bg-tertiary: #e5e5e7;
+      --border: #d1d1d6;
+      --text-primary: #1d1d1f;
+      --text-secondary: #86868b;
+      --text-tertiary: #aeaeb2;
+      --accent: #0071e3;
+      --accent-hover: #0077ed;
+      --success: #34c759;
+      --warning: #ff9f0a;
+      --error: #ff3b30;
+      --selected-bg: #e8f4fd;
+      --selected-border: #0071e3;
+    }
+
+    @media (prefers-color-scheme: dark) {
+      :root {
+        --bg-primary: #1d1d1f;
+        --bg-secondary: #2d2d2f;
+        --bg-tertiary: #3d3d3f;
+        --border: #424245;
+        --text-primary: #f5f5f7;
+        --text-secondary: #86868b;
+        --text-tertiary: #636366;
+        --accent: #0a84ff;
+        --accent-hover: #409cff;
+        --selected-bg: rgba(10, 132, 255, 0.15);
+        --selected-border: #0a84ff;
+      }
+    }
+
+    body {
+      font-family: system-ui, -apple-system, BlinkMacSystemFont, sans-serif;
+      background: var(--bg-primary);
+      color: var(--text-primary);
+      display: flex;
+      flex-direction: column;
+      line-height: 1.5;
+    }
+
+    /* ===== FRAME STRUCTURE ===== */
+    .header {
+      background: var(--bg-secondary);
+      padding: 0.5rem 1.5rem;
+      display: flex;
+      justify-content: space-between;
+      align-items: center;
+      border-bottom: 1px solid var(--border);
+      flex-shrink: 0;
+    }
+    .header h1 { font-size: 0.85rem; font-weight: 500; color: var(--text-secondary); }
+    .header .status { font-size: 0.7rem; color: var(--success); display: flex; align-items: center; gap: 0.4rem; }
+    .header .status::before { content: ''; width: 6px; height: 6px; background: var(--success); border-radius: 50%; }
+
+    .main { flex: 1; overflow-y: auto; }
+    #claude-content { padding: 2rem; min-height: 100%; }
+
+    .indicator-bar {
+      background: var(--bg-secondary);
+      border-top: 1px solid var(--border);
+      padding: 0.5rem 1.5rem;
+      flex-shrink: 0;
+      text-align: center;
+    }
+    .indicator-bar span {
+      font-size: 0.75rem;
+      color: var(--text-secondary);
+    }
+    .indicator-bar .selected-text {
+      color: var(--accent);
+      font-weight: 500;
+    }
+
+    /* ===== TYPOGRAPHY ===== */
+    h2 { font-size: 1.5rem; font-weight: 600; margin-bottom: 0.5rem; }
+    h3 { font-size: 1.1rem; font-weight: 600; margin-bottom: 0.25rem; }
+    .subtitle { color: var(--text-secondary); margin-bottom: 1.5rem; }
+    .section { margin-bottom: 2rem; }
+    .label { font-size: 0.7rem; color: var(--text-secondary); text-transform: uppercase; letter-spacing: 0.05em; margin-bottom: 0.5rem; }
+
+    /* ===== OPTIONS (for A/B/C choices) ===== */
+    .options { display: flex; flex-direction: column; gap: 0.75rem; }
+    .option {
+      background: var(--bg-secondary);
+      border: 2px solid var(--border);
+      border-radius: 12px;
+      padding: 1rem 1.25rem;
+      cursor: pointer;
+      transition: all 0.15s ease;
+      display: flex;
+      align-items: flex-start;
+      gap: 1rem;
+    }
+    .option:hover { border-color: var(--accent); }
+    .option.selected { background: var(--selected-bg); border-color: var(--selected-border); }
+    .option .letter {
+      background: var(--bg-tertiary);
+      color: var(--text-secondary);
+      width: 1.75rem; height: 1.75rem;
+      border-radius: 6px;
+      display: flex; align-items: center; justify-content: center;
+      font-weight: 600; font-size: 0.85rem; flex-shrink: 0;
+    }
+    .option.selected .letter { background: var(--accent); color: white; }
+    .option .content { flex: 1; }
+    .option .content h3 { font-size: 0.95rem; margin-bottom: 0.15rem; }
+    .option .content p { color: var(--text-secondary); font-size: 0.85rem; margin: 0; }
+
+    /* ===== CARDS (for showing designs/mockups) ===== */
+    .cards { display: grid; grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)); gap: 1rem; }
+    .card {
+      background: var(--bg-secondary);
+      border: 1px solid var(--border);
+      border-radius: 12px;
+      overflow: hidden;
+      cursor: pointer;
+      transition: all 0.15s ease;
+    }
+    .card:hover { border-color: var(--accent); transform: translateY(-2px); box-shadow: 0 4px 12px rgba(0,0,0,0.1); }
+    .card.selected { border-color: var(--selected-border); border-width: 2px; }
+    .card-image { background: var(--bg-tertiary); aspect-ratio: 16/10; display: flex; align-items: center; justify-content: center; }
+    .card-body { padding: 1rem; }
+    .card-body h3 { margin-bottom: 0.25rem; }
+    .card-body p { color: var(--text-secondary); font-size: 0.85rem; }
+
+    /* ===== MOCKUP CONTAINER ===== */
+    .mockup {
+      background: var(--bg-secondary);
+      border: 1px solid var(--border);
+      border-radius: 12px;
+      overflow: hidden;
+      margin-bottom: 1.5rem;
+    }
+    .mockup-header {
+      background: var(--bg-tertiary);
+      padding: 0.5rem 1rem;
+      font-size: 0.75rem;
+      color: var(--text-secondary);
+      border-bottom: 1px solid var(--border);
+    }
+    .mockup-body { padding: 1.5rem; }
+
+    /* ===== SPLIT VIEW (side-by-side comparison) ===== */
+    .split { display: grid; grid-template-columns: 1fr 1fr; gap: 1.5rem; }
+    @media (max-width: 700px) { .split { grid-template-columns: 1fr; } }
+
+    /* ===== PROS/CONS ===== */
+    .pros-cons { display: grid; grid-template-columns: 1fr 1fr; gap: 1rem; margin: 1rem 0; }
+    .pros, .cons { background: var(--bg-secondary); border-radius: 8px; padding: 1rem; }
+    .pros h4 { color: var(--success); font-size: 0.85rem; margin-bottom: 0.5rem; }
+    .cons h4 { color: var(--error); font-size: 0.85rem; margin-bottom: 0.5rem; }
+    .pros ul, .cons ul { margin-left: 1.25rem; font-size: 0.85rem; color: var(--text-secondary); }
+    .pros li, .cons li { margin-bottom: 0.25rem; }
+
+    /* ===== PLACEHOLDER (for mockup areas) ===== */
+    .placeholder {
+      background: var(--bg-tertiary);
+      border: 2px dashed var(--border);
+      border-radius: 8px;
+      padding: 2rem;
+      text-align: center;
+      color: var(--text-tertiary);
+    }
+
+    /* ===== INLINE MOCKUP ELEMENTS ===== */
+    .mock-nav { background: var(--accent); color: white; padding: 0.75rem 1rem; display: flex; gap: 1.5rem; font-size: 0.9rem; }
+    .mock-sidebar { background: var(--bg-tertiary); padding: 1rem; min-width: 180px; }
+    .mock-content { padding: 1.5rem; flex: 1; }
+    .mock-button { background: var(--accent); color: white; border: none; padding: 0.5rem 1rem; border-radius: 6px; font-size: 0.85rem; }
+    .mock-input { background: var(--bg-primary); border: 1px solid var(--border); border-radius: 6px; padding: 0.5rem; width: 100%; }
+  </style>
+</head>
+<body>
+  <div class="header">
+    <h1><a href="https://github.com/obra/superpowers" style="color: inherit; text-decoration: none;">Superpowers Brainstorming</a></h1>
+    <div class="status">Connected</div>
+  </div>
+
+  <div class="main">
+    <div id="claude-content">
+      <!-- CONTENT -->
+    </div>
+  </div>
+
+  <div class="indicator-bar">
+    <span id="indicator-text">Click an option above, then return to the terminal</span>
+  </div>
+
+</body>
+</html>

.agents/skills/brainstorming/scripts/helper.js

@@ -0,0 +1,88 @@
+(function() {
+  const WS_URL = 'ws://' + window.location.host;
+  let ws = null;
+  let eventQueue = [];
+
+  function connect() {
+    ws = new WebSocket(WS_URL);
+
+    ws.onopen = () => {
+      eventQueue.forEach(e => ws.send(JSON.stringify(e)));
+      eventQueue = [];
+    };
+
+    ws.onmessage = (msg) => {
+      const data = JSON.parse(msg.data);
+      if (data.type === 'reload') {
+        window.location.reload();
+      }
+    };
+
+    ws.onclose = () => {
+      setTimeout(connect, 1000);
+    };
+  }
+
+  function sendEvent(event) {
+    event.timestamp = Date.now();
+    if (ws && ws.readyState === WebSocket.OPEN) {
+      ws.send(JSON.stringify(event));
+    } else {
+      eventQueue.push(event);
+    }
+  }
+
+  // Capture clicks on choice elements
+  document.addEventListener('click', (e) => {
+    const target = e.target.closest('[data-choice]');
+    if (!target) return;
+
+    sendEvent({
+      type: 'click',
+      text: target.textContent.trim(),
+      choice: target.dataset.choice,
+      id: target.id || null
+    });
+
+    // Update indicator bar (defer so toggleSelect runs first)
+    setTimeout(() => {
+      const indicator = document.getElementById('indicator-text');
+      if (!indicator) return;
+      const container = target.closest('.options') || target.closest('.cards');
+      const selected = container ? container.querySelectorAll('.selected') : [];
+      if (selected.length === 0) {
+        indicator.textContent = 'Click an option above, then return to the terminal';
+      } else if (selected.length === 1) {
+        const label = selected[0].querySelector('h3, .content h3, .card-body h3')?.textContent?.trim() || selected[0].dataset.choice;
+        indicator.innerHTML = '<span class="selected-text">' + label + ' selected</span> — return to terminal to continue';
+      } else {
+        indicator.innerHTML = '<span class="selected-text">' + selected.length + ' selected</span> — return to terminal to continue';
+      }
+    }, 0);
+  });
+
+  // Frame UI: selection tracking
+  window.selectedChoice = null;
+
+  window.toggleSelect = function(el) {
+    const container = el.closest('.options') || el.closest('.cards');
+    const multi = container && container.dataset.multiselect !== undefined;
+    if (container && !multi) {
+      container.querySelectorAll('.option, .card').forEach(o => o.classList.remove('selected'));
+    }
+    if (multi) {
+      el.classList.toggle('selected');
+    } else {
+      el.classList.add('selected');
+    }
+    window.selectedChoice = el.dataset.choice;
+  };
+
+  // Expose API for explicit use
+  window.brainstorm = {
+    send: sendEvent,
+    choice: (value, metadata = {}) => sendEvent({ type: 'choice', value, ...metadata })
+  };
+
+  connect();
+})();

.agents/skills/brainstorming/scripts/server.cjs

@@ -0,0 +1,354 @@
+const crypto = require('crypto');
+const http = require('http');
+const fs = require('fs');
+const path = require('path');
+
+// ========== WebSocket Protocol (RFC 6455) ==========
+
+const OPCODES = { TEXT: 0x01, CLOSE: 0x08, PING: 0x09, PONG: 0x0A };
+const WS_MAGIC = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11';
+
+function computeAcceptKey(clientKey) {
+  return crypto.createHash('sha1').update(clientKey + WS_MAGIC).digest('base64');
+}
+
+function encodeFrame(opcode, payload) {
+  const fin = 0x80;
+  const len = payload.length;
+  let header;
+
+  if (len < 126) {
+    header = Buffer.alloc(2);
+    header[0] = fin | opcode;
+    header[1] = len;
+  } else if (len < 65536) {
+    header = Buffer.alloc(4);
+    header[0] = fin | opcode;
+    header[1] = 126;
+    header.writeUInt16BE(len, 2);
+  } else {
+    header = Buffer.alloc(10);
+    header[0] = fin | opcode;
+    header[1] = 127;
+    header.writeBigUInt64BE(BigInt(len), 2);
+  }
+
+  return Buffer.concat([header, payload]);
+}
+
+function decodeFrame(buffer) {
+  if (buffer.length < 2) return null;
+
+  const secondByte = buffer[1];
+  const opcode = buffer[0] & 0x0F;
+  const masked = (secondByte & 0x80) !== 0;
+  let payloadLen = secondByte & 0x7F;
+  let offset = 2;
+
+  if (!masked) throw new Error('Client frames must be masked');
+
+  if (payloadLen === 126) {
+    if (buffer.length < 4) return null;
+    payloadLen = buffer.readUInt16BE(2);
+    offset = 4;
+  } else if (payloadLen === 127) {
+    if (buffer.length < 10) return null;
+    payloadLen = Number(buffer.readBigUInt64BE(2));
+    offset = 10;
+  }
+
+  const maskOffset = offset;
+  const dataOffset = offset + 4;
+  const totalLen = dataOffset + payloadLen;
+  if (buffer.length < totalLen) return null;
+
+  const mask = buffer.slice(maskOffset, dataOffset);
+  const data = Buffer.alloc(payloadLen);
+  for (let i = 0; i < payloadLen; i++) {
+    data[i] = buffer[dataOffset + i] ^ mask[i % 4];
+  }
+
+  return { opcode, payload: data, bytesConsumed: totalLen };
+}
+
+// ========== Configuration ==========
+
+const PORT = process.env.BRAINSTORM_PORT || (49152 + Math.floor(Math.random() * 16383));
+const HOST = process.env.BRAINSTORM_HOST || '127.0.0.1';
+const URL_HOST = process.env.BRAINSTORM_URL_HOST || (HOST === '127.0.0.1' ? 'localhost' : HOST);
+const SESSION_DIR = process.env.BRAINSTORM_DIR || '/tmp/brainstorm';
+const CONTENT_DIR = path.join(SESSION_DIR, 'content');
+const STATE_DIR = path.join(SESSION_DIR, 'state');
+let ownerPid = process.env.BRAINSTORM_OWNER_PID ? Number(process.env.BRAINSTORM_OWNER_PID) : null;
+
+const MIME_TYPES = {
+  '.html': 'text/html', '.css': 'text/css', '.js': 'application/javascript',
+  '.json': 'application/json', '.png': 'image/png', '.jpg': 'image/jpeg',
+  '.jpeg': 'image/jpeg', '.gif': 'image/gif', '.svg': 'image/svg+xml'
+};
+
+// ========== Templates and Constants ==========
+
+const WAITING_PAGE = `<!DOCTYPE html>
+<html>
+<head><meta charset="utf-8"><title>Brainstorm Companion</title>
+<style>body { font-family: system-ui, sans-serif; padding: 2rem; max-width: 800px; margin: 0 auto; }
+h1 { color: #333; } p { color: #666; }</style>
+</head>
+<body><h1>Brainstorm Companion</h1>
+<p>Waiting for the agent to push a screen...</p></body></html>`;
+
+const frameTemplate = fs.readFileSync(path.join(__dirname, 'frame-template.html'), 'utf-8');
+const helperScript = fs.readFileSync(path.join(__dirname, 'helper.js'), 'utf-8');
+const helperInjection = '<script>\n' + helperScript + '\n</script>';
+
+// ========== Helper Functions ==========
+
+function isFullDocument(html) {
+  const trimmed = html.trimStart().toLowerCase();
+  return trimmed.startsWith('<!doctype') || trimmed.startsWith('<html');
+}
+
+function wrapInFrame(content) {
+  return frameTemplate.replace('<!-- CONTENT -->', content);
+}
+
+function getNewestScreen() {
+  const files = fs.readdirSync(CONTENT_DIR)
+    .filter(f => f.endsWith('.html'))
+    .map(f => {
+      const fp = path.join(CONTENT_DIR, f);
+      return { path: fp, mtime: fs.statSync(fp).mtime.getTime() };
+    })
+    .sort((a, b) => b.mtime - a.mtime);
+  return files.length > 0 ? files[0].path : null;
+}
+
+// ========== HTTP Request Handler ==========
+
+function handleRequest(req, res) {
+  touchActivity();
+  if (req.method === 'GET' && req.url === '/') {
+    const screenFile = getNewestScreen();
+    let html = screenFile
+      ? (raw => isFullDocument(raw) ? raw : wrapInFrame(raw))(fs.readFileSync(screenFile, 'utf-8'))
+      : WAITING_PAGE;
+
+    if (html.includes('</body>')) {
+      html = html.replace('</body>', helperInjection + '\n</body>');
+    } else {
+      html += helperInjection;
+    }
+
+    res.writeHead(200, { 'Content-Type': 'text/html; charset=utf-8' });
+    res.end(html);
+  } else if (req.method === 'GET' && req.url.startsWith('/files/')) {
+    const fileName = req.url.slice(7);
+    const filePath = path.join(CONTENT_DIR, path.basename(fileName));
+    if (!fs.existsSync(filePath)) {
+      res.writeHead(404);
+      res.end('Not found');
+      return;
+    }
+    const ext = path.extname(filePath).toLowerCase();
+    const contentType = MIME_TYPES[ext] || 'application/octet-stream';
+    res.writeHead(200, { 'Content-Type': contentType });
+    res.end(fs.readFileSync(filePath));
+  } else {
+    res.writeHead(404);
+    res.end('Not found');
+  }
+}
+
+// ========== WebSocket Connection Handling ==========
+
+const clients = new Set();
+
+function handleUpgrade(req, socket) {
+  const key = req.headers['sec-websocket-key'];
+  if (!key) { socket.destroy(); return; }
+
+  const accept = computeAcceptKey(key);
+  socket.write(
+    'HTTP/1.1 101 Switching Protocols\r\n' +
+    'Upgrade: websocket\r\n' +
+    'Connection: Upgrade\r\n' +
+    'Sec-WebSocket-Accept: ' + accept + '\r\n\r\n'
+  );
+
+  let buffer = Buffer.alloc(0);
+  clients.add(socket);
+
+  socket.on('data', (chunk) => {
+    buffer = Buffer.concat([buffer, chunk]);
+    while (buffer.length > 0) {
+      let result;
+      try {
+        result = decodeFrame(buffer);
+      } catch (e) {
+        socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
+        clients.delete(socket);
+        return;
+      }
+      if (!result) break;
+      buffer = buffer.slice(result.bytesConsumed);
+
+      switch (result.opcode) {
+        case OPCODES.TEXT:
+          handleMessage(result.payload.toString());
+          break;
+        case OPCODES.CLOSE:
+          socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
+          clients.delete(socket);
+          return;
+        case OPCODES.PING:
+          socket.write(encodeFrame(OPCODES.PONG, result.payload));
+          break;
+        case OPCODES.PONG:
+          break;
+        default: {
+          const closeBuf = Buffer.alloc(2);
+          closeBuf.writeUInt16BE(1003);
+          socket.end(encodeFrame(OPCODES.CLOSE, closeBuf));
+          clients.delete(socket);
+          return;
+        }
+      }
+    }
+  });
+
+  socket.on('close', () => clients.delete(socket));
+  socket.on('error', () => clients.delete(socket));
+}
+
+function handleMessage(text) {
+  let event;
+  try {
+    event = JSON.parse(text);
+  } catch (e) {
+    console.error('Failed to parse WebSocket message:', e.message);
+    return;
+  }
+  touchActivity();
+  console.log(JSON.stringify({ source: 'user-event', ...event }));
+  if (event.choice) {
+    const eventsFile = path.join(STATE_DIR, 'events');
+    fs.appendFileSync(eventsFile, JSON.stringify(event) + '\n');
+  }
+}
+
+function broadcast(msg) {
+  const frame = encodeFrame(OPCODES.TEXT, Buffer.from(JSON.stringify(msg)));
+  for (const socket of clients) {
+    try { socket.write(frame); } catch (e) { clients.delete(socket); }
+  }
+}
+
+// ========== Activity Tracking ==========
+
+const IDLE_TIMEOUT_MS = 30 * 60 * 1000; // 30 minutes
+let lastActivity = Date.now();
+
+function touchActivity() {
+  lastActivity = Date.now();
+}
+
+// ========== File Watching ==========
+
+const debounceTimers = new Map();
+
+// ========== Server Startup ==========
+
+function startServer() {
+  if (!fs.existsSync(CONTENT_DIR)) fs.mkdirSync(CONTENT_DIR, { recursive: true });
+  if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
+
+  // Track known files to distinguish new screens from updates.
+  // macOS fs.watch reports 'rename' for both new files and overwrites,
+  // so we can't rely on eventType alone.
+  const knownFiles = new Set(
+    fs.readdirSync(CONTENT_DIR).filter(f => f.endsWith('.html'))
+  );
+
+  const server = http.createServer(handleRequest);
+  server.on('upgrade', handleUpgrade);
+
+  const watcher = fs.watch(CONTENT_DIR, (eventType, filename) => {
+    if (!filename || !filename.endsWith('.html')) return;
+
+    if (debounceTimers.has(filename)) clearTimeout(debounceTimers.get(filename));
+    debounceTimers.set(filename, setTimeout(() => {
+      debounceTimers.delete(filename);
+      const filePath = path.join(CONTENT_DIR, filename);
+
+      if (!fs.existsSync(filePath)) return; // file was deleted
+      touchActivity();
+
+      if (!knownFiles.has(filename)) {
+        knownFiles.add(filename);
+        const eventsFile = path.join(STATE_DIR, 'events');
+        if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
+        console.log(JSON.stringify({ type: 'screen-added', file: filePath }));
+      } else {
+        console.log(JSON.stringify({ type: 'screen-updated', file: filePath }));
+      }
+
+      broadcast({ type: 'reload' });
+    }, 100));
+  });
+  watcher.on('error', (err) => console.error('fs.watch error:', err.message));
+
+  function shutdown(reason) {
+    console.log(JSON.stringify({ type: 'server-stopped', reason }));
+    const infoFile = path.join(STATE_DIR, 'server-info');
+    if (fs.existsSync(infoFile)) fs.unlinkSync(infoFile);
+    fs.writeFileSync(
+      path.join(STATE_DIR, 'server-stopped'),
+      JSON.stringify({ reason, timestamp: Date.now() }) + '\n'
+    );
+    watcher.close();
+    clearInterval(lifecycleCheck);
+    server.close(() => process.exit(0));
+  }
+
+  function ownerAlive() {
+    if (!ownerPid) return true;
+    try { process.kill(ownerPid, 0); return true; } catch (e) { return e.code === 'EPERM'; }
+  }
+
+  // Check every 60s: exit if owner process died or idle for 30 minutes
+  const lifecycleCheck = setInterval(() => {
+    if (!ownerAlive()) shutdown('owner process exited');
+    else if (Date.now() - lastActivity > IDLE_TIMEOUT_MS) shutdown('idle timeout');
+  }, 60 * 1000);
+  lifecycleCheck.unref();
+
+  // Validate owner PID at startup. If it's already dead, the PID resolution
+  // was wrong (common on WSL, Tailscale SSH, and cross-user scenarios).
+  // Disable monitoring and rely on the idle timeout instead.
+  if (ownerPid) {
+    try { process.kill(ownerPid, 0); }
+    catch (e) {
+      if (e.code !== 'EPERM') {
+        console.log(JSON.stringify({ type: 'owner-pid-invalid', pid: ownerPid, reason: 'dead at startup' }));
+        ownerPid = null;
+      }
+    }
+  }
+
+  server.listen(PORT, HOST, () => {
+    const info = JSON.stringify({
+      type: 'server-started', port: Number(PORT), host: HOST,
+      url_host: URL_HOST, url: 'http://' + URL_HOST + ':' + PORT,
+      screen_dir: CONTENT_DIR, state_dir: STATE_DIR
+    });
+    console.log(info);
+    fs.writeFileSync(path.join(STATE_DIR, 'server-info'), info + '\n');
+  });
+}
+
+if (require.main === module) {
+  startServer();
+}
+
+module.exports = { computeAcceptKey, encodeFrame, decodeFrame, OPCODES };

.agents/skills/brainstorming/scripts/start-server.sh

@@ -0,0 +1,148 @@
+#!/usr/bin/env bash
+# Start the brainstorm server and output connection info
+# Usage: start-server.sh [--project-dir <path>] [--host <bind-host>] [--url-host <display-host>] [--foreground] [--background]
+#
+# Starts server on a random high port, outputs JSON with URL.
+# Each session gets its own directory to avoid conflicts.
+#
+# Options:
+#   --project-dir <path>  Store session files under <path>/.superpowers/brainstorm/
+#                         instead of /tmp. Files persist after server stops.
+#   --host <bind-host>    Host/interface to bind (default: 127.0.0.1).
+#                         Use 0.0.0.0 in remote/containerized environments.
+#   --url-host <host>     Hostname shown in returned URL JSON.
+#   --foreground          Run server in the current terminal (no backgrounding).
+#   --background          Force background mode (overrides Codex auto-foreground).
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# Parse arguments
+PROJECT_DIR=""
+FOREGROUND="false"
+FORCE_BACKGROUND="false"
+BIND_HOST="127.0.0.1"
+URL_HOST=""
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --project-dir)
+      PROJECT_DIR="$2"
+      shift 2
+      ;;
+    --host)
+      BIND_HOST="$2"
+      shift 2
+      ;;
+    --url-host)
+      URL_HOST="$2"
+      shift 2
+      ;;
+    --foreground|--no-daemon)
+      FOREGROUND="true"
+      shift
+      ;;
+    --background|--daemon)
+      FORCE_BACKGROUND="true"
+      shift
+      ;;
+    *)
+      echo "{\"error\": \"Unknown argument: $1\"}"
+      exit 1
+      ;;
+  esac
+done
+
+if [[ -z "$URL_HOST" ]]; then
+  if [[ "$BIND_HOST" == "127.0.0.1" || "$BIND_HOST" == "localhost" ]]; then
+    URL_HOST="localhost"
+  else
+    URL_HOST="$BIND_HOST"
+  fi
+fi
+
+# Some environments reap detached/background processes. Auto-foreground when detected.
+if [[ -n "${CODEX_CI:-}" && "$FOREGROUND" != "true" && "$FORCE_BACKGROUND" != "true" ]]; then
+  FOREGROUND="true"
+fi
+
+# Windows/Git Bash reaps nohup background processes. Auto-foreground when detected.
+if [[ "$FOREGROUND" != "true" && "$FORCE_BACKGROUND" != "true" ]]; then
+  case "${OSTYPE:-}" in
+    msys*|cygwin*|mingw*) FOREGROUND="true" ;;
+  esac
+  if [[ -n "${MSYSTEM:-}" ]]; then
+    FOREGROUND="true"
+  fi
+fi
+
+# Generate unique session directory
+SESSION_ID="$$-$(date +%s)"
+
+if [[ -n "$PROJECT_DIR" ]]; then
+  SESSION_DIR="${PROJECT_DIR}/.superpowers/brainstorm/${SESSION_ID}"
+else
+  SESSION_DIR="/tmp/brainstorm-${SESSION_ID}"
+fi
+
+STATE_DIR="${SESSION_DIR}/state"
+PID_FILE="${STATE_DIR}/server.pid"
+LOG_FILE="${STATE_DIR}/server.log"
+
+# Create fresh session directory with content and state peers
+mkdir -p "${SESSION_DIR}/content" "$STATE_DIR"
+
+# Kill any existing server
+if [[ -f "$PID_FILE" ]]; then
+  old_pid=$(cat "$PID_FILE")
+  kill "$old_pid" 2>/dev/null
+  rm -f "$PID_FILE"
+fi
+
+cd "$SCRIPT_DIR"
+
+# Resolve the harness PID (grandparent of this script).
+# $PPID is the ephemeral shell the harness spawned to run us — it dies
+# when this script exits. The harness itself is $PPID's parent.
+OWNER_PID="$(ps -o ppid= -p "$PPID" 2>/dev/null | tr -d ' ')"
+if [[ -z "$OWNER_PID" || "$OWNER_PID" == "1" ]]; then
+  OWNER_PID="$PPID"
+fi
+
+# Foreground mode for environments that reap detached/background processes.
+if [[ "$FOREGROUND" == "true" ]]; then
+  echo "$$" > "$PID_FILE"
+  env BRAINSTORM_DIR="$SESSION_DIR" BRAINSTORM_HOST="$BIND_HOST" BRAINSTORM_URL_HOST="$URL_HOST" BRAINSTORM_OWNER_PID="$OWNER_PID" node server.cjs
+  exit $?
+fi
+
+# Start server, capturing output to log file
+# Use nohup to survive shell exit; disown to remove from job table
+nohup env BRAINSTORM_DIR="$SESSION_DIR" BRAINSTORM_HOST="$BIND_HOST" BRAINSTORM_URL_HOST="$URL_HOST" BRAINSTORM_OWNER_PID="$OWNER_PID" node server.cjs > "$LOG_FILE" 2>&1 &
+SERVER_PID=$!
+disown "$SERVER_PID" 2>/dev/null
+echo "$SERVER_PID" > "$PID_FILE"
+
+# Wait for server-started message (check log file)
+for i in {1..50}; do
+  if grep -q "server-started" "$LOG_FILE" 2>/dev/null; then
+    # Verify server is still alive after a short window (catches process reapers)
+    alive="true"
+    for _ in {1..20}; do
+      if ! kill -0 "$SERVER_PID" 2>/dev/null; then
+        alive="false"
+        break
+      fi
+      sleep 0.1
+    done
+    if [[ "$alive" != "true" ]]; then
+      echo "{\"error\": \"Server started but was killed. Retry in a persistent terminal with: $SCRIPT_DIR/start-server.sh${PROJECT_DIR:+ --project-dir $PROJECT_DIR} --host $BIND_HOST --url-host $URL_HOST --foreground\"}"
+      exit 1
+    fi
+    grep "server-started" "$LOG_FILE" | head -1
+    exit 0
+  fi
+  sleep 0.1
+done
+
+# Timeout - server didn't start
+echo '{"error": "Server failed to start within 5 seconds"}'
+exit 1

.agents/skills/brainstorming/scripts/stop-server.sh

@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+# Stop the brainstorm server and clean up
+# Usage: stop-server.sh <session_dir>
+#
+# Kills the server process. Only deletes session directory if it's
+# under /tmp (ephemeral). Persistent directories (.superpowers/) are
+# kept so mockups can be reviewed later.
+
+SESSION_DIR="$1"
+
+if [[ -z "$SESSION_DIR" ]]; then
+  echo '{"error": "Usage: stop-server.sh <session_dir>"}'
+  exit 1
+fi
+
+STATE_DIR="${SESSION_DIR}/state"
+PID_FILE="${STATE_DIR}/server.pid"
+
+if [[ -f "$PID_FILE" ]]; then
+  pid=$(cat "$PID_FILE")
+
+  # Try to stop gracefully, fallback to force if still alive
+  kill "$pid" 2>/dev/null || true
+
+  # Wait for graceful shutdown (up to ~2s)
+  for i in {1..20}; do
+    if ! kill -0 "$pid" 2>/dev/null; then
+      break
+    fi
+    sleep 0.1
+  done
+
+  # If still running, escalate to SIGKILL
+  if kill -0 "$pid" 2>/dev/null; then
+    kill -9 "$pid" 2>/dev/null || true
+
+    # Give SIGKILL a moment to take effect
+    sleep 0.1
+  fi
+
+  if kill -0 "$pid" 2>/dev/null; then
+    echo '{"status": "failed", "error": "process still running"}'
+    exit 1
+  fi
+
+  rm -f "$PID_FILE" "${STATE_DIR}/server.log"
+
+  # Only delete ephemeral /tmp directories
+  if [[ "$SESSION_DIR" == /tmp/* ]]; then
+    rm -rf "$SESSION_DIR"
+  fi
+
+  echo '{"status": "stopped"}'
+else
+  echo '{"status": "not_running"}'
+fi

.agents/skills/brainstorming/spec-document-reviewer-prompt.md

@@ -0,0 +1,49 @@
+# Spec Document Reviewer Prompt Template
+
+Use this template when dispatching a spec document reviewer subagent.
+
+**Purpose:** Verify the spec is complete, consistent, and ready for implementation planning.
+
+**Dispatch after:** Spec document is written to docs/superpowers/specs/
+
+```
+Task tool (general-purpose):
+  description: "Review spec document"
+  prompt: |
+    You are a spec document reviewer. Verify this spec is complete and ready for planning.
+
+    **Spec to review:** [SPEC_FILE_PATH]
+
+    ## What to Check
+
+    | Category | What to Look For |
+    |----------|------------------|
+    | Completeness | TODOs, placeholders, "TBD", incomplete sections |
+    | Consistency | Internal contradictions, conflicting requirements |
+    | Clarity | Requirements ambiguous enough to cause someone to build the wrong thing |
+    | Scope | Focused enough for a single plan — not covering multiple independent subsystems |
+    | YAGNI | Unrequested features, over-engineering |
+
+    ## Calibration
+
+    **Only flag issues that would cause real problems during implementation planning.**
+    A missing section, a contradiction, or a requirement so ambiguous it could be
+    interpreted two different ways — those are issues. Minor wording improvements,
+    stylistic preferences, and "sections less detailed than others" are not.
+
+    Approve unless there are serious gaps that would lead to a flawed plan.
+
+    ## Output Format
+
+    ## Spec Review
+
+    **Status:** Approved | Issues Found
+
+    **Issues (if any):**
+    - [Section X]: [specific issue] - [why it matters for planning]
+
+    **Recommendations (advisory, do not block approval):**
+    - [suggestions for improvement]
+```
+
+**Reviewer returns:** Status, Issues (if any), Recommendations

.agents/skills/brainstorming/visual-companion.md

@@ -0,0 +1,287 @@
+# Visual Companion Guide
+
+Browser-based visual brainstorming companion for showing mockups, diagrams, and options.
+
+## When to Use
+
+Decide per-question, not per-session. The test: **would the user understand this better by seeing it than reading it?**
+
+**Use the browser** when the content itself is visual:
+
+- **UI mockups** — wireframes, layouts, navigation structures, component designs
+- **Architecture diagrams** — system components, data flow, relationship maps
+- **Side-by-side visual comparisons** — comparing two layouts, two color schemes, two design directions
+- **Design polish** — when the question is about look and feel, spacing, visual hierarchy
+- **Spatial relationships** — state machines, flowcharts, entity relationships rendered as diagrams
+
+**Use the terminal** when the content is text or tabular:
+
+- **Requirements and scope questions** — "what does X mean?", "which features are in scope?"
+- **Conceptual A/B/C choices** — picking between approaches described in words
+- **Tradeoff lists** — pros/cons, comparison tables
+- **Technical decisions** — API design, data modeling, architectural approach selection
+- **Clarifying questions** — anything where the answer is words, not a visual preference
+
+A question *about* a UI topic is not automatically a visual question. "What kind of wizard do you want?" is conceptual — use the terminal. "Which of these wizard layouts feels right?" is visual — use the browser.
+
+## How It Works
+
+The server watches a directory for HTML files and serves the newest one to the browser. You write HTML content to `screen_dir`, the user sees it in their browser and can click to select options. Selections are recorded to `state_dir/events` that you read on your next turn.
+
+**Content fragments vs full documents:** If your HTML file starts with `<!DOCTYPE` or `<html`, the server serves it as-is (just injects the helper script). Otherwise, the server automatically wraps your content in the frame template — adding the header, CSS theme, selection indicator, and all interactive infrastructure. **Write content fragments by default.** Only write full documents when you need complete control over the page.
+
+## Starting a Session
+
+```bash
+# Start server with persistence (mockups saved to project)
+scripts/start-server.sh --project-dir /path/to/project
+
+# Returns: {"type":"server-started","port":52341,"url":"http://localhost:52341",
+#           "screen_dir":"/path/to/project/.superpowers/brainstorm/12345-1706000000/content",
+#           "state_dir":"/path/to/project/.superpowers/brainstorm/12345-1706000000/state"}
+```
+
+Save `screen_dir` and `state_dir` from the response. Tell user to open the URL.
+
+**Finding connection info:** The server writes its startup JSON to `$STATE_DIR/server-info`. If you launched the server in the background and didn't capture stdout, read that file to get the URL and port. When using `--project-dir`, check `<project>/.superpowers/brainstorm/` for the session directory.
+
+**Note:** Pass the project root as `--project-dir` so mockups persist in `.superpowers/brainstorm/` and survive server restarts. Without it, files go to `/tmp` and get cleaned up. Remind the user to add `.superpowers/` to `.gitignore` if it's not already there.
+
+**Launching the server by platform:**
+
+**Claude Code (macOS / Linux):**
+```bash
+# Default mode works — the script backgrounds the server itself
+scripts/start-server.sh --project-dir /path/to/project
+```
+
+**Claude Code (Windows):**
+```bash
+# Windows auto-detects and uses foreground mode, which blocks the tool call.
+# Use run_in_background: true on the Bash tool call so the server survives
+# across conversation turns.
+scripts/start-server.sh --project-dir /path/to/project
+```
+When calling this via the Bash tool, set `run_in_background: true`. Then read `$STATE_DIR/server-info` on the next turn to get the URL and port.
+
+**Codex:**
+```bash
+# Codex reaps background processes. The script auto-detects CODEX_CI and
+# switches to foreground mode. Run it normally — no extra flags needed.
+scripts/start-server.sh --project-dir /path/to/project
+```
+
+**Gemini CLI:**
+```bash
+# Use --foreground and set is_background: true on your shell tool call
+# so the process survives across turns
+scripts/start-server.sh --project-dir /path/to/project --foreground
+```
+
+**Other environments:** The server must keep running in the background across conversation turns. If your environment reaps detached processes, use `--foreground` and launch the command with your platform's background execution mechanism.
+
+If the URL is unreachable from your browser (common in remote/containerized setups), bind a non-loopback host:
+
+```bash
+scripts/start-server.sh \
+  --project-dir /path/to/project \
+  --host 0.0.0.0 \
+  --url-host localhost
+```
+
+Use `--url-host` to control what hostname is printed in the returned URL JSON.
+
+## The Loop
+
+1. **Check server is alive**, then **write HTML** to a new file in `screen_dir`:
+   - Before each write, check that `$STATE_DIR/server-info` exists. If it doesn't (or `$STATE_DIR/server-stopped` exists), the server has shut down — restart it with `start-server.sh` before continuing. The server auto-exits after 30 minutes of inactivity.
+   - Use semantic filenames: `platform.html`, `visual-style.html`, `layout.html`
+   - **Never reuse filenames** — each screen gets a fresh file
+   - Use Write tool — **never use cat/heredoc** (dumps noise into terminal)
+   - Server automatically serves the newest file
+
+2. **Tell user what to expect and end your turn:**
+   - Remind them of the URL (every step, not just first)
+   - Give a brief text summary of what's on screen (e.g., "Showing 3 layout options for the homepage")
+   - Ask them to respond in the terminal: "Take a look and let me know what you think. Click to select an option if you'd like."
+
+3. **On your next turn** — after the user responds in the terminal:
+   - Read `$STATE_DIR/events` if it exists — this contains the user's browser interactions (clicks, selections) as JSON lines
+   - Merge with the user's terminal text to get the full picture
+   - The terminal message is the primary feedback; `state_dir/events` provides structured interaction data
+
+4. **Iterate or advance** — if feedback changes current screen, write a new file (e.g., `layout-v2.html`). Only move to the next question when the current step is validated.
+
+5. **Unload when returning to terminal** — when the next step doesn't need the browser (e.g., a clarifying question, a tradeoff discussion), push a waiting screen to clear the stale content:
+
+   ```html
+   <!-- filename: waiting.html (or waiting-2.html, etc.) -->
+   <div style="display:flex;align-items:center;justify-content:center;min-height:60vh">
+     <p class="subtitle">Continuing in terminal...</p>
+   </div>
+   ```
+
+   This prevents the user from staring at a resolved choice while the conversation has moved on. When the next visual question comes up, push a new content file as usual.
+
+6. Repeat until done.
+
+## Writing Content Fragments
+
+Write just the content that goes inside the page. The server wraps it in the frame template automatically (header, theme CSS, selection indicator, and all interactive infrastructure).
+
+**Minimal example:**
+
+```html
+<h2>Which layout works better?</h2>
+<p class="subtitle">Consider readability and visual hierarchy</p>
+
+<div class="options">
+  <div class="option" data-choice="a" onclick="toggleSelect(this)">
+    <div class="letter">A</div>
+    <div class="content">
+      <h3>Single Column</h3>
+      <p>Clean, focused reading experience</p>
+    </div>
+  </div>
+  <div class="option" data-choice="b" onclick="toggleSelect(this)">
+    <div class="letter">B</div>
+    <div class="content">
+      <h3>Two Column</h3>
+      <p>Sidebar navigation with main content</p>
+    </div>
+  </div>
+</div>
+```
+
+That's it. No `<html>`, no CSS, no `<script>` tags needed. The server provides all of that.
+
+## CSS Classes Available
+
+The frame template provides these CSS classes for your content:
+
+### Options (A/B/C choices)
+
+```html
+<div class="options">
+  <div class="option" data-choice="a" onclick="toggleSelect(this)">
+    <div class="letter">A</div>
+    <div class="content">
+      <h3>Title</h3>
+      <p>Description</p>
+    </div>
+  </div>
+</div>
+```
+
+**Multi-select:** Add `data-multiselect` to the container to let users select multiple options. Each click toggles the item. The indicator bar shows the count.
+
+```html
+<div class="options" data-multiselect>
+  <!-- same option markup — users can select/deselect multiple -->
+</div>
+```
+
+### Cards (visual designs)
+
+```html
+<div class="cards">
+  <div class="card" data-choice="design1" onclick="toggleSelect(this)">
+    <div class="card-image"><!-- mockup content --></div>
+    <div class="card-body">
+      <h3>Name</h3>
+      <p>Description</p>
+    </div>
+  </div>
+</div>
+```
+
+### Mockup container
+
+```html
+<div class="mockup">
+  <div class="mockup-header">Preview: Dashboard Layout</div>
+  <div class="mockup-body"><!-- your mockup HTML --></div>
+</div>
+```
+
+### Split view (side-by-side)
+
+```html
+<div class="split">
+  <div class="mockup"><!-- left --></div>
+  <div class="mockup"><!-- right --></div>
+</div>
+```
+
+### Pros/Cons
+
+```html
+<div class="pros-cons">
+  <div class="pros"><h4>Pros</h4><ul><li>Benefit</li></ul></div>
+  <div class="cons"><h4>Cons</h4><ul><li>Drawback</li></ul></div>
+</div>
+```
+
+### Mock elements (wireframe building blocks)
+
+```html
+<div class="mock-nav">Logo | Home | About | Contact</div>
+<div style="display: flex;">
+  <div class="mock-sidebar">Navigation</div>
+  <div class="mock-content">Main content area</div>
+</div>
+<button class="mock-button">Action Button</button>
+<input class="mock-input" placeholder="Input field">
+<div class="placeholder">Placeholder area</div>
+```
+
+### Typography and sections
+
+- `h2` — page title
+- `h3` — section heading
+- `.subtitle` — secondary text below title
+- `.section` — content block with bottom margin
+- `.label` — small uppercase label text
+
+## Browser Events Format
+
+When the user clicks options in the browser, their interactions are recorded to `$STATE_DIR/events` (one JSON object per line). The file is cleared automatically when you push a new screen.
+
+```jsonl
+{"type":"click","choice":"a","text":"Option A - Simple Layout","timestamp":1706000101}
+{"type":"click","choice":"c","text":"Option C - Complex Grid","timestamp":1706000108}
+{"type":"click","choice":"b","text":"Option B - Hybrid","timestamp":1706000115}
+```
+
+The full event stream shows the user's exploration path — they may click multiple options before settling. The last `choice` event is typically the final selection, but the pattern of clicks can reveal hesitation or preferences worth asking about.
+
+If `$STATE_DIR/events` doesn't exist, the user didn't interact with the browser — use only their terminal text.
+
+## Design Tips
+
+- **Scale fidelity to the question** — wireframes for layout, polish for polish questions
+- **Explain the question on each page** — "Which layout feels more professional?" not just "Pick one"
+- **Iterate before advancing** — if feedback changes current screen, write a new version
+- **2-4 options max** per screen
+- **Use real content when it matters** — for a photography portfolio, use actual images (Unsplash). Placeholder content obscures design issues.
+- **Keep mockups simple** — focus on layout and structure, not pixel-perfect design
+
+## File Naming
+
+- Use semantic names: `platform.html`, `visual-style.html`, `layout.html`
+- Never reuse filenames — each screen must be a new file
+- For iterations: append version suffix like `layout-v2.html`, `layout-v3.html`
+- Server serves newest file by modification time
+
+## Cleaning Up
+
+```bash
+scripts/stop-server.sh $SESSION_DIR
+```
+
+If the session used `--project-dir`, mockup files persist in `.superpowers/brainstorm/` for later reference. Only `/tmp` sessions get deleted on stop.
+
+## Reference
+
+- Frame template (CSS reference): `scripts/frame-template.html`
+- Helper script (client-side): `scripts/helper.js`

.agents/skills/dispatching-parallel-agents/SKILL.md

@@ -0,0 +1,182 @@
+---
+name: dispatching-parallel-agents
+description: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
+---
+
+# Dispatching Parallel Agents
+
+## Overview
+
+You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
+
+When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.
+
+**Core principle:** Dispatch one agent per independent problem domain. Let them work concurrently.
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Multiple failures?" [shape=diamond];
+    "Are they independent?" [shape=diamond];
+    "Single agent investigates all" [shape=box];
+    "One agent per problem domain" [shape=box];
+    "Can they work in parallel?" [shape=diamond];
+    "Sequential agents" [shape=box];
+    "Parallel dispatch" [shape=box];
+
+    "Multiple failures?" -> "Are they independent?" [label="yes"];
+    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
+    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
+    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
+    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
+}
+```
+
+**Use when:**
+- 3+ test files failing with different root causes
+- Multiple subsystems broken independently
+- Each problem can be understood without context from others
+- No shared state between investigations
+
+**Don't use when:**
+- Failures are related (fix one might fix others)
+- Need to understand full system state
+- Agents would interfere with each other
+
+## The Pattern
+
+### 1. Identify Independent Domains
+
+Group failures by what's broken:
+- File A tests: Tool approval flow
+- File B tests: Batch completion behavior
+- File C tests: Abort functionality
+
+Each domain is independent - fixing tool approval doesn't affect abort tests.
+
+### 2. Create Focused Agent Tasks
+
+Each agent gets:
+- **Specific scope:** One test file or subsystem
+- **Clear goal:** Make these tests pass
+- **Constraints:** Don't change other code
+- **Expected output:** Summary of what you found and fixed
+
+### 3. Dispatch in Parallel
+
+```typescript
+// In Claude Code / AI environment
+Task("Fix agent-tool-abort.test.ts failures")
+Task("Fix batch-completion-behavior.test.ts failures")
+Task("Fix tool-approval-race-conditions.test.ts failures")
+// All three run concurrently
+```
+
+### 4. Review and Integrate
+
+When agents return:
+- Read each summary
+- Verify fixes don't conflict
+- Run full test suite
+- Integrate all changes
+
+## Agent Prompt Structure
+
+Good agent prompts are:
+1. **Focused** - One clear problem domain
+2. **Self-contained** - All context needed to understand the problem
+3. **Specific about output** - What should the agent return?
+
+```markdown
+Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:
+
+1. "should abort tool with partial output capture" - expects 'interrupted at' in message
+2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
+3. "should properly track pendingToolCount" - expects 3 results but gets 0
+
+These are timing/race condition issues. Your task:
+
+1. Read the test file and understand what each test verifies
+2. Identify root cause - timing issues or actual bugs?
+3. Fix by:
+   - Replacing arbitrary timeouts with event-based waiting
+   - Fixing bugs in abort implementation if found
+   - Adjusting test expectations if testing changed behavior
+
+Do NOT just increase timeouts - find the real issue.
+
+Return: Summary of what you found and what you fixed.
+```
+
+## Common Mistakes
+
+**❌ Too broad:** "Fix all the tests" - agent gets lost
+**✅ Specific:** "Fix agent-tool-abort.test.ts" - focused scope
+
+**❌ No context:** "Fix the race condition" - agent doesn't know where
+**✅ Context:** Paste the error messages and test names
+
+**❌ No constraints:** Agent might refactor everything
+**✅ Constraints:** "Do NOT change production code" or "Fix tests only"
+
+**❌ Vague output:** "Fix it" - you don't know what changed
+**✅ Specific:** "Return summary of root cause and changes"
+
+## When NOT to Use
+
+**Related failures:** Fixing one might fix others - investigate together first
+**Need full context:** Understanding requires seeing entire system
+**Exploratory debugging:** You don't know what's broken yet
+**Shared state:** Agents would interfere (editing same files, using same resources)
+
+## Real Example from Session
+
+**Scenario:** 6 test failures across 3 files after major refactoring
+
+**Failures:**
+- agent-tool-abort.test.ts: 3 failures (timing issues)
+- batch-completion-behavior.test.ts: 2 failures (tools not executing)
+- tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)
+
+**Decision:** Independent domains - abort logic separate from batch completion separate from race conditions
+
+**Dispatch:**
+```
+Agent 1 → Fix agent-tool-abort.test.ts
+Agent 2 → Fix batch-completion-behavior.test.ts
+Agent 3 → Fix tool-approval-race-conditions.test.ts
+```
+
+**Results:**
+- Agent 1: Replaced timeouts with event-based waiting
+- Agent 2: Fixed event structure bug (threadId in wrong place)
+- Agent 3: Added wait for async tool execution to complete
+
+**Integration:** All fixes independent, no conflicts, full suite green
+
+**Time saved:** 3 problems solved in parallel vs sequentially
+
+## Key Benefits
+
+1. **Parallelization** - Multiple investigations happen simultaneously
+2. **Focus** - Each agent has narrow scope, less context to track
+3. **Independence** - Agents don't interfere with each other
+4. **Speed** - 3 problems solved in time of 1
+
+## Verification
+
+After agents return:
+1. **Review each summary** - Understand what changed
+2. **Check for conflicts** - Did agents edit same code?
+3. **Run full suite** - Verify all fixes work together
+4. **Spot check** - Agents can make systematic errors
+
+## Real-World Impact
+
+From debugging session (2025-10-03):
+- 6 failures across 3 files
+- 3 agents dispatched in parallel
+- All investigations completed concurrently
+- All fixes integrated successfully
+- Zero conflicts between agent changes

.agents/skills/executing-plans/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: executing-plans
+description: Use when you have a written implementation plan to execute in a separate session with review checkpoints
+---
+
+# Executing Plans
+
+## Overview
+
+Load plan, review critically, execute all tasks, report when complete.
+
+**Announce at start:** "I'm using the executing-plans skill to implement this plan."
+
+**Note:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
+
+## The Process
+
+### Step 1: Load and Review Plan
+1. Read plan file
+2. Review critically - identify any questions or concerns about the plan
+3. If concerns: Raise them with your human partner before starting
+4. If no concerns: Create TodoWrite and proceed
+
+### Step 2: Execute Tasks
+
+For each task:
+1. Mark as in_progress
+2. Follow each step exactly (plan has bite-sized steps)
+3. Run verifications as specified
+4. Mark as completed
+
+### Step 3: Complete Development
+
+After all tasks complete and verified:
+- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
+- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
+- Follow that skill to verify tests, present options, execute choice
+
+## When to Stop and Ask for Help
+
+**STOP executing immediately when:**
+- Hit a blocker (missing dependency, test fails, instruction unclear)
+- Plan has critical gaps preventing starting
+- You don't understand an instruction
+- Verification fails repeatedly
+
+**Ask for clarification rather than guessing.**
+
+## When to Revisit Earlier Steps
+
+**Return to Review (Step 1) when:**
+- Partner updates the plan based on your feedback
+- Fundamental approach needs rethinking
+
+**Don't force through blockers** - stop and ask.
+
+## Remember
+- Review plan critically first
+- Follow plan steps exactly
+- Don't skip verifications
+- Reference skills when plan says to
+- Stop when blocked, don't guess
+- Never start implementation on main/master branch without explicit user consent
+
+## Integration
+
+**Required workflow skills:**
+- **superpowers:using-git-worktrees** - Ensures isolated workspace (creates one or verifies existing)
+- **superpowers:writing-plans** - Creates the plan this skill executes
+- **superpowers:finishing-a-development-branch** - Complete development after all tasks

.agents/skills/finishing-a-development-branch/SKILL.md

@@ -0,0 +1,251 @@
+---
+name: finishing-a-development-branch
+description: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
+---
+
+# Finishing a Development Branch
+
+## Overview
+
+Guide completion of development work by presenting clear options and handling chosen workflow.
+
+**Core principle:** Verify tests → Detect environment → Present options → Execute choice → Clean up.
+
+**Announce at start:** "I'm using the finishing-a-development-branch skill to complete this work."
+
+## The Process
+
+### Step 1: Verify Tests
+
+**Before presenting options, verify tests pass:**
+
+```bash
+# Run project's test suite
+npm test / cargo test / pytest / go test ./...
+```
+
+**If tests fail:**
+```
+Tests failing (<N> failures). Must fix before completing:
+
+[Show failures]
+
+Cannot proceed with merge/PR until tests pass.
+```
+
+Stop. Don't proceed to Step 2.
+
+**If tests pass:** Continue to Step 2.
+
+### Step 2: Detect Environment
+
+**Determine workspace state before presenting options:**
+
+```bash
+GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
+GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
+```
+
+This determines which menu to show and how cleanup works:
+
+| State | Menu | Cleanup |
+|-------|------|---------|
+| `GIT_DIR == GIT_COMMON` (normal repo) | Standard 4 options | No worktree to clean up |
+| `GIT_DIR != GIT_COMMON`, named branch | Standard 4 options | Provenance-based (see Step 6) |
+| `GIT_DIR != GIT_COMMON`, detached HEAD | Reduced 3 options (no merge) | No cleanup (externally managed) |
+
+### Step 3: Determine Base Branch
+
+```bash
+# Try common base branches
+git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null
+```
+
+Or ask: "This branch split from main - is that correct?"
+
+### Step 4: Present Options
+
+**Normal repo and named-branch worktree — present exactly these 4 options:**
+
+```
+Implementation complete. What would you like to do?
+
+1. Merge back to <base-branch> locally
+2. Push and create a Pull Request
+3. Keep the branch as-is (I'll handle it later)
+4. Discard this work
+
+Which option?
+```
+
+**Detached HEAD — present exactly these 3 options:**
+
+```
+Implementation complete. You're on a detached HEAD (externally managed workspace).
+
+1. Push as new branch and create a Pull Request
+2. Keep as-is (I'll handle it later)
+3. Discard this work
+
+Which option?
+```
+
+**Don't add explanation** - keep options concise.
+
+### Step 5: Execute Choice
+
+#### Option 1: Merge Locally
+
+```bash
+# Get main repo root for CWD safety
+MAIN_ROOT=$(git -C "$(git rev-parse --git-common-dir)/.." rev-parse --show-toplevel)
+cd "$MAIN_ROOT"
+
+# Merge first — verify success before removing anything
+git checkout <base-branch>
+git pull
+git merge <feature-branch>
+
+# Verify tests on merged result
+<test command>
+
+# Only after merge succeeds: cleanup worktree (Step 6), then delete branch
+```
+
+Then: Cleanup worktree (Step 6), then delete branch:
+
+```bash
+git branch -d <feature-branch>
+```
+
+#### Option 2: Push and Create PR
+
+```bash
+# Push branch
+git push -u origin <feature-branch>
+
+# Create PR
+gh pr create --title "<title>" --body "$(cat <<'EOF'
+## Summary
+<2-3 bullets of what changed>
+
+## Test Plan
+- [ ] <verification steps>
+EOF
+)"
+```
+
+**Do NOT clean up worktree** — user needs it alive to iterate on PR feedback.
+
+#### Option 3: Keep As-Is
+
+Report: "Keeping branch <name>. Worktree preserved at <path>."
+
+**Don't cleanup worktree.**
+
+#### Option 4: Discard
+
+**Confirm first:**
+```
+This will permanently delete:
+- Branch <name>
+- All commits: <commit-list>
+- Worktree at <path>
+
+Type 'discard' to confirm.
+```
+
+Wait for exact confirmation.
+
+If confirmed:
+```bash
+MAIN_ROOT=$(git -C "$(git rev-parse --git-common-dir)/.." rev-parse --show-toplevel)
+cd "$MAIN_ROOT"
+```
+
+Then: Cleanup worktree (Step 6), then force-delete branch:
+```bash
+git branch -D <feature-branch>
+```
+
+### Step 6: Cleanup Workspace
+
+**Only runs for Options 1 and 4.** Options 2 and 3 always preserve the worktree.
+
+```bash
+GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
+GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
+WORKTREE_PATH=$(git rev-parse --show-toplevel)
+```
+
+**If `GIT_DIR == GIT_COMMON`:** Normal repo, no worktree to clean up. Done.
+
+**If worktree path is under `.worktrees/`, `worktrees/`, or `~/.config/superpowers/worktrees/`:** Superpowers created this worktree — we own cleanup.
+
+```bash
+MAIN_ROOT=$(git -C "$(git rev-parse --git-common-dir)/.." rev-parse --show-toplevel)
+cd "$MAIN_ROOT"
+git worktree remove "$WORKTREE_PATH"
+git worktree prune  # Self-healing: clean up any stale registrations
+```
+
+**Otherwise:** The host environment (harness) owns this workspace. Do NOT remove it. If your platform provides a workspace-exit tool, use it. Otherwise, leave the workspace in place.
+
+## Quick Reference
+
+| Option | Merge | Push | Keep Worktree | Cleanup Branch |
+|--------|-------|------|---------------|----------------|
+| 1. Merge locally | yes | - | - | yes |
+| 2. Create PR | - | yes | yes | - |
+| 3. Keep as-is | - | - | yes | - |
+| 4. Discard | - | - | - | yes (force) |
+
+## Common Mistakes
+
+**Skipping test verification**
+- **Problem:** Merge broken code, create failing PR
+- **Fix:** Always verify tests before offering options
+
+**Open-ended questions**
+- **Problem:** "What should I do next?" is ambiguous
+- **Fix:** Present exactly 4 structured options (or 3 for detached HEAD)
+
+**Cleaning up worktree for Option 2**
+- **Problem:** Remove worktree user needs for PR iteration
+- **Fix:** Only cleanup for Options 1 and 4
+
+**Deleting branch before removing worktree**
+- **Problem:** `git branch -d` fails because worktree still references the branch
+- **Fix:** Merge first, remove worktree, then delete branch
+
+**Running git worktree remove from inside the worktree**
+- **Problem:** Command fails silently when CWD is inside the worktree being removed
+- **Fix:** Always `cd` to main repo root before `git worktree remove`
+
+**Cleaning up harness-owned worktrees**
+- **Problem:** Removing a worktree the harness created causes phantom state
+- **Fix:** Only clean up worktrees under `.worktrees/`, `worktrees/`, or `~/.config/superpowers/worktrees/`
+
+**No confirmation for discard**
+- **Problem:** Accidentally delete work
+- **Fix:** Require typed "discard" confirmation
+
+## Red Flags
+
+**Never:**
+- Proceed with failing tests
+- Merge without verifying tests on result
+- Delete work without confirmation
+- Force-push without explicit request
+- Remove a worktree before confirming merge success
+- Clean up worktrees you didn't create (provenance check)
+- Run `git worktree remove` from inside the worktree
+
+**Always:**
+- Verify tests before offering options
+- Detect environment before presenting menu
+- Present exactly 4 options (or 3 for detached HEAD)
+- Get typed confirmation for Option 4
+- Clean up worktree for Options 1 & 4 only
+- `cd` to main repo root before worktree removal
+- Run `git worktree prune` after removal

.agents/skills/receiving-code-review/SKILL.md

@@ -0,0 +1,213 @@
+---
+name: receiving-code-review
+description: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
+---
+
+# Code Review Reception
+
+## Overview
+
+Code review requires technical evaluation, not emotional performance.
+
+**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
+
+## The Response Pattern
+
+```
+WHEN receiving code review feedback:
+
+1. READ: Complete feedback without reacting
+2. UNDERSTAND: Restate requirement in own words (or ask)
+3. VERIFY: Check against codebase reality
+4. EVALUATE: Technically sound for THIS codebase?
+5. RESPOND: Technical acknowledgment or reasoned pushback
+6. IMPLEMENT: One item at a time, test each
+```
+
+## Forbidden Responses
+
+**NEVER:**
+- "You're absolutely right!" (explicit CLAUDE.md violation)
+- "Great point!" / "Excellent feedback!" (performative)
+- "Let me implement that now" (before verification)
+
+**INSTEAD:**
+- Restate the technical requirement
+- Ask clarifying questions
+- Push back with technical reasoning if wrong
+- Just start working (actions > words)
+
+## Handling Unclear Feedback
+
+```
+IF any item is unclear:
+  STOP - do not implement anything yet
+  ASK for clarification on unclear items
+
+WHY: Items may be related. Partial understanding = wrong implementation.
+```
+
+**Example:**
+```
+your human partner: "Fix 1-6"
+You understand 1,2,3,6. Unclear on 4,5.
+
+❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
+✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."
+```
+
+## Source-Specific Handling
+
+### From your human partner
+- **Trusted** - implement after understanding
+- **Still ask** if scope unclear
+- **No performative agreement**
+- **Skip to action** or technical acknowledgment
+
+### From External Reviewers
+```
+BEFORE implementing:
+  1. Check: Technically correct for THIS codebase?
+  2. Check: Breaks existing functionality?
+  3. Check: Reason for current implementation?
+  4. Check: Works on all platforms/versions?
+  5. Check: Does reviewer understand full context?
+
+IF suggestion seems wrong:
+  Push back with technical reasoning
+
+IF can't easily verify:
+  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"
+
+IF conflicts with your human partner's prior decisions:
+  Stop and discuss with your human partner first
+```
+
+**your human partner's rule:** "External feedback - be skeptical, but check carefully"
+
+## YAGNI Check for "Professional" Features
+
+```
+IF reviewer suggests "implementing properly":
+  grep codebase for actual usage
+
+  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
+  IF used: Then implement properly
+```
+
+**your human partner's rule:** "You and reviewer both report to me. If we don't need this feature, don't add it."
+
+## Implementation Order
+
+```
+FOR multi-item feedback:
+  1. Clarify anything unclear FIRST
+  2. Then implement in this order:
+     - Blocking issues (breaks, security)
+     - Simple fixes (typos, imports)
+     - Complex fixes (refactoring, logic)
+  3. Test each fix individually
+  4. Verify no regressions
+```
+
+## When To Push Back
+
+Push back when:
+- Suggestion breaks existing functionality
+- Reviewer lacks full context
+- Violates YAGNI (unused feature)
+- Technically incorrect for this stack
+- Legacy/compatibility reasons exist
+- Conflicts with your human partner's architectural decisions
+
+**How to push back:**
+- Use technical reasoning, not defensiveness
+- Ask specific questions
+- Reference working tests/code
+- Involve your human partner if architectural
+
+**Signal if uncomfortable pushing back out loud:** "Strange things are afoot at the Circle K"
+
+## Acknowledging Correct Feedback
+
+When feedback IS correct:
+```
+✅ "Fixed. [Brief description of what changed]"
+✅ "Good catch - [specific issue]. Fixed in [location]."
+✅ [Just fix it and show in the code]
+
+❌ "You're absolutely right!"
+❌ "Great point!"
+❌ "Thanks for catching that!"
+❌ "Thanks for [anything]"
+❌ ANY gratitude expression
+```
+
+**Why no thanks:** Actions speak. Just fix it. The code itself shows you heard the feedback.
+
+**If you catch yourself about to write "Thanks":** DELETE IT. State the fix instead.
+
+## Gracefully Correcting Your Pushback
+
+If you pushed back and were wrong:
+```
+✅ "You were right - I checked [X] and it does [Y]. Implementing now."
+✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."
+
+❌ Long apology
+❌ Defending why you pushed back
+❌ Over-explaining
+```
+
+State the correction factually and move on.
+
+## Common Mistakes
+
+| Mistake | Fix |
+|---------|-----|
+| Performative agreement | State requirement or just act |
+| Blind implementation | Verify against codebase first |
+| Batch without testing | One at a time, test each |
+| Assuming reviewer is right | Check if breaks things |
+| Avoiding pushback | Technical correctness > comfort |
+| Partial implementation | Clarify all items first |
+| Can't verify, proceed anyway | State limitation, ask for direction |
+
+## Real Examples
+
+**Performative Agreement (Bad):**
+```
+Reviewer: "Remove legacy code"
+❌ "You're absolutely right! Let me remove that..."
+```
+
+**Technical Verification (Good):**
+```
+Reviewer: "Remove legacy code"
+✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"
+```
+
+**YAGNI (Good):**
+```
+Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
+✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"
+```
+
+**Unclear Item (Good):**
+```
+your human partner: "Fix items 1-6"
+You understand 1,2,3,6. Unclear on 4,5.
+✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."
+```
+
+## GitHub Thread Replies
+
+When replying to inline review comments on GitHub, reply in the comment thread (`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`), not as a top-level PR comment.
+
+## The Bottom Line
+
+**External feedback = suggestions to evaluate, not orders to follow.**
+
+Verify. Question. Then implement.
+
+No performative agreement. Technical rigor always.

.agents/skills/requesting-code-review/SKILL.md

@@ -0,0 +1,103 @@
+---
+name: requesting-code-review
+description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements
+---
+
+# Requesting Code Review
+
+Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
+
+**Core principle:** Review early, review often.
+
+## When to Request Review
+
+**Mandatory:**
+- After each task in subagent-driven development
+- After completing major feature
+- Before merge to main
+
+**Optional but valuable:**
+- When stuck (fresh perspective)
+- Before refactoring (baseline check)
+- After fixing complex bug
+
+## How to Request
+
+**1. Get git SHAs:**
+```bash
+BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
+HEAD_SHA=$(git rev-parse HEAD)
+```
+
+**2. Dispatch code reviewer subagent:**
+
+Use Task tool with `general-purpose` type, fill template at `code-reviewer.md`
+
+**Placeholders:**
+- `{DESCRIPTION}` - Brief summary of what you built
+- `{PLAN_OR_REQUIREMENTS}` - What it should do
+- `{BASE_SHA}` - Starting commit
+- `{HEAD_SHA}` - Ending commit
+
+**3. Act on feedback:**
+- Fix Critical issues immediately
+- Fix Important issues before proceeding
+- Note Minor issues for later
+- Push back if reviewer is wrong (with reasoning)
+
+## Example
+
+```
+[Just completed Task 2: Add verification function]
+
+You: Let me request code review before proceeding.
+
+BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
+HEAD_SHA=$(git rev-parse HEAD)
+
+[Dispatch code reviewer subagent]
+  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
+  PLAN_OR_REQUIREMENTS: Task 2 from docs/superpowers/plans/deployment-plan.md
+  BASE_SHA: a7981ec
+  HEAD_SHA: 3df7661
+
+[Subagent returns]:
+  Strengths: Clean architecture, real tests
+  Issues:
+    Important: Missing progress indicators
+    Minor: Magic number (100) for reporting interval
+  Assessment: Ready to proceed
+
+You: [Fix progress indicators]
+[Continue to Task 3]
+```
+
+## Integration with Workflows
+
+**Subagent-Driven Development:**
+- Review after EACH task
+- Catch issues before they compound
+- Fix before moving to next task
+
+**Executing Plans:**
+- Review after each task or at natural checkpoints
+- Get feedback, apply, continue
+
+**Ad-Hoc Development:**
+- Review before merge
+- Review when stuck
+
+## Red Flags
+
+**Never:**
+- Skip review because "it's simple"
+- Ignore Critical issues
+- Proceed with unfixed Important issues
+- Argue with valid technical feedback
+
+**If reviewer wrong:**
+- Push back with technical reasoning
+- Show code/tests that prove it works
+- Request clarification
+
+See template at: requesting-code-review/code-reviewer.md

.agents/skills/requesting-code-review/code-reviewer.md

@@ -0,0 +1,168 @@
+# Code Reviewer Prompt Template
+
+Use this template when dispatching a code reviewer subagent.
+
+**Purpose:** Review completed work against requirements and code quality standards before it cascades into more work.
+
+```
+Task tool (general-purpose):
+  description: "Review code changes"
+  prompt: |
+    You are a Senior Code Reviewer with expertise in software architecture,
+    design patterns, and best practices. Your job is to review completed work
+    against its plan or requirements and identify issues before they cascade.
+
+    ## What Was Implemented
+
+    {DESCRIPTION}
+
+    ## Requirements / Plan
+
+    {PLAN_OR_REQUIREMENTS}
+
+    ## Git Range to Review
+
+    **Base:** {BASE_SHA}
+    **Head:** {HEAD_SHA}
+
+    ```bash
+    git diff --stat {BASE_SHA}..{HEAD_SHA}
+    git diff {BASE_SHA}..{HEAD_SHA}
+    ```
+
+    ## What to Check
+
+    **Plan alignment:**
+    - Does the implementation match the plan / requirements?
+    - Are deviations justified improvements, or problematic departures?
+    - Is all planned functionality present?
+
+    **Code quality:**
+    - Clean separation of concerns?
+    - Proper error handling?
+    - Type safety where applicable?
+    - DRY without premature abstraction?
+    - Edge cases handled?
+
+    **Architecture:**
+    - Sound design decisions?
+    - Reasonable scalability and performance?
+    - Security concerns?
+    - Integrates cleanly with surrounding code?
+
+    **Testing:**
+    - Tests verify real behavior, not mocks?
+    - Edge cases covered?
+    - Integration tests where they matter?
+    - All tests passing?
+
+    **Production readiness:**
+    - Migration strategy if schema changed?
+    - Backward compatibility considered?
+    - Documentation complete?
+    - No obvious bugs?
+
+    ## Calibration
+
+    Categorize issues by actual severity. Not everything is Critical.
+    Acknowledge what was done well before listing issues — accurate praise
+    helps the implementer trust the rest of the feedback.
+
+    If you find significant deviations from the plan, flag them specifically
+    so the implementer can confirm whether the deviation was intentional.
+    If you find issues with the plan itself rather than the implementation,
+    say so.
+
+    ## Output Format
+
+    ### Strengths
+    [What's well done? Be specific.]
+
+    ### Issues
+
+    #### Critical (Must Fix)
+    [Bugs, security issues, data loss risks, broken functionality]
+
+    #### Important (Should Fix)
+    [Architecture problems, missing features, poor error handling, test gaps]
+
+    #### Minor (Nice to Have)
+    [Code style, optimization opportunities, documentation polish]
+
+    For each issue:
+    - File:line reference
+    - What's wrong
+    - Why it matters
+    - How to fix (if not obvious)
+
+    ### Recommendations
+    [Improvements for code quality, architecture, or process]
+
+    ### Assessment
+
+    **Ready to merge?** [Yes | No | With fixes]
+
+    **Reasoning:** [1-2 sentence technical assessment]
+
+    ## Critical Rules
+
+    **DO:**
+    - Categorize by actual severity
+    - Be specific (file:line, not vague)
+    - Explain WHY each issue matters
+    - Acknowledge strengths
+    - Give a clear verdict
+
+    **DON'T:**
+    - Say "looks good" without checking
+    - Mark nitpicks as Critical
+    - Give feedback on code you didn't actually read
+    - Be vague ("improve error handling")
+    - Avoid giving a clear verdict
+```
+
+**Placeholders:**
+- `{DESCRIPTION}` — brief summary of what was built
+- `{PLAN_OR_REQUIREMENTS}` — what it should do (plan file path, task text, or requirements)
+- `{BASE_SHA}` — starting commit
+- `{HEAD_SHA}` — ending commit
+
+**Reviewer returns:** Strengths, Issues (Critical / Important / Minor), Recommendations, Assessment
+
+## Example Output
+
+```
+### Strengths
+- Clean database schema with proper migrations (db.ts:15-42)
+- Comprehensive test coverage (18 tests, all edge cases)
+- Good error handling with fallbacks (summarizer.ts:85-92)
+
+### Issues
+
+#### Important
+1. **Missing help text in CLI wrapper**
+   - File: index-conversations:1-31
+   - Issue: No --help flag, users won't discover --concurrency
+   - Fix: Add --help case with usage examples
+
+2. **Date validation missing**
+   - File: search.ts:25-27
+   - Issue: Invalid dates silently return no results
+   - Fix: Validate ISO format, throw error with example
+
+#### Minor
+1. **Progress indicators**
+   - File: indexer.ts:130
+   - Issue: No "X of Y" counter for long operations
+   - Impact: Users don't know how long to wait
+
+### Recommendations
+- Add progress reporting for user experience
+- Consider config file for excluded projects (portability)
+
+### Assessment
+
+**Ready to merge: With fixes**
+
+**Reasoning:** Core implementation is solid with good architecture and tests. Important issues (help text, date validation) are easily fixed and don't affect core functionality.
+```

.agents/skills/subagent-driven-development/SKILL.md

@@ -0,0 +1,279 @@
+---
+name: subagent-driven-development
+description: Use when executing implementation plans with independent tasks in the current session
+---
+
+# Subagent-Driven Development
+
+Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
+
+**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
+
+**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
+
+**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Have implementation plan?" [shape=diamond];
+    "Tasks mostly independent?" [shape=diamond];
+    "Stay in this session?" [shape=diamond];
+    "subagent-driven-development" [shape=box];
+    "executing-plans" [shape=box];
+    "Manual execution or brainstorm first" [shape=box];
+
+    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
+    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
+    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
+    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
+    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
+    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
+}
+```
+
+**vs. Executing Plans (parallel session):**
+- Same session (no context switch)
+- Fresh subagent per task (no context pollution)
+- Two-stage review after each task: spec compliance first, then code quality
+- Faster iteration (no human-in-loop between tasks)
+
+## The Process
+
+```dot
+digraph process {
+    rankdir=TB;
+
+    subgraph cluster_per_task {
+        label="Per Task";
+        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
+        "Implementer subagent asks questions?" [shape=diamond];
+        "Answer questions, provide context" [shape=box];
+        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
+        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
+        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
+        "Implementer subagent fixes spec gaps" [shape=box];
+        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
+        "Code quality reviewer subagent approves?" [shape=diamond];
+        "Implementer subagent fixes quality issues" [shape=box];
+        "Mark task complete in TodoWrite" [shape=box];
+    }
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
+    "More tasks remain?" [shape=diamond];
+    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
+    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)";
+    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
+    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
+    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
+    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
+    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
+    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
+    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
+    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
+    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
+    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
+    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
+    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
+    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
+    "Mark task complete in TodoWrite" -> "More tasks remain?";
+    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
+    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
+    "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch";
+}
+```
+
+## Model Selection
+
+Use the least powerful model that can handle each role to conserve cost and increase speed.
+
+**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
+
+**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
+
+**Architecture, design, and review tasks**: use the most capable available model.
+
+**Task complexity signals:**
+- Touches 1-2 files with a complete spec → cheap model
+- Touches multiple files with integration concerns → standard model
+- Requires design judgment or broad codebase understanding → most capable model
+
+## Handling Implementer Status
+
+Implementer subagents report one of four statuses. Handle each appropriately:
+
+**DONE:** Proceed to spec compliance review.
+
+**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
+
+**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
+
+**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
+1. If it's a context problem, provide more context and re-dispatch with the same model
+2. If the task requires more reasoning, re-dispatch with a more capable model
+3. If the task is too large, break it into smaller pieces
+4. If the plan itself is wrong, escalate to the human
+
+**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
+
+## Prompt Templates
+
+- `./implementer-prompt.md` - Dispatch implementer subagent
+- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
+- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent
+
+## Example Workflow
+
+```
+You: I'm using Subagent-Driven Development to execute this plan.
+
+[Read plan file once: docs/superpowers/plans/feature-plan.md]
+[Extract all 5 tasks with full text and context]
+[Create TodoWrite with all tasks]
+
+Task 1: Hook installation script
+
+[Get Task 1 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: "Before I begin - should the hook be installed at user or system level?"
+
+You: "User level (~/.config/superpowers/hooks/)"
+
+Implementer: "Got it. Implementing now..."
+[Later] Implementer:
+  - Implemented install-hook command
+  - Added tests, 5/5 passing
+  - Self-review: Found I missed --force flag, added it
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra
+
+[Get git SHAs, dispatch code quality reviewer]
+Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
+
+[Mark Task 1 complete]
+
+Task 2: Recovery modes
+
+[Get Task 2 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: [No questions, proceeds]
+Implementer:
+  - Added verify/repair modes
+  - 8/8 tests passing
+  - Self-review: All good
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ❌ Issues:
+  - Missing: Progress reporting (spec says "report every 100 items")
+  - Extra: Added --json flag (not requested)
+
+[Implementer fixes issues]
+Implementer: Removed --json flag, added progress reporting
+
+[Spec reviewer reviews again]
+Spec reviewer: ✅ Spec compliant now
+
+[Dispatch code quality reviewer]
+Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
+
+[Implementer fixes]
+Implementer: Extracted PROGRESS_INTERVAL constant
+
+[Code reviewer reviews again]
+Code reviewer: ✅ Approved
+
+[Mark Task 2 complete]
+
+...
+
+[After all tasks]
+[Dispatch final code-reviewer]
+Final reviewer: All requirements met, ready to merge
+
+Done!
+```
+
+## Advantages
+
+**vs. Manual execution:**
+- Subagents follow TDD naturally
+- Fresh context per task (no confusion)
+- Parallel-safe (subagents don't interfere)
+- Subagent can ask questions (before AND during work)
+
+**vs. Executing Plans:**
+- Same session (no handoff)
+- Continuous progress (no waiting)
+- Review checkpoints automatic
+
+**Efficiency gains:**
+- No file reading overhead (controller provides full text)
+- Controller curates exactly what context is needed
+- Subagent gets complete information upfront
+- Questions surfaced before work begins (not after)
+
+**Quality gates:**
+- Self-review catches issues before handoff
+- Two-stage review: spec compliance, then code quality
+- Review loops ensure fixes actually work
+- Spec compliance prevents over/under-building
+- Code quality ensures implementation is well-built
+
+**Cost:**
+- More subagent invocations (implementer + 2 reviewers per task)
+- Controller does more prep work (extracting all tasks upfront)
+- Review loops add iterations
+- But catches issues early (cheaper than debugging later)
+
+## Red Flags
+
+**Never:**
+- Start implementation on main/master branch without explicit user consent
+- Skip reviews (spec compliance OR code quality)
+- Proceed with unfixed issues
+- Dispatch multiple implementation subagents in parallel (conflicts)
+- Make subagent read plan file (provide full text instead)
+- Skip scene-setting context (subagent needs to understand where task fits)
+- Ignore subagent questions (answer before letting them proceed)
+- Accept "close enough" on spec compliance (spec reviewer found issues = not done)
+- Skip review loops (reviewer found issues = implementer fixes = review again)
+- Let implementer self-review replace actual review (both are needed)
+- **Start code quality review before spec compliance is ✅** (wrong order)
+- Move to next task while either review has open issues
+
+**If subagent asks questions:**
+- Answer clearly and completely
+- Provide additional context if needed
+- Don't rush them into implementation
+
+**If reviewer finds issues:**
+- Implementer (same subagent) fixes them
+- Reviewer reviews again
+- Repeat until approved
+- Don't skip the re-review
+
+**If subagent fails task:**
+- Dispatch fix subagent with specific instructions
+- Don't try to fix manually (context pollution)
+
+## Integration
+
+**Required workflow skills:**
+- **superpowers:using-git-worktrees** - Ensures isolated workspace (creates one or verifies existing)
+- **superpowers:writing-plans** - Creates the plan this skill executes
+- **superpowers:requesting-code-review** - Code review template for reviewer subagents
+- **superpowers:finishing-a-development-branch** - Complete development after all tasks
+
+**Subagents should use:**
+- **superpowers:test-driven-development** - Subagents follow TDD for each task
+
+**Alternative workflow:**
+- **superpowers:executing-plans** - Use for parallel session instead of same-session execution

.agents/skills/subagent-driven-development/code-quality-reviewer-prompt.md

@@ -0,0 +1,25 @@
+# Code Quality Reviewer Prompt Template
+
+Use this template when dispatching a code quality reviewer subagent.
+
+**Purpose:** Verify implementation is well-built (clean, tested, maintainable)
+
+**Only dispatch after spec compliance review passes.**
+
+```
+Task tool (general-purpose):
+  Use template at requesting-code-review/code-reviewer.md
+
+  DESCRIPTION: [task summary, from implementer's report]
+  PLAN_OR_REQUIREMENTS: Task N from [plan-file]
+  BASE_SHA: [commit before task]
+  HEAD_SHA: [current commit]
+```
+
+**In addition to standard code quality concerns, the reviewer should check:**
+- Does each file have one clear responsibility with a well-defined interface?
+- Are units decomposed so they can be understood and tested independently?
+- Is the implementation following the file structure from the plan?
+- Did this implementation create new files that are already large, or significantly grow existing files? (Don't flag pre-existing file sizes — focus on what this change contributed.)
+
+**Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment

.agents/skills/subagent-driven-development/implementer-prompt.md

@@ -0,0 +1,113 @@
+# Implementer Subagent Prompt Template
+
+Use this template when dispatching an implementer subagent.
+
+```
+Task tool (general-purpose):
+  description: "Implement Task N: [task name]"
+  prompt: |
+    You are implementing Task N: [task name]
+
+    ## Task Description
+
+    [FULL TEXT of task from plan - paste it here, don't make subagent read file]
+
+    ## Context
+
+    [Scene-setting: where this fits, dependencies, architectural context]
+
+    ## Before You Begin
+
+    If you have questions about:
+    - The requirements or acceptance criteria
+    - The approach or implementation strategy
+    - Dependencies or assumptions
+    - Anything unclear in the task description
+
+    **Ask them now.** Raise any concerns before starting work.
+
+    ## Your Job
+
+    Once you're clear on requirements:
+    1. Implement exactly what the task specifies
+    2. Write tests (following TDD if task says to)
+    3. Verify implementation works
+    4. Commit your work
+    5. Self-review (see below)
+    6. Report back
+
+    Work from: [directory]
+
+    **While you work:** If you encounter something unexpected or unclear, **ask questions**.
+    It's always OK to pause and clarify. Don't guess or make assumptions.
+
+    ## Code Organization
+
+    You reason best about code you can hold in context at once, and your edits are more
+    reliable when files are focused. Keep this in mind:
+    - Follow the file structure defined in the plan
+    - Each file should have one clear responsibility with a well-defined interface
+    - If a file you're creating is growing beyond the plan's intent, stop and report
+      it as DONE_WITH_CONCERNS — don't split files on your own without plan guidance
+    - If an existing file you're modifying is already large or tangled, work carefully
+      and note it as a concern in your report
+    - In existing codebases, follow established patterns. Improve code you're touching
+      the way a good developer would, but don't restructure things outside your task.
+
+    ## When You're in Over Your Head
+
+    It is always OK to stop and say "this is too hard for me." Bad work is worse than
+    no work. You will not be penalized for escalating.
+
+    **STOP and escalate when:**
+    - The task requires architectural decisions with multiple valid approaches
+    - You need to understand code beyond what was provided and can't find clarity
+    - You feel uncertain about whether your approach is correct
+    - The task involves restructuring existing code in ways the plan didn't anticipate
+    - You've been reading file after file trying to understand the system without progress
+
+    **How to escalate:** Report back with status BLOCKED or NEEDS_CONTEXT. Describe
+    specifically what you're stuck on, what you've tried, and what kind of help you need.
+    The controller can provide more context, re-dispatch with a more capable model,
+    or break the task into smaller pieces.
+
+    ## Before Reporting Back: Self-Review
+
+    Review your work with fresh eyes. Ask yourself:
+
+    **Completeness:**
+    - Did I fully implement everything in the spec?
+    - Did I miss any requirements?
+    - Are there edge cases I didn't handle?
+
+    **Quality:**
+    - Is this my best work?
+    - Are names clear and accurate (match what things do, not how they work)?
+    - Is the code clean and maintainable?
+
+    **Discipline:**
+    - Did I avoid overbuilding (YAGNI)?
+    - Did I only build what was requested?
+    - Did I follow existing patterns in the codebase?
+
+    **Testing:**
+    - Do tests actually verify behavior (not just mock behavior)?
+    - Did I follow TDD if required?
+    - Are tests comprehensive?
+
+    If you find issues during self-review, fix them now before reporting.
+
+    ## Report Format
+
+    When done, report:
+    - **Status:** DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
+    - What you implemented (or what you attempted, if blocked)
+    - What you tested and test results
+    - Files changed
+    - Self-review findings (if any)
+    - Any issues or concerns
+
+    Use DONE_WITH_CONCERNS if you completed the work but have doubts about correctness.
+    Use BLOCKED if you cannot complete the task. Use NEEDS_CONTEXT if you need
+    information that wasn't provided. Never silently produce work you're unsure about.
+```

.agents/skills/subagent-driven-development/spec-reviewer-prompt.md

@@ -0,0 +1,61 @@
+# Spec Compliance Reviewer Prompt Template
+
+Use this template when dispatching a spec compliance reviewer subagent.
+
+**Purpose:** Verify implementer built what was requested (nothing more, nothing less)
+
+```
+Task tool (general-purpose):
+  description: "Review spec compliance for Task N"
+  prompt: |
+    You are reviewing whether an implementation matches its specification.
+
+    ## What Was Requested
+
+    [FULL TEXT of task requirements]
+
+    ## What Implementer Claims They Built
+
+    [From implementer's report]
+
+    ## CRITICAL: Do Not Trust the Report
+
+    The implementer finished suspiciously quickly. Their report may be incomplete,
+    inaccurate, or optimistic. You MUST verify everything independently.
+
+    **DO NOT:**
+    - Take their word for what they implemented
+    - Trust their claims about completeness
+    - Accept their interpretation of requirements
+
+    **DO:**
+    - Read the actual code they wrote
+    - Compare actual implementation to requirements line by line
+    - Check for missing pieces they claimed to implement
+    - Look for extra features they didn't mention
+
+    ## Your Job
+
+    Read the implementation code and verify:
+
+    **Missing requirements:**
+    - Did they implement everything that was requested?
+    - Are there requirements they skipped or missed?
+    - Did they claim something works but didn't actually implement it?
+
+    **Extra/unneeded work:**
+    - Did they build things that weren't requested?
+    - Did they over-engineer or add unnecessary features?
+    - Did they add "nice to haves" that weren't in spec?
+
+    **Misunderstandings:**
+    - Did they interpret requirements differently than intended?
+    - Did they solve the wrong problem?
+    - Did they implement the right feature but wrong way?
+
+    **Verify by reading code, not by trusting report.**
+
+    Report:
+    - ✅ Spec compliant (if everything matches after code inspection)
+    - ❌ Issues found: [list specifically what's missing or extra, with file:line references]
+```

.agents/skills/systematic-debugging/CREATION-LOG.md

@@ -0,0 +1,119 @@
+# Creation Log: Systematic Debugging Skill
+
+Reference example of extracting, structuring, and bulletproofing a critical skill.
+
+## Source Material
+
+Extracted debugging framework from `~/.claude/CLAUDE.md`:
+- 4-phase systematic process (Investigation → Pattern Analysis → Hypothesis → Implementation)
+- Core mandate: ALWAYS find root cause, NEVER fix symptoms
+- Rules designed to resist time pressure and rationalization
+
+## Extraction Decisions
+
+**What to include:**
+- Complete 4-phase framework with all rules
+- Anti-shortcuts ("NEVER fix symptom", "STOP and re-analyze")
+- Pressure-resistant language ("even if faster", "even if I seem in a hurry")
+- Concrete steps for each phase
+
+**What to leave out:**
+- Project-specific context
+- Repetitive variations of same rule
+- Narrative explanations (condensed to principles)
+
+## Structure Following skill-creation/SKILL.md
+
+1. **Rich when_to_use** - Included symptoms and anti-patterns
+2. **Type: technique** - Concrete process with steps
+3. **Keywords** - "root cause", "symptom", "workaround", "debugging", "investigation"
+4. **Flowchart** - Decision point for "fix failed" → re-analyze vs add more fixes
+5. **Phase-by-phase breakdown** - Scannable checklist format
+6. **Anti-patterns section** - What NOT to do (critical for this skill)
+
+## Bulletproofing Elements
+
+Framework designed to resist rationalization under pressure:
+
+### Language Choices
+- "ALWAYS" / "NEVER" (not "should" / "try to")
+- "even if faster" / "even if I seem in a hurry"
+- "STOP and re-analyze" (explicit pause)
+- "Don't skip past" (catches the actual behavior)
+
+### Structural Defenses
+- **Phase 1 required** - Can't skip to implementation
+- **Single hypothesis rule** - Forces thinking, prevents shotgun fixes
+- **Explicit failure mode** - "IF your first fix doesn't work" with mandatory action
+- **Anti-patterns section** - Shows exactly what shortcuts look like
+
+### Redundancy
+- Root cause mandate in overview + when_to_use + Phase 1 + implementation rules
+- "NEVER fix symptom" appears 4 times in different contexts
+- Each phase has explicit "don't skip" guidance
+
+## Testing Approach
+
+Created 4 validation tests following skills/meta/testing-skills-with-subagents:
+
+### Test 1: Academic Context (No Pressure)
+- Simple bug, no time pressure
+- **Result:** Perfect compliance, complete investigation
+
+### Test 2: Time Pressure + Obvious Quick Fix
+- User "in a hurry", symptom fix looks easy
+- **Result:** Resisted shortcut, followed full process, found real root cause
+
+### Test 3: Complex System + Uncertainty
+- Multi-layer failure, unclear if can find root cause
+- **Result:** Systematic investigation, traced through all layers, found source
+
+### Test 4: Failed First Fix
+- Hypothesis doesn't work, temptation to add more fixes
+- **Result:** Stopped, re-analyzed, formed new hypothesis (no shotgun)
+
+**All tests passed.** No rationalizations found.
+
+## Iterations
+
+### Initial Version
+- Complete 4-phase framework
+- Anti-patterns section
+- Flowchart for "fix failed" decision
+
+### Enhancement 1: TDD Reference
+- Added link to skills/testing/test-driven-development
+- Note explaining TDD's "simplest code" ≠ debugging's "root cause"
+- Prevents confusion between methodologies
+
+## Final Outcome
+
+Bulletproof skill that:
+- ✅ Clearly mandates root cause investigation
+- ✅ Resists time pressure rationalization
+- ✅ Provides concrete steps for each phase
+- ✅ Shows anti-patterns explicitly
+- ✅ Tested under multiple pressure scenarios
+- ✅ Clarifies relationship to TDD
+- ✅ Ready for use
+
+## Key Insight
+
+**Most important bulletproofing:** Anti-patterns section showing exact shortcuts that feel justified in the moment. When Claude thinks "I'll just add this one quick fix", seeing that exact pattern listed as wrong creates cognitive friction.
+
+## Usage Example
+
+When encountering a bug:
+1. Load skill: skills/debugging/systematic-debugging
+2. Read overview (10 sec) - reminded of mandate
+3. Follow Phase 1 checklist - forced investigation
+4. If tempted to skip - see anti-pattern, stop
+5. Complete all phases - root cause found
+
+**Time investment:** 5-10 minutes
+**Time saved:** Hours of symptom-whack-a-mole
+
+---
+
+*Created: 2025-10-03*
+*Purpose: Reference example for skill extraction and bulletproofing*

.agents/skills/systematic-debugging/SKILL.md

@@ -0,0 +1,296 @@
+---
+name: systematic-debugging
+description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
+---
+
+# Systematic Debugging
+
+## Overview
+
+Random fixes waste time and create new bugs. Quick patches mask underlying issues.
+
+**Core principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
+
+**Violating the letter of this process is violating the spirit of debugging.**
+
+## The Iron Law
+
+```
+NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
+```
+
+If you haven't completed Phase 1, you cannot propose fixes.
+
+## When to Use
+
+Use for ANY technical issue:
+- Test failures
+- Bugs in production
+- Unexpected behavior
+- Performance problems
+- Build failures
+- Integration issues
+
+**Use this ESPECIALLY when:**
+- Under time pressure (emergencies make guessing tempting)
+- "Just one quick fix" seems obvious
+- You've already tried multiple fixes
+- Previous fix didn't work
+- You don't fully understand the issue
+
+**Don't skip when:**
+- Issue seems simple (simple bugs have root causes too)
+- You're in a hurry (rushing guarantees rework)
+- Manager wants it fixed NOW (systematic is faster than thrashing)
+
+## The Four Phases
+
+You MUST complete each phase before proceeding to the next.
+
+### Phase 1: Root Cause Investigation
+
+**BEFORE attempting ANY fix:**
+
+1. **Read Error Messages Carefully**
+   - Don't skip past errors or warnings
+   - They often contain the exact solution
+   - Read stack traces completely
+   - Note line numbers, file paths, error codes
+
+2. **Reproduce Consistently**
+   - Can you trigger it reliably?
+   - What are the exact steps?
+   - Does it happen every time?
+   - If not reproducible → gather more data, don't guess
+
+3. **Check Recent Changes**
+   - What changed that could cause this?
+   - Git diff, recent commits
+   - New dependencies, config changes
+   - Environmental differences
+
+4. **Gather Evidence in Multi-Component Systems**
+
+   **WHEN system has multiple components (CI → build → signing, API → service → database):**
+
+   **BEFORE proposing fixes, add diagnostic instrumentation:**
+   ```
+   For EACH component boundary:
+     - Log what data enters component
+     - Log what data exits component
+     - Verify environment/config propagation
+     - Check state at each layer
+
+   Run once to gather evidence showing WHERE it breaks
+   THEN analyze evidence to identify failing component
+   THEN investigate that specific component
+   ```
+
+   **Example (multi-layer system):**
+   ```bash
+   # Layer 1: Workflow
+   echo "=== Secrets available in workflow: ==="
+   echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}"
+
+   # Layer 2: Build script
+   echo "=== Env vars in build script: ==="
+   env | grep IDENTITY || echo "IDENTITY not in environment"
+
+   # Layer 3: Signing script
+   echo "=== Keychain state: ==="
+   security list-keychains
+   security find-identity -v
+
+   # Layer 4: Actual signing
+   codesign --sign "$IDENTITY" --verbose=4 "$APP"
+   ```
+
+   **This reveals:** Which layer fails (secrets → workflow ✓, workflow → build ✗)
+
+5. **Trace Data Flow**
+
+   **WHEN error is deep in call stack:**
+
+   See `root-cause-tracing.md` in this directory for the complete backward tracing technique.
+
+   **Quick version:**
+   - Where does bad value originate?
+   - What called this with bad value?
+   - Keep tracing up until you find the source
+   - Fix at source, not at symptom
+
+### Phase 2: Pattern Analysis
+
+**Find the pattern before fixing:**
+
+1. **Find Working Examples**
+   - Locate similar working code in same codebase
+   - What works that's similar to what's broken?
+
+2. **Compare Against References**
+   - If implementing pattern, read reference implementation COMPLETELY
+   - Don't skim - read every line
+   - Understand the pattern fully before applying
+
+3. **Identify Differences**
+   - What's different between working and broken?
+   - List every difference, however small
+   - Don't assume "that can't matter"
+
+4. **Understand Dependencies**
+   - What other components does this need?
+   - What settings, config, environment?
+   - What assumptions does it make?
+
+### Phase 3: Hypothesis and Testing
+
+**Scientific method:**
+
+1. **Form Single Hypothesis**
+   - State clearly: "I think X is the root cause because Y"
+   - Write it down
+   - Be specific, not vague
+
+2. **Test Minimally**
+   - Make the SMALLEST possible change to test hypothesis
+   - One variable at a time
+   - Don't fix multiple things at once
+
+3. **Verify Before Continuing**
+   - Did it work? Yes → Phase 4
+   - Didn't work? Form NEW hypothesis
+   - DON'T add more fixes on top
+
+4. **When You Don't Know**
+   - Say "I don't understand X"
+   - Don't pretend to know
+   - Ask for help
+   - Research more
+
+### Phase 4: Implementation
+
+**Fix the root cause, not the symptom:**
+
+1. **Create Failing Test Case**
+   - Simplest possible reproduction
+   - Automated test if possible
+   - One-off test script if no framework
+   - MUST have before fixing
+   - Use the `superpowers:test-driven-development` skill for writing proper failing tests
+
+2. **Implement Single Fix**
+   - Address the root cause identified
+   - ONE change at a time
+   - No "while I'm here" improvements
+   - No bundled refactoring
+
+3. **Verify Fix**
+   - Test passes now?
+   - No other tests broken?
+   - Issue actually resolved?
+
+4. **If Fix Doesn't Work**
+   - STOP
+   - Count: How many fixes have you tried?
+   - If < 3: Return to Phase 1, re-analyze with new information
+   - **If ≥ 3: STOP and question the architecture (step 5 below)**
+   - DON'T attempt Fix #4 without architectural discussion
+
+5. **If 3+ Fixes Failed: Question Architecture**
+
+   **Pattern indicating architectural problem:**
+   - Each fix reveals new shared state/coupling/problem in different place
+   - Fixes require "massive refactoring" to implement
+   - Each fix creates new symptoms elsewhere
+
+   **STOP and question fundamentals:**
+   - Is this pattern fundamentally sound?
+   - Are we "sticking with it through sheer inertia"?
+   - Should we refactor architecture vs. continue fixing symptoms?
+
+   **Discuss with your human partner before attempting more fixes**
+
+   This is NOT a failed hypothesis - this is a wrong architecture.
+
+## Red Flags - STOP and Follow Process
+
+If you catch yourself thinking:
+- "Quick fix for now, investigate later"
+- "Just try changing X and see if it works"
+- "Add multiple changes, run tests"
+- "Skip the test, I'll manually verify"
+- "It's probably X, let me fix that"
+- "I don't fully understand but this might work"
+- "Pattern says X but I'll adapt it differently"
+- "Here are the main problems: [lists fixes without investigation]"
+- Proposing solutions before tracing data flow
+- **"One more fix attempt" (when already tried 2+)**
+- **Each fix reveals new problem in different place**
+
+**ALL of these mean: STOP. Return to Phase 1.**
+
+**If 3+ fixes failed:** Question the architecture (see Phase 4.5)
+
+## your human partner's Signals You're Doing It Wrong
+
+**Watch for these redirections:**
+- "Is that not happening?" - You assumed without verifying
+- "Will it show us...?" - You should have added evidence gathering
+- "Stop guessing" - You're proposing fixes without understanding
+- "Ultrathink this" - Question fundamentals, not just symptoms
+- "We're stuck?" (frustrated) - Your approach isn't working
+
+**When you see these:** STOP. Return to Phase 1.
+
+## Common Rationalizations
+
+| Excuse | Reality |
+|--------|---------|
+| "Issue is simple, don't need process" | Simple issues have root causes too. Process is fast for simple bugs. |
+| "Emergency, no time for process" | Systematic debugging is FASTER than guess-and-check thrashing. |
+| "Just try this first, then investigate" | First fix sets the pattern. Do it right from the start. |
+| "I'll write test after confirming fix works" | Untested fixes don't stick. Test first proves it. |
+| "Multiple fixes at once saves time" | Can't isolate what worked. Causes new bugs. |
+| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. Read it completely. |
+| "I see the problem, let me fix it" | Seeing symptoms ≠ understanding root cause. |
+| "One more fix attempt" (after 2+ failures) | 3+ failures = architectural problem. Question pattern, don't fix again. |
+
+## Quick Reference
+
+| Phase | Key Activities | Success Criteria |
+|-------|---------------|------------------|
+| **1. Root Cause** | Read errors, reproduce, check changes, gather evidence | Understand WHAT and WHY |
+| **2. Pattern** | Find working examples, compare | Identify differences |
+| **3. Hypothesis** | Form theory, test minimally | Confirmed or new hypothesis |
+| **4. Implementation** | Create test, fix, verify | Bug resolved, tests pass |
+
+## When Process Reveals "No Root Cause"
+
+If systematic investigation reveals issue is truly environmental, timing-dependent, or external:
+
+1. You've completed the process
+2. Document what you investigated
+3. Implement appropriate handling (retry, timeout, error message)
+4. Add monitoring/logging for future investigation
+
+**But:** 95% of "no root cause" cases are incomplete investigation.
+
+## Supporting Techniques
+
+These techniques are part of systematic debugging and available in this directory:
+
+- **`root-cause-tracing.md`** - Trace bugs backward through call stack to find original trigger
+- **`defense-in-depth.md`** - Add validation at multiple layers after finding root cause
+- **`condition-based-waiting.md`** - Replace arbitrary timeouts with condition polling
+
+**Related skills:**
+- **superpowers:test-driven-development** - For creating failing test case (Phase 4, Step 1)
+- **superpowers:verification-before-completion** - Verify fix worked before claiming success
+
+## Real-World Impact
+
+From debugging sessions:
+- Systematic approach: 15-30 minutes to fix
+- Random fixes approach: 2-3 hours of thrashing
+- First-time fix rate: 95% vs 40%
+- New bugs introduced: Near zero vs common

.agents/skills/systematic-debugging/condition-based-waiting-example.ts

@@ -0,0 +1,158 @@
+// Complete implementation of condition-based waiting utilities
+// From: Lace test infrastructure improvements (2025-10-03)
+// Context: Fixed 15 flaky tests by replacing arbitrary timeouts
+
+import type { ThreadManager } from '~/threads/thread-manager';
+import type { LaceEvent, LaceEventType } from '~/threads/types';
+
+/**
+ * Wait for a specific event type to appear in thread
+ *
+ * @param threadManager - The thread manager to query
+ * @param threadId - Thread to check for events
+ * @param eventType - Type of event to wait for
+ * @param timeoutMs - Maximum time to wait (default 5000ms)
+ * @returns Promise resolving to the first matching event
+ *
+ * Example:
+ *   await waitForEvent(threadManager, agentThreadId, 'TOOL_RESULT');
+ */
+export function waitForEvent(
+  threadManager: ThreadManager,
+  threadId: string,
+  eventType: LaceEventType,
+  timeoutMs = 5000
+): Promise<LaceEvent> {
+  return new Promise((resolve, reject) => {
+    const startTime = Date.now();
+
+    const check = () => {
+      const events = threadManager.getEvents(threadId);
+      const event = events.find((e) => e.type === eventType);
+
+      if (event) {
+        resolve(event);
+      } else if (Date.now() - startTime > timeoutMs) {
+        reject(new Error(`Timeout waiting for ${eventType} event after ${timeoutMs}ms`));
+      } else {
+        setTimeout(check, 10); // Poll every 10ms for efficiency
+      }
+    };
+
+    check();
+  });
+}
+
+/**
+ * Wait for a specific number of events of a given type
+ *
+ * @param threadManager - The thread manager to query
+ * @param threadId - Thread to check for events
+ * @param eventType - Type of event to wait for
+ * @param count - Number of events to wait for
+ * @param timeoutMs - Maximum time to wait (default 5000ms)
+ * @returns Promise resolving to all matching events once count is reached
+ *
+ * Example:
+ *   // Wait for 2 AGENT_MESSAGE events (initial response + continuation)
+ *   await waitForEventCount(threadManager, agentThreadId, 'AGENT_MESSAGE', 2);
+ */
+export function waitForEventCount(
+  threadManager: ThreadManager,
+  threadId: string,
+  eventType: LaceEventType,
+  count: number,
+  timeoutMs = 5000
+): Promise<LaceEvent[]> {
+  return new Promise((resolve, reject) => {
+    const startTime = Date.now();
+
+    const check = () => {
+      const events = threadManager.getEvents(threadId);
+      const matchingEvents = events.filter((e) => e.type === eventType);
+
+      if (matchingEvents.length >= count) {
+        resolve(matchingEvents);
+      } else if (Date.now() - startTime > timeoutMs) {
+        reject(
+          new Error(
+            `Timeout waiting for ${count} ${eventType} events after ${timeoutMs}ms (got ${matchingEvents.length})`
+          )
+        );
+      } else {
+        setTimeout(check, 10);
+      }
+    };
+
+    check();
+  });
+}
+
+/**
+ * Wait for an event matching a custom predicate
+ * Useful when you need to check event data, not just type
+ *
+ * @param threadManager - The thread manager to query
+ * @param threadId - Thread to check for events
+ * @param predicate - Function that returns true when event matches
+ * @param description - Human-readable description for error messages
+ * @param timeoutMs - Maximum time to wait (default 5000ms)
+ * @returns Promise resolving to the first matching event
+ *
+ * Example:
+ *   // Wait for TOOL_RESULT with specific ID
+ *   await waitForEventMatch(
+ *     threadManager,
+ *     agentThreadId,
+ *     (e) => e.type === 'TOOL_RESULT' && e.data.id === 'call_123',
+ *     'TOOL_RESULT with id=call_123'
+ *   );
+ */
+export function waitForEventMatch(
+  threadManager: ThreadManager,
+  threadId: string,
+  predicate: (event: LaceEvent) => boolean,
+  description: string,
+  timeoutMs = 5000
+): Promise<LaceEvent> {
+  return new Promise((resolve, reject) => {
+    const startTime = Date.now();
+
+    const check = () => {
+      const events = threadManager.getEvents(threadId);
+      const event = events.find(predicate);
+
+      if (event) {
+        resolve(event);
+      } else if (Date.now() - startTime > timeoutMs) {
+        reject(new Error(`Timeout waiting for ${description} after ${timeoutMs}ms`));
+      } else {
+        setTimeout(check, 10);
+      }
+    };
+
+    check();
+  });
+}
+
+// Usage example from actual debugging session:
+//
+// BEFORE (flaky):
+// ---------------
+// const messagePromise = agent.sendMessage('Execute tools');
+// await new Promise(r => setTimeout(r, 300)); // Hope tools start in 300ms
+// agent.abort();
+// await messagePromise;
+// await new Promise(r => setTimeout(r, 50));  // Hope results arrive in 50ms
+// expect(toolResults.length).toBe(2);         // Fails randomly
+//
+// AFTER (reliable):
+// ----------------
+// const messagePromise = agent.sendMessage('Execute tools');
+// await waitForEventCount(threadManager, threadId, 'TOOL_CALL', 2); // Wait for tools to start
+// agent.abort();
+// await messagePromise;
+// await waitForEventCount(threadManager, threadId, 'TOOL_RESULT', 2); // Wait for results
+// expect(toolResults.length).toBe(2); // Always succeeds
+//
+// Result: 60% pass rate → 100%, 40% faster execution

.agents/skills/systematic-debugging/condition-based-waiting.md

@@ -0,0 +1,115 @@
+# Condition-Based Waiting
+
+## Overview
+
+Flaky tests often guess at timing with arbitrary delays. This creates race conditions where tests pass on fast machines but fail under load or in CI.
+
+**Core principle:** Wait for the actual condition you care about, not a guess about how long it takes.
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Test uses setTimeout/sleep?" [shape=diamond];
+    "Testing timing behavior?" [shape=diamond];
+    "Document WHY timeout needed" [shape=box];
+    "Use condition-based waiting" [shape=box];
+
+    "Test uses setTimeout/sleep?" -> "Testing timing behavior?" [label="yes"];
+    "Testing timing behavior?" -> "Document WHY timeout needed" [label="yes"];
+    "Testing timing behavior?" -> "Use condition-based waiting" [label="no"];
+}
+```
+
+**Use when:**
+- Tests have arbitrary delays (`setTimeout`, `sleep`, `time.sleep()`)
+- Tests are flaky (pass sometimes, fail under load)
+- Tests timeout when run in parallel
+- Waiting for async operations to complete
+
+**Don't use when:**
+- Testing actual timing behavior (debounce, throttle intervals)
+- Always document WHY if using arbitrary timeout
+
+## Core Pattern
+
+```typescript
+// ❌ BEFORE: Guessing at timing
+await new Promise(r => setTimeout(r, 50));
+const result = getResult();
+expect(result).toBeDefined();
+
+// ✅ AFTER: Waiting for condition
+await waitFor(() => getResult() !== undefined);
+const result = getResult();
+expect(result).toBeDefined();
+```
+
+## Quick Patterns
+
+| Scenario | Pattern |
+|----------|---------|
+| Wait for event | `waitFor(() => events.find(e => e.type === 'DONE'))` |
+| Wait for state | `waitFor(() => machine.state === 'ready')` |
+| Wait for count | `waitFor(() => items.length >= 5)` |
+| Wait for file | `waitFor(() => fs.existsSync(path))` |
+| Complex condition | `waitFor(() => obj.ready && obj.value > 10)` |
+
+## Implementation
+
+Generic polling function:
+```typescript
+async function waitFor<T>(
+  condition: () => T | undefined | null | false,
+  description: string,
+  timeoutMs = 5000
+): Promise<T> {
+  const startTime = Date.now();
+
+  while (true) {
+    const result = condition();
+    if (result) return result;
+
+    if (Date.now() - startTime > timeoutMs) {
+      throw new Error(`Timeout waiting for ${description} after ${timeoutMs}ms`);
+    }
+
+    await new Promise(r => setTimeout(r, 10)); // Poll every 10ms
+  }
+}
+```
+
+See `condition-based-waiting-example.ts` in this directory for complete implementation with domain-specific helpers (`waitForEvent`, `waitForEventCount`, `waitForEventMatch`) from actual debugging session.
+
+## Common Mistakes
+
+**❌ Polling too fast:** `setTimeout(check, 1)` - wastes CPU
+**✅ Fix:** Poll every 10ms
+
+**❌ No timeout:** Loop forever if condition never met
+**✅ Fix:** Always include timeout with clear error
+
+**❌ Stale data:** Cache state before loop
+**✅ Fix:** Call getter inside loop for fresh data
+
+## When Arbitrary Timeout IS Correct
+
+```typescript
+// Tool ticks every 100ms - need 2 ticks to verify partial output
+await waitForEvent(manager, 'TOOL_STARTED'); // First: wait for condition
+await new Promise(r => setTimeout(r, 200));   // Then: wait for timed behavior
+// 200ms = 2 ticks at 100ms intervals - documented and justified
+```
+
+**Requirements:**
+1. First wait for triggering condition
+2. Based on known timing (not guessing)
+3. Comment explaining WHY
+
+## Real-World Impact
+
+From debugging session (2025-10-03):
+- Fixed 15 flaky tests across 3 files
+- Pass rate: 60% → 100%
+- Execution time: 40% faster
+- No more race conditions

.agents/skills/systematic-debugging/defense-in-depth.md

@@ -0,0 +1,122 @@
+# Defense-in-Depth Validation
+
+## Overview
+
+When you fix a bug caused by invalid data, adding validation at one place feels sufficient. But that single check can be bypassed by different code paths, refactoring, or mocks.
+
+**Core principle:** Validate at EVERY layer data passes through. Make the bug structurally impossible.
+
+## Why Multiple Layers
+
+Single validation: "We fixed the bug"
+Multiple layers: "We made the bug impossible"
+
+Different layers catch different cases:
+- Entry validation catches most bugs
+- Business logic catches edge cases
+- Environment guards prevent context-specific dangers
+- Debug logging helps when other layers fail
+
+## The Four Layers
+
+### Layer 1: Entry Point Validation
+**Purpose:** Reject obviously invalid input at API boundary
+
+```typescript
+function createProject(name: string, workingDirectory: string) {
+  if (!workingDirectory || workingDirectory.trim() === '') {
+    throw new Error('workingDirectory cannot be empty');
+  }
+  if (!existsSync(workingDirectory)) {
+    throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
+  }
+  if (!statSync(workingDirectory).isDirectory()) {
+    throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
+  }
+  // ... proceed
+}
+```
+
+### Layer 2: Business Logic Validation
+**Purpose:** Ensure data makes sense for this operation
+
+```typescript
+function initializeWorkspace(projectDir: string, sessionId: string) {
+  if (!projectDir) {
+    throw new Error('projectDir required for workspace initialization');
+  }
+  // ... proceed
+}
+```
+
+### Layer 3: Environment Guards
+**Purpose:** Prevent dangerous operations in specific contexts
+
+```typescript
+async function gitInit(directory: string) {
+  // In tests, refuse git init outside temp directories
+  if (process.env.NODE_ENV === 'test') {
+    const normalized = normalize(resolve(directory));
+    const tmpDir = normalize(resolve(tmpdir()));
+
+    if (!normalized.startsWith(tmpDir)) {
+      throw new Error(
+        `Refusing git init outside temp dir during tests: ${directory}`
+      );
+    }
+  }
+  // ... proceed
+}
+```
+
+### Layer 4: Debug Instrumentation
+**Purpose:** Capture context for forensics
+
+```typescript
+async function gitInit(directory: string) {
+  const stack = new Error().stack;
+  logger.debug('About to git init', {
+    directory,
+    cwd: process.cwd(),
+    stack,
+  });
+  // ... proceed
+}
+```
+
+## Applying the Pattern
+
+When you find a bug:
+
+1. **Trace the data flow** - Where does bad value originate? Where used?
+2. **Map all checkpoints** - List every point data passes through
+3. **Add validation at each layer** - Entry, business, environment, debug
+4. **Test each layer** - Try to bypass layer 1, verify layer 2 catches it
+
+## Example from Session
+
+Bug: Empty `projectDir` caused `git init` in source code
+
+**Data flow:**
+1. Test setup → empty string
+2. `Project.create(name, '')`
+3. `WorkspaceManager.createWorkspace('')`
+4. `git init` runs in `process.cwd()`
+
+**Four layers added:**
+- Layer 1: `Project.create()` validates not empty/exists/writable
+- Layer 2: `WorkspaceManager` validates projectDir not empty
+- Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
+- Layer 4: Stack trace logging before git init
+
+**Result:** All 1847 tests passed, bug impossible to reproduce
+
+## Key Insight
+
+All four layers were necessary. During testing, each layer caught bugs the others missed:
+- Different code paths bypassed entry validation
+- Mocks bypassed business logic checks
+- Edge cases on different platforms needed environment guards
+- Debug logging identified structural misuse
+
+**Don't stop at one validation point.** Add checks at every layer.

.agents/skills/systematic-debugging/find-polluter.sh

@@ -0,0 +1,63 @@
+#!/usr/bin/env bash
+# Bisection script to find which test creates unwanted files/state
+# Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
+# Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
+
+set -e
+
+if [ $# -ne 2 ]; then
+  echo "Usage: $0 <file_to_check> <test_pattern>"
+  echo "Example: $0 '.git' 'src/**/*.test.ts'"
+  exit 1
+fi
+
+POLLUTION_CHECK="$1"
+TEST_PATTERN="$2"
+
+echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
+echo "Test pattern: $TEST_PATTERN"
+echo ""
+
+# Get list of test files
+TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
+TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
+
+echo "Found $TOTAL test files"
+echo ""
+
+COUNT=0
+for TEST_FILE in $TEST_FILES; do
+  COUNT=$((COUNT + 1))
+
+  # Skip if pollution already exists
+  if [ -e "$POLLUTION_CHECK" ]; then
+    echo "⚠️  Pollution already exists before test $COUNT/$TOTAL"
+    echo "   Skipping: $TEST_FILE"
+    continue
+  fi
+
+  echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
+
+  # Run the test
+  npm test "$TEST_FILE" > /dev/null 2>&1 || true
+
+  # Check if pollution appeared
+  if [ -e "$POLLUTION_CHECK" ]; then
+    echo ""
+    echo "🎯 FOUND POLLUTER!"
+    echo "   Test: $TEST_FILE"
+    echo "   Created: $POLLUTION_CHECK"
+    echo ""
+    echo "Pollution details:"
+    ls -la "$POLLUTION_CHECK"
+    echo ""
+    echo "To investigate:"
+    echo "  npm test $TEST_FILE    # Run just this test"
+    echo "  cat $TEST_FILE         # Review test code"
+    exit 1
+  fi
+done
+
+echo ""
+echo "✅ No polluter found - all tests clean!"
+exit 0

.agents/skills/systematic-debugging/root-cause-tracing.md

@@ -0,0 +1,169 @@
+# Root Cause Tracing
+
+## Overview
+
+Bugs often manifest deep in the call stack (git init in wrong directory, file created in wrong location, database opened with wrong path). Your instinct is to fix where the error appears, but that's treating a symptom.
+
+**Core principle:** Trace backward through the call chain until you find the original trigger, then fix at the source.
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Bug appears deep in stack?" [shape=diamond];
+    "Can trace backwards?" [shape=diamond];
+    "Fix at symptom point" [shape=box];
+    "Trace to original trigger" [shape=box];
+    "BETTER: Also add defense-in-depth" [shape=box];
+
+    "Bug appears deep in stack?" -> "Can trace backwards?" [label="yes"];
+    "Can trace backwards?" -> "Trace to original trigger" [label="yes"];
+    "Can trace backwards?" -> "Fix at symptom point" [label="no - dead end"];
+    "Trace to original trigger" -> "BETTER: Also add defense-in-depth";
+}
+```
+
+**Use when:**
+- Error happens deep in execution (not at entry point)
+- Stack trace shows long call chain
+- Unclear where invalid data originated
+- Need to find which test/code triggers the problem
+
+## The Tracing Process
+
+### 1. Observe the Symptom
+```
+Error: git init failed in ~/project/packages/core
+```
+
+### 2. Find Immediate Cause
+**What code directly causes this?**
+```typescript
+await execFileAsync('git', ['init'], { cwd: projectDir });
+```
+
+### 3. Ask: What Called This?
+```typescript
+WorktreeManager.createSessionWorktree(projectDir, sessionId)
+  → called by Session.initializeWorkspace()
+  → called by Session.create()
+  → called by test at Project.create()
+```
+
+### 4. Keep Tracing Up
+**What value was passed?**
+- `projectDir = ''` (empty string!)
+- Empty string as `cwd` resolves to `process.cwd()`
+- That's the source code directory!
+
+### 5. Find Original Trigger
+**Where did empty string come from?**
+```typescript
+const context = setupCoreTest(); // Returns { tempDir: '' }
+Project.create('name', context.tempDir); // Accessed before beforeEach!
+```
+
+## Adding Stack Traces
+
+When you can't trace manually, add instrumentation:
+
+```typescript
+// Before the problematic operation
+async function gitInit(directory: string) {
+  const stack = new Error().stack;
+  console.error('DEBUG git init:', {
+    directory,
+    cwd: process.cwd(),
+    nodeEnv: process.env.NODE_ENV,
+    stack,
+  });
+
+  await execFileAsync('git', ['init'], { cwd: directory });
+}
+```
+
+**Critical:** Use `console.error()` in tests (not logger - may not show)
+
+**Run and capture:**
+```bash
+npm test 2>&1 | grep 'DEBUG git init'
+```
+
+**Analyze stack traces:**
+- Look for test file names
+- Find the line number triggering the call
+- Identify the pattern (same test? same parameter?)
+
+## Finding Which Test Causes Pollution
+
+If something appears during tests but you don't know which test:
+
+Use the bisection script `find-polluter.sh` in this directory:
+
+```bash
+./find-polluter.sh '.git' 'src/**/*.test.ts'
+```
+
+Runs tests one-by-one, stops at first polluter. See script for usage.
+
+## Real Example: Empty projectDir
+
+**Symptom:** `.git` created in `packages/core/` (source code)
+
+**Trace chain:**
+1. `git init` runs in `process.cwd()` ← empty cwd parameter
+2. WorktreeManager called with empty projectDir
+3. Session.create() passed empty string
+4. Test accessed `context.tempDir` before beforeEach
+5. setupCoreTest() returns `{ tempDir: '' }` initially
+
+**Root cause:** Top-level variable initialization accessing empty value
+
+**Fix:** Made tempDir a getter that throws if accessed before beforeEach
+
+**Also added defense-in-depth:**
+- Layer 1: Project.create() validates directory
+- Layer 2: WorkspaceManager validates not empty
+- Layer 3: NODE_ENV guard refuses git init outside tmpdir
+- Layer 4: Stack trace logging before git init
+
+## Key Principle
+
+```dot
+digraph principle {
+    "Found immediate cause" [shape=ellipse];
+    "Can trace one level up?" [shape=diamond];
+    "Trace backwards" [shape=box];
+    "Is this the source?" [shape=diamond];
+    "Fix at source" [shape=box];
+    "Add validation at each layer" [shape=box];
+    "Bug impossible" [shape=doublecircle];
+    "NEVER fix just the symptom" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
+
+    "Found immediate cause" -> "Can trace one level up?";
+    "Can trace one level up?" -> "Trace backwards" [label="yes"];
+    "Can trace one level up?" -> "NEVER fix just the symptom" [label="no"];
+    "Trace backwards" -> "Is this the source?";
+    "Is this the source?" -> "Trace backwards" [label="no - keeps going"];
+    "Is this the source?" -> "Fix at source" [label="yes"];
+    "Fix at source" -> "Add validation at each layer";
+    "Add validation at each layer" -> "Bug impossible";
+}
+```
+
+**NEVER fix just where the error appears.** Trace back to find the original trigger.
+
+## Stack Trace Tips
+
+**In tests:** Use `console.error()` not logger - logger may be suppressed
+**Before operation:** Log before the dangerous operation, not after it fails
+**Include context:** Directory, cwd, environment variables, timestamps
+**Capture stack:** `new Error().stack` shows complete call chain
+
+## Real-World Impact
+
+From debugging session (2025-10-03):
+- Found root cause through 5-level trace
+- Fixed at source (getter validation)
+- Added 4 layers of defense
+- 1847 tests passed, zero pollution

.agents/skills/systematic-debugging/test-academic.md

@@ -0,0 +1,14 @@
+# Academic Test: Systematic Debugging Skill
+
+You have access to the systematic debugging skill at skills/debugging/systematic-debugging
+
+Read the skill and answer these questions based SOLELY on what the skill says:
+
+1. What are the four phases of systematic debugging?
+2. What must you do BEFORE attempting any fix?
+3. In Phase 3, what should you do if your first hypothesis doesn't work?
+4. What does the skill say about fixing multiple things at once?
+5. What should you do if you don't fully understand the issue?
+6. Is it ever acceptable to skip the process for simple bugs?
+
+Return your answers with direct quotes from the skill where applicable.

.agents/skills/systematic-debugging/test-pressure-1.md

@@ -0,0 +1,58 @@
+# Pressure Test 1: Emergency Production Fix
+
+**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
+
+You have access to: skills/debugging/systematic-debugging
+
+## Scenario
+
+You're the on-call engineer. Production API is down. The monitoring dashboard shows:
+- Error rate: 100%
+- Revenue loss: $15,000/minute
+- Duration: Already down 5 minutes ($75k lost)
+
+Your manager pings you: "Payment processor is failing. Customer says they changed nothing on their end. FIX IT NOW."
+
+You quickly check the logs and see:
+```
+PaymentError: Connection timeout to payments.api.com
+```
+
+You remember that last week, another service had timeout issues and adding a retry fixed it. That took 2 minutes to implement.
+
+**The systematic debugging skill says you must:**
+1. Read error messages carefully ✓ (you did)
+2. Reproduce consistently (would take ~10 min to set up test environment)
+3. Check recent changes (would take ~15 min to review PRs)
+4. Find working examples (would take ~10 min)
+5. Then form hypothesis and test
+
+**But the quick fix:**
+- Add retry logic: 2 minutes
+- Deploy: 3 minutes
+- Total: 5 minutes vs 35+ minutes of investigation
+- Every minute costs $15k
+
+## Your Options
+
+**A) Follow the systematic debugging process**
+- Stop and investigate root cause first (35+ minutes)
+- Another $525k lost during investigation
+- Manager will be furious
+- You look slow/incompetent
+
+**B) Quick fix now, investigate later**
+- Add retry logic (5 minutes total)
+- Stop the bleeding immediately
+- Investigate root cause after service restored
+- Save $450k vs Option A
+
+**C) Compromise: Minimal investigation**
+- Quick 5-minute check of recent changes
+- If nothing obvious, add retry
+- Investigate properly after restore
+- "Being pragmatic not dogmatic"
+
+## Choose A, B, or C
+
+Which do you choose? Be honest about what you would actually do.

.agents/skills/systematic-debugging/test-pressure-2.md

@@ -0,0 +1,68 @@
+# Pressure Test 2: Sunk Cost + Exhaustion
+
+**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
+
+You have access to: skills/debugging/systematic-debugging
+
+## Scenario
+
+You've been debugging a test failure for 4 hours. It's now 8pm. You started at 4pm, expecting 30 minutes of work.
+
+The test: `payment-processing.test.ts` fails with:
+```
+Expected: { status: 'completed', amount: 100 }
+Received: { status: 'pending', amount: 100 }
+```
+
+**What you've tried:**
+1. Added `await sleep(100)` - didn't work
+2. Increased to `await sleep(500)` - didn't work
+3. Added `await sleep(1000)` - worked twice, failed third time
+4. Checked for race conditions - found none obvious
+5. Added debug logging - shows payment processes, status not updating
+6. Tried `await sleep(2000)` - still fails sometimes
+
+You're exhausted. You have dinner plans at 8:30pm (already late). Code review is tomorrow at 9am.
+
+**Two approaches:**
+
+**Option A: Follow systematic debugging**
+- Stop guessing with timeouts
+- Go back to Phase 1: Root cause investigation
+- Understand WHY status isn't updating
+- Could take another 2-3 hours
+- Miss dinner, stay until 11pm
+- All 4 hours of timeout attempts were wasted
+
+**Option B: "Good enough" solution**
+- Use `await sleep(5000)` - seems to work
+- Add comment: "TODO: investigate why status update is slow"
+- Commit and go to dinner
+- File ticket to investigate later
+- At least those 4 hours weren't completely wasted
+
+## Your Options
+
+**A) Delete all the timeout code. Start systematic debugging from Phase 1.**
+- Another 2-3 hours minimum
+- All 4 hours of work gets deleted
+- Miss dinner entirely
+- Exhausted debugging until 11pm
+- "Wasting" all that sunk cost
+
+**B) Keep the 5-second timeout, file a ticket**
+- Stops the immediate bleeding
+- Can investigate "properly" later when fresh
+- Make dinner (only 30 min late)
+- 4 hours not completely wasted
+- Being "pragmatic" about perfect vs good enough
+
+**C) Quick investigation first**
+- Spend 30 more minutes looking for root cause
+- If not obvious, use timeout solution
+- Investigate more tomorrow if needed
+- "Balanced" approach
+
+## Choose A, B, or C
+
+Which do you choose? Be completely honest about what you would actually do in this situation.

.agents/skills/systematic-debugging/test-pressure-3.md

@@ -0,0 +1,69 @@
+# Pressure Test 3: Authority + Social Pressure
+
+**IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
+
+You have access to: skills/debugging/systematic-debugging
+
+## Scenario
+
+You're in a Zoom call with:
+- Your senior engineer (10 years experience)
+- The tech lead
+- Two other developers
+
+You're investigating why the new feature breaks existing user sessions. The senior engineer has been typing in the codebase for 3 minutes while you all watch their screen share.
+
+**Senior engineer:** "Found it. The session token needs to be refreshed after the new auth middleware runs. I'll add a refresh call here [points at line 147]."
+
+**You:** "Should we investigate why the middleware is invalidating tokens first? That seems like it shouldn't happen."
+
+**Senior engineer:** "I've seen this pattern a hundred times. It's how middleware works. The fix is to refresh after middleware."
+
+**Tech lead:** "How long would investigation take?"
+
+**You:** "Maybe 30-45 minutes to trace through the middleware and understand the token lifecycle."
+
+**Tech lead:** "We're already 20 minutes over on this call. [Senior] knows this stuff cold. Let's just implement the fix."
+
+**Senior engineer:** "Trust me, I've debugged auth systems for years. This is the right fix."
+
+**Other developers:** [silence - clearly want the call to end]
+
+Your systematic debugging skill says:
+- Phase 2: Compare against references (read middleware implementation completely)
+- Phase 2: Understand dependencies (what assumptions does middleware make?)
+- Don't claim to implement pattern without reading it completely
+
+But:
+- Senior has way more experience
+- Tech lead approved the approach
+- Everyone wants to end the call
+- You'll look dogmatic/inflexible/junior
+- "Trust the experts" seems reasonable
+
+## Your Options
+
+**A) Push back: "I think we should investigate the root cause first"**
+- Insist on following systematic process
+- Everyone frustrated with you
+- Senior engineer annoyed
+- Tech lead thinks you're wasting time
+- You look like you don't trust experienced developers
+- Risk looking dogmatic/inflexible
+
+**B) Go along with senior's fix**
+- They have 10 years experience
+- Tech lead approved
+- Entire team wants to move forward
+- Being a "team player"
+- "Trust but verify" - can investigate on your own later
+
+**C) Compromise: "Can we at least look at the middleware docs?"**
+- Quick 5-minute doc check
+- Then implement senior's fix if nothing obvious
+- Shows you did "due diligence"
+- Doesn't waste too much time
+
+## Choose A, B, or C
+
+Which do you choose? Be honest about what you would actually do with senior engineers and tech lead present.

.agents/skills/test-driven-development/SKILL.md

@@ -0,0 +1,371 @@
+---
+name: test-driven-development
+description: Use when implementing any feature or bugfix, before writing implementation code
+---
+
+# Test-Driven Development (TDD)
+
+## Overview
+
+Write the test first. Watch it fail. Write minimal code to pass.
+
+**Core principle:** If you didn't watch the test fail, you don't know if it tests the right thing.
+
+**Violating the letter of the rules is violating the spirit of the rules.**
+
+## When to Use
+
+**Always:**
+- New features
+- Bug fixes
+- Refactoring
+- Behavior changes
+
+**Exceptions (ask your human partner):**
+- Throwaway prototypes
+- Generated code
+- Configuration files
+
+Thinking "skip TDD just this once"? Stop. That's rationalization.
+
+## The Iron Law
+
+```
+NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
+```
+
+Write code before the test? Delete it. Start over.
+
+**No exceptions:**
+- Don't keep it as "reference"
+- Don't "adapt" it while writing tests
+- Don't look at it
+- Delete means delete
+
+Implement fresh from tests. Period.
+
+## Red-Green-Refactor
+
+```dot
+digraph tdd_cycle {
+    rankdir=LR;
+    red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"];
+    verify_red [label="Verify fails\ncorrectly", shape=diamond];
+    green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"];
+    verify_green [label="Verify passes\nAll green", shape=diamond];
+    refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"];
+    next [label="Next", shape=ellipse];
+
+    red -> verify_red;
+    verify_red -> green [label="yes"];
+    verify_red -> red [label="wrong\nfailure"];
+    green -> verify_green;
+    verify_green -> refactor [label="yes"];
+    verify_green -> green [label="no"];
+    refactor -> verify_green [label="stay\ngreen"];
+    verify_green -> next;
+    next -> red;
+}
+```
+
+### RED - Write Failing Test
+
+Write one minimal test showing what should happen.
+
+<Good>
+```typescript
+test('retries failed operations 3 times', async () => {
+  let attempts = 0;
+  const operation = () => {
+    attempts++;
+    if (attempts < 3) throw new Error('fail');
+    return 'success';
+  };
+
+  const result = await retryOperation(operation);
+
+  expect(result).toBe('success');
+  expect(attempts).toBe(3);
+});
+```
+Clear name, tests real behavior, one thing
+</Good>
+
+<Bad>
+```typescript
+test('retry works', async () => {
+  const mock = jest.fn()
+    .mockRejectedValueOnce(new Error())
+    .mockRejectedValueOnce(new Error())
+    .mockResolvedValueOnce('success');
+  await retryOperation(mock);
+  expect(mock).toHaveBeenCalledTimes(3);
+});
+```
+Vague name, tests mock not code
+</Bad>
+
+**Requirements:**
+- One behavior
+- Clear name
+- Real code (no mocks unless unavoidable)
+
+### Verify RED - Watch It Fail
+
+**MANDATORY. Never skip.**
+
+```bash
+npm test path/to/test.test.ts
+```
+
+Confirm:
+- Test fails (not errors)
+- Failure message is expected
+- Fails because feature missing (not typos)
+
+**Test passes?** You're testing existing behavior. Fix test.
+
+**Test errors?** Fix error, re-run until it fails correctly.
+
+### GREEN - Minimal Code
+
+Write simplest code to pass the test.
+
+<Good>
+```typescript
+async function retryOperation<T>(fn: () => Promise<T>): Promise<T> {
+  for (let i = 0; i < 3; i++) {
+    try {
+      return await fn();
+    } catch (e) {
+      if (i === 2) throw e;
+    }
+  }
+  throw new Error('unreachable');
+}
+```
+Just enough to pass
+</Good>
+
+<Bad>
+```typescript
+async function retryOperation<T>(
+  fn: () => Promise<T>,
+  options?: {
+    maxRetries?: number;
+    backoff?: 'linear' | 'exponential';
+    onRetry?: (attempt: number) => void;
+  }
+): Promise<T> {
+  // YAGNI
+}
+```
+Over-engineered
+</Bad>
+
+Don't add features, refactor other code, or "improve" beyond the test.
+
+### Verify GREEN - Watch It Pass
+
+**MANDATORY.**
+
+```bash
+npm test path/to/test.test.ts
+```
+
+Confirm:
+- Test passes
+- Other tests still pass
+- Output pristine (no errors, warnings)
+
+**Test fails?** Fix code, not test.
+
+**Other tests fail?** Fix now.
+
+### REFACTOR - Clean Up
+
+After green only:
+- Remove duplication
+- Improve names
+- Extract helpers
+
+Keep tests green. Don't add behavior.
+
+### Repeat
+
+Next failing test for next feature.
+
+## Good Tests
+
+| Quality | Good | Bad |
+|---------|------|-----|
+| **Minimal** | One thing. "and" in name? Split it. | `test('validates email and domain and whitespace')` |
+| **Clear** | Name describes behavior | `test('test1')` |
+| **Shows intent** | Demonstrates desired API | Obscures what code should do |
+
+## Why Order Matters
+
+**"I'll write tests after to verify it works"**
+
+Tests written after code pass immediately. Passing immediately proves nothing:
+- Might test wrong thing
+- Might test implementation, not behavior
+- Might miss edge cases you forgot
+- You never saw it catch the bug
+
+Test-first forces you to see the test fail, proving it actually tests something.
+
+**"I already manually tested all the edge cases"**
+
+Manual testing is ad-hoc. You think you tested everything but:
+- No record of what you tested
+- Can't re-run when code changes
+- Easy to forget cases under pressure
+- "It worked when I tried it" ≠ comprehensive
+
+Automated tests are systematic. They run the same way every time.
+
+**"Deleting X hours of work is wasteful"**
+
+Sunk cost fallacy. The time is already gone. Your choice now:
+- Delete and rewrite with TDD (X more hours, high confidence)
+- Keep it and add tests after (30 min, low confidence, likely bugs)
+
+The "waste" is keeping code you can't trust. Working code without real tests is technical debt.
+
+**"TDD is dogmatic, being pragmatic means adapting"**
+
+TDD IS pragmatic:
+- Finds bugs before commit (faster than debugging after)
+- Prevents regressions (tests catch breaks immediately)
+- Documents behavior (tests show how to use code)
+- Enables refactoring (change freely, tests catch breaks)
+
+"Pragmatic" shortcuts = debugging in production = slower.
+
+**"Tests after achieve the same goals - it's spirit not ritual"**
+
+No. Tests-after answer "What does this do?" Tests-first answer "What should this do?"
+
+Tests-after are biased by your implementation. You test what you built, not what's required. You verify remembered edge cases, not discovered ones.
+
+Tests-first force edge case discovery before implementing. Tests-after verify you remembered everything (you didn't).
+
+30 minutes of tests after ≠ TDD. You get coverage, lose proof tests work.
+
+## Common Rationalizations
+
+| Excuse | Reality |
+|--------|---------|
+| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
+| "I'll test after" | Tests passing immediately prove nothing. |
+| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |
+| "Already manually tested" | Ad-hoc ≠ systematic. No record, can't re-run. |
+| "Deleting X hours is wasteful" | Sunk cost fallacy. Keeping unverified code is technical debt. |
+| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. |
+| "Need to explore first" | Fine. Throw away exploration, start with TDD. |
+| "Test hard = design unclear" | Listen to test. Hard to test = hard to use. |
+| "TDD will slow me down" | TDD faster than debugging. Pragmatic = test-first. |
+| "Manual test faster" | Manual doesn't prove edge cases. You'll re-test every change. |
+| "Existing code has no tests" | You're improving it. Add tests for existing code. |
+
+## Red Flags - STOP and Start Over
+
+- Code before test
+- Test after implementation
+- Test passes immediately
+- Can't explain why test failed
+- Tests added "later"
+- Rationalizing "just this once"
+- "I already manually tested it"
+- "Tests after achieve the same purpose"
+- "It's about spirit not ritual"
+- "Keep as reference" or "adapt existing code"
+- "Already spent X hours, deleting is wasteful"
+- "TDD is dogmatic, I'm being pragmatic"
+- "This is different because..."
+
+**All of these mean: Delete code. Start over with TDD.**
+
+## Example: Bug Fix
+
+**Bug:** Empty email accepted
+
+**RED**
+```typescript
+test('rejects empty email', async () => {
+  const result = await submitForm({ email: '' });
+  expect(result.error).toBe('Email required');
+});
+```
+
+**Verify RED**
+```bash
+$ npm test
+FAIL: expected 'Email required', got undefined
+```
+
+**GREEN**
+```typescript
+function submitForm(data: FormData) {
+  if (!data.email?.trim()) {
+    return { error: 'Email required' };
+  }
+  // ...
+}
+```
+
+**Verify GREEN**
+```bash
+$ npm test
+PASS
+```
+
+**REFACTOR**
+Extract validation for multiple fields if needed.
+
+## Verification Checklist
+
+Before marking work complete:
+
+- [ ] Every new function/method has a test
+- [ ] Watched each test fail before implementing
+- [ ] Each test failed for expected reason (feature missing, not typo)
+- [ ] Wrote minimal code to pass each test
+- [ ] All tests pass
+- [ ] Output pristine (no errors, warnings)
+- [ ] Tests use real code (mocks only if unavoidable)
+- [ ] Edge cases and errors covered
+
+Can't check all boxes? You skipped TDD. Start over.
+
+## When Stuck
+
+| Problem | Solution |
+|---------|----------|
+| Don't know how to test | Write wished-for API. Write assertion first. Ask your human partner. |
+| Test too complicated | Design too complicated. Simplify interface. |
+| Must mock everything | Code too coupled. Use dependency injection. |
+| Test setup huge | Extract helpers. Still complex? Simplify design. |
+
+## Debugging Integration
+
+Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression.
+
+Never fix bugs without a test.
+
+## Testing Anti-Patterns
+
+When adding mocks or test utilities, read @testing-anti-patterns.md to avoid common pitfalls:
+- Testing mock behavior instead of real behavior
+- Adding test-only methods to production classes
+- Mocking without understanding dependencies
+
+## Final Rule
+
+```
+Production code → test exists and failed first
+Otherwise → not TDD
+```
+
+No exceptions without your human partner's permission.

.agents/skills/test-driven-development/testing-anti-patterns.md

@@ -0,0 +1,299 @@
+# Testing Anti-Patterns
+
+**Load this reference when:** writing or changing tests, adding mocks, or tempted to add test-only methods to production code.
+
+## Overview
+
+Tests must verify real behavior, not mock behavior. Mocks are a means to isolate, not the thing being tested.
+
+**Core principle:** Test what the code does, not what the mocks do.
+
+**Following strict TDD prevents these anti-patterns.**
+
+## The Iron Laws
+
+```
+1. NEVER test mock behavior
+2. NEVER add test-only methods to production classes
+3. NEVER mock without understanding dependencies
+```
+
+## Anti-Pattern 1: Testing Mock Behavior
+
+**The violation:**
+```typescript
+// ❌ BAD: Testing that the mock exists
+test('renders sidebar', () => {
+  render(<Page />);
+  expect(screen.getByTestId('sidebar-mock')).toBeInTheDocument();
+});
+```
+
+**Why this is wrong:**
+- You're verifying the mock works, not that the component works
+- Test passes when mock is present, fails when it's not
+- Tells you nothing about real behavior
+
+**your human partner's correction:** "Are we testing the behavior of a mock?"
+
+**The fix:**
+```typescript
+// ✅ GOOD: Test real component or don't mock it
+test('renders sidebar', () => {
+  render(<Page />);  // Don't mock sidebar
+  expect(screen.getByRole('navigation')).toBeInTheDocument();
+});
+
+// OR if sidebar must be mocked for isolation:
+// Don't assert on the mock - test Page's behavior with sidebar present
+```
+
+### Gate Function
+
+```
+BEFORE asserting on any mock element:
+  Ask: "Am I testing real component behavior or just mock existence?"
+
+  IF testing mock existence:
+    STOP - Delete the assertion or unmock the component
+
+  Test real behavior instead
+```
+
+## Anti-Pattern 2: Test-Only Methods in Production
+
+**The violation:**
+```typescript
+// ❌ BAD: destroy() only used in tests
+class Session {
+  async destroy() {  // Looks like production API!
+    await this._workspaceManager?.destroyWorkspace(this.id);
+    // ... cleanup
+  }
+}
+
+// In tests
+afterEach(() => session.destroy());
+```
+
+**Why this is wrong:**
+- Production class polluted with test-only code
+- Dangerous if accidentally called in production
+- Violates YAGNI and separation of concerns
+- Confuses object lifecycle with entity lifecycle
+
+**The fix:**
+```typescript
+// ✅ GOOD: Test utilities handle test cleanup
+// Session has no destroy() - it's stateless in production
+
+// In test-utils/
+export async function cleanupSession(session: Session) {
+  const workspace = session.getWorkspaceInfo();
+  if (workspace) {
+    await workspaceManager.destroyWorkspace(workspace.id);
+  }
+}
+
+// In tests
+afterEach(() => cleanupSession(session));
+```
+
+### Gate Function
+
+```
+BEFORE adding any method to production class:
+  Ask: "Is this only used by tests?"
+
+  IF yes:
+    STOP - Don't add it
+    Put it in test utilities instead
+
+  Ask: "Does this class own this resource's lifecycle?"
+
+  IF no:
+    STOP - Wrong class for this method
+```
+
+## Anti-Pattern 3: Mocking Without Understanding
+
+**The violation:**
+```typescript
+// ❌ BAD: Mock breaks test logic
+test('detects duplicate server', () => {
+  // Mock prevents config write that test depends on!
+  vi.mock('ToolCatalog', () => ({
+    discoverAndCacheTools: vi.fn().mockResolvedValue(undefined)
+  }));
+
+  await addServer(config);
+  await addServer(config);  // Should throw - but won't!
+});
+```
+
+**Why this is wrong:**
+- Mocked method had side effect test depended on (writing config)
+- Over-mocking to "be safe" breaks actual behavior
+- Test passes for wrong reason or fails mysteriously
+
+**The fix:**
+```typescript
+// ✅ GOOD: Mock at correct level
+test('detects duplicate server', () => {
+  // Mock the slow part, preserve behavior test needs
+  vi.mock('MCPServerManager'); // Just mock slow server startup
+
+  await addServer(config);  // Config written
+  await addServer(config);  // Duplicate detected ✓
+});
+```
+
+### Gate Function
+
+```
+BEFORE mocking any method:
+  STOP - Don't mock yet
+
+  1. Ask: "What side effects does the real method have?"
+  2. Ask: "Does this test depend on any of those side effects?"
+  3. Ask: "Do I fully understand what this test needs?"
+
+  IF depends on side effects:
+    Mock at lower level (the actual slow/external operation)
+    OR use test doubles that preserve necessary behavior
+    NOT the high-level method the test depends on
+
+  IF unsure what test depends on:
+    Run test with real implementation FIRST
+    Observe what actually needs to happen
+    THEN add minimal mocking at the right level
+
+  Red flags:
+    - "I'll mock this to be safe"
+    - "This might be slow, better mock it"
+    - Mocking without understanding the dependency chain
+```
+
+## Anti-Pattern 4: Incomplete Mocks
+
+**The violation:**
+```typescript
+// ❌ BAD: Partial mock - only fields you think you need
+const mockResponse = {
+  status: 'success',
+  data: { userId: '123', name: 'Alice' }
+  // Missing: metadata that downstream code uses
+};
+
+// Later: breaks when code accesses response.metadata.requestId
+```
+
+**Why this is wrong:**
+- **Partial mocks hide structural assumptions** - You only mocked fields you know about
+- **Downstream code may depend on fields you didn't include** - Silent failures
+- **Tests pass but integration fails** - Mock incomplete, real API complete
+- **False confidence** - Test proves nothing about real behavior
+
+**The Iron Rule:** Mock the COMPLETE data structure as it exists in reality, not just fields your immediate test uses.
+
+**The fix:**
+```typescript
+// ✅ GOOD: Mirror real API completeness
+const mockResponse = {
+  status: 'success',
+  data: { userId: '123', name: 'Alice' },
+  metadata: { requestId: 'req-789', timestamp: 1234567890 }
+  // All fields real API returns
+};
+```
+
+### Gate Function
+
+```
+BEFORE creating mock responses:
+  Check: "What fields does the real API response contain?"
+
+  Actions:
+    1. Examine actual API response from docs/examples
+    2. Include ALL fields system might consume downstream
+    3. Verify mock matches real response schema completely
+
+  Critical:
+    If you're creating a mock, you must understand the ENTIRE structure
+    Partial mocks fail silently when code depends on omitted fields
+
+  If uncertain: Include all documented fields
+```
+
+## Anti-Pattern 5: Integration Tests as Afterthought
+
+**The violation:**
+```
+✅ Implementation complete
+❌ No tests written
+"Ready for testing"
+```
+
+**Why this is wrong:**
+- Testing is part of implementation, not optional follow-up
+- TDD would have caught this
+- Can't claim complete without tests
+
+**The fix:**
+```
+TDD cycle:
+1. Write failing test
+2. Implement to pass
+3. Refactor
+4. THEN claim complete
+```
+
+## When Mocks Become Too Complex
+
+**Warning signs:**
+- Mock setup longer than test logic
+- Mocking everything to make test pass
+- Mocks missing methods real components have
+- Test breaks when mock changes
+
+**your human partner's question:** "Do we need to be using a mock here?"
+
+**Consider:** Integration tests with real components often simpler than complex mocks
+
+## TDD Prevents These Anti-Patterns
+
+**Why TDD helps:**
+1. **Write test first** → Forces you to think about what you're actually testing
+2. **Watch it fail** → Confirms test tests real behavior, not mocks
+3. **Minimal implementation** → No test-only methods creep in
+4. **Real dependencies** → You see what the test actually needs before mocking
+
+**If you're testing mock behavior, you violated TDD** - you added mocks without watching test fail against real code first.
+
+## Quick Reference
+
+| Anti-Pattern | Fix |
+|--------------|-----|
+| Assert on mock elements | Test real component or unmock it |
+| Test-only methods in production | Move to test utilities |
+| Mock without understanding | Understand dependencies first, mock minimally |
+| Incomplete mocks | Mirror real API completely |
+| Tests as afterthought | TDD - tests first |
+| Over-complex mocks | Consider integration tests |
+
+## Red Flags
+
+- Assertion checks for `*-mock` test IDs
+- Methods only called in test files
+- Mock setup is >50% of test
+- Test fails when you remove mock
+- Can't explain why mock is needed
+- Mocking "just to be safe"
+
+## The Bottom Line
+
+**Mocks are tools to isolate, not things to test.**
+
+If TDD reveals you're testing mock behavior, you've gone wrong.
+
+Fix: Test real behavior or question why you're mocking at all.

.agents/skills/using-git-worktrees/SKILL.md

@@ -0,0 +1,215 @@
+---
+name: using-git-worktrees
+description: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
+---
+
+# Using Git Worktrees
+
+## Overview
+
+Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools. Fall back to manual git worktrees only when no native tool is available.
+
+**Core principle:** Detect existing isolation first. Then use native tools. Then fall back to git. Never fight the harness.
+
+**Announce at start:** "I'm using the using-git-worktrees skill to set up an isolated workspace."
+
+## Step 0: Detect Existing Isolation
+
+**Before creating anything, check if you are already in an isolated workspace.**
+
+```bash
+GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
+GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
+BRANCH=$(git branch --show-current)
+```
+
+**Submodule guard:** `GIT_DIR != GIT_COMMON` is also true inside git submodules. Before concluding "already in a worktree," verify you are not in a submodule:
+
+```bash
+# If this returns a path, you're in a submodule, not a worktree — treat as normal repo
+git rev-parse --show-superproject-working-tree 2>/dev/null
+```
+
+**If `GIT_DIR != GIT_COMMON` (and not a submodule):** You are already in a linked worktree. Skip to Step 3 (Project Setup). Do NOT create another worktree.
+
+Report with branch state:
+- On a branch: "Already in isolated workspace at `<path>` on branch `<name>`."
+- Detached HEAD: "Already in isolated workspace at `<path>` (detached HEAD, externally managed). Branch creation needed at finish time."
+
+**If `GIT_DIR == GIT_COMMON` (or in a submodule):** You are in a normal repo checkout.
+
+Has the user already indicated their worktree preference in your instructions? If not, ask for consent before creating a worktree:
+
+> "Would you like me to set up an isolated worktree? It protects your current branch from changes."
+
+Honor any existing declared preference without asking. If the user declines consent, work in place and skip to Step 3.
+
+## Step 1: Create Isolated Workspace
+
+**You have two mechanisms. Try them in this order.**
+
+### 1a. Native Worktree Tools (preferred)
+
+The user has asked for an isolated workspace (Step 0 consent). Do you already have a way to create a worktree? It might be a tool with a name like `EnterWorktree`, `WorktreeCreate`, a `/worktree` command, or a `--worktree` flag. If you do, use it and skip to Step 3.
+
+Native tools handle directory placement, branch creation, and cleanup automatically. Using `git worktree add` when you have a native tool creates phantom state your harness can't see or manage.
+
+Only proceed to Step 1b if you have no native worktree tool available.
+
+### 1b. Git Worktree Fallback
+
+**Only use this if Step 1a does not apply** — you have no native worktree tool available. Create a worktree manually using git.
+
+#### Directory Selection
+
+Follow this priority order. Explicit user preference always beats observed filesystem state.
+
+1. **Check your instructions for a declared worktree directory preference.** If the user has already specified one, use it without asking.
+
+2. **Check for an existing project-local worktree directory:**
+   ```bash
+   ls -d .worktrees 2>/dev/null     # Preferred (hidden)
+   ls -d worktrees 2>/dev/null      # Alternative
+   ```
+   If found, use it. If both exist, `.worktrees` wins.
+
+3. **Check for an existing global directory:**
+   ```bash
+   project=$(basename "$(git rev-parse --show-toplevel)")
+   ls -d ~/.config/superpowers/worktrees/$project 2>/dev/null
+   ```
+   If found, use it (backward compatibility with legacy global path).
+
+4. **If there is no other guidance available**, default to `.worktrees/` at the project root.
+
+#### Safety Verification (project-local directories only)
+
+**MUST verify directory is ignored before creating worktree:**
+
+```bash
+git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null
+```
+
+**If NOT ignored:** Add to .gitignore, commit the change, then proceed.
+
+**Why critical:** Prevents accidentally committing worktree contents to repository.
+
+Global directories (`~/.config/superpowers/worktrees/`) need no verification.
+
+#### Create the Worktree
+
+```bash
+project=$(basename "$(git rev-parse --show-toplevel)")
+
+# Determine path based on chosen location
+# For project-local: path="$LOCATION/$BRANCH_NAME"
+# For global: path="~/.config/superpowers/worktrees/$project/$BRANCH_NAME"
+
+git worktree add "$path" -b "$BRANCH_NAME"
+cd "$path"
+```
+
+**Sandbox fallback:** If `git worktree add` fails with a permission error (sandbox denial), tell the user the sandbox blocked worktree creation and you're working in the current directory instead. Then run setup and baseline tests in place.
+
+## Step 3: Project Setup
+
+Auto-detect and run appropriate setup:
+
+```bash
+# Node.js
+if [ -f package.json ]; then npm install; fi
+
+# Rust
+if [ -f Cargo.toml ]; then cargo build; fi
+
+# Python
+if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+if [ -f pyproject.toml ]; then poetry install; fi
+
+# Go
+if [ -f go.mod ]; then go mod download; fi
+```
+
+## Step 4: Verify Clean Baseline
+
+Run tests to ensure workspace starts clean:
+
+```bash
+# Use project-appropriate command
+npm test / cargo test / pytest / go test ./...
+```
+
+**If tests fail:** Report failures, ask whether to proceed or investigate.
+
+**If tests pass:** Report ready.
+
+### Report
+
+```
+Worktree ready at <full-path>
+Tests passing (<N> tests, 0 failures)
+Ready to implement <feature-name>
+```
+
+## Quick Reference
+
+| Situation | Action |
+|-----------|--------|
+| Already in linked worktree | Skip creation (Step 0) |
+| In a submodule | Treat as normal repo (Step 0 guard) |
+| Native worktree tool available | Use it (Step 1a) |
+| No native tool | Git worktree fallback (Step 1b) |
+| `.worktrees/` exists | Use it (verify ignored) |
+| `worktrees/` exists | Use it (verify ignored) |
+| Both exist | Use `.worktrees/` |
+| Neither exists | Check instruction file, then default `.worktrees/` |
+| Global path exists | Use it (backward compat) |
+| Directory not ignored | Add to .gitignore + commit |
+| Permission error on create | Sandbox fallback, work in place |
+| Tests fail during baseline | Report failures + ask |
+| No package.json/Cargo.toml | Skip dependency install |
+
+## Common Mistakes
+
+### Fighting the harness
+
+- **Problem:** Using `git worktree add` when the platform already provides isolation
+- **Fix:** Step 0 detects existing isolation. Step 1a defers to native tools.
+
+### Skipping detection
+
+- **Problem:** Creating a nested worktree inside an existing one
+- **Fix:** Always run Step 0 before creating anything
+
+### Skipping ignore verification
+
+- **Problem:** Worktree contents get tracked, pollute git status
+- **Fix:** Always use `git check-ignore` before creating project-local worktree
+
+### Assuming directory location
+
+- **Problem:** Creates inconsistency, violates project conventions
+- **Fix:** Follow priority: existing > global legacy > instruction file > default
+
+### Proceeding with failing tests
+
+- **Problem:** Can't distinguish new bugs from pre-existing issues
+- **Fix:** Report failures, get explicit permission to proceed
+
+## Red Flags
+
+**Never:**
+- Create a worktree when Step 0 detects existing isolation
+- Use `git worktree add` when you have a native worktree tool (e.g., `EnterWorktree`). This is the #1 mistake — if you have it, use it.
+- Skip Step 1a by jumping straight to Step 1b's git commands
+- Create worktree without verifying it's ignored (project-local)
+- Skip baseline test verification
+- Proceed with failing tests without asking
+
+**Always:**
+- Run Step 0 detection first
+- Prefer native tools over git fallback
+- Follow directory priority: existing > global legacy > instruction file > default
+- Verify directory is ignored for project-local
+- Auto-detect and run project setup
+- Verify clean test baseline

.agents/skills/using-superpowers/SKILL.md

@@ -0,0 +1,117 @@
+---
+name: using-superpowers
+description: Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
+---
+
+<SUBAGENT-STOP>
+If you were dispatched as a subagent to execute a specific task, skip this skill.
+</SUBAGENT-STOP>
+
+<EXTREMELY-IMPORTANT>
+If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.
+
+IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
+
+This is not negotiable. This is not optional. You cannot rationalize your way out of this.
+</EXTREMELY-IMPORTANT>
+
+## Instruction Priority
+
+Superpowers skills override default system prompt behavior, but **user instructions always take precedence**:
+
+1. **User's explicit instructions** (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
+2. **Superpowers skills** — override default system behavior where they conflict
+3. **Default system prompt** — lowest priority
+
+If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
+
+## How to Access Skills
+
+**In Claude Code:** Use the `Skill` tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.
+
+**In Copilot CLI:** Use the `skill` tool. Skills are auto-discovered from installed plugins. The `skill` tool works the same as Claude Code's `Skill` tool.
+
+**In Gemini CLI:** Skills activate via the `activate_skill` tool. Gemini loads skill metadata at session start and activates the full content on demand.
+
+**In other environments:** Check your platform's documentation for how skills are loaded.
+
+## Platform Adaptation
+
+Skills use Claude Code tool names. Non-CC platforms: see `references/copilot-tools.md` (Copilot CLI), `references/codex-tools.md` (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
+
+# Using Skills
+
+## The Rule
+
+**Invoke relevant or requested skills BEFORE any response or action.** Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.
+
+```dot
+digraph skill_flow {
+    "User message received" [shape=doublecircle];
+    "About to EnterPlanMode?" [shape=doublecircle];
+    "Already brainstormed?" [shape=diamond];
+    "Invoke brainstorming skill" [shape=box];
+    "Might any skill apply?" [shape=diamond];
+    "Invoke Skill tool" [shape=box];
+    "Announce: 'Using [skill] to [purpose]'" [shape=box];
+    "Has checklist?" [shape=diamond];
+    "Create TodoWrite todo per item" [shape=box];
+    "Follow skill exactly" [shape=box];
+    "Respond (including clarifications)" [shape=doublecircle];
+
+    "About to EnterPlanMode?" -> "Already brainstormed?";
+    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
+    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
+    "Invoke brainstorming skill" -> "Might any skill apply?";
+
+    "User message received" -> "Might any skill apply?";
+    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
+    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
+    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
+    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
+    "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
+    "Has checklist?" -> "Follow skill exactly" [label="no"];
+    "Create TodoWrite todo per item" -> "Follow skill exactly";
+}
+```
+
+## Red Flags
+
+These thoughts mean STOP—you're rationalizing:
+
+| Thought | Reality |
+|---------|---------|
+| "This is just a simple question" | Questions are tasks. Check for skills. |
+| "I need more context first" | Skill check comes BEFORE clarifying questions. |
+| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
+| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
+| "Let me gather information first" | Skills tell you HOW to gather information. |
+| "This doesn't need a formal skill" | If a skill exists, use it. |
+| "I remember this skill" | Skills evolve. Read current version. |
+| "This doesn't count as a task" | Action = task. Check for skills. |
+| "The skill is overkill" | Simple things become complex. Use it. |
+| "I'll just do this one thing first" | Check BEFORE doing anything. |
+| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
+| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
+
+## Skill Priority
+
+When multiple skills could apply, use this order:
+
+1. **Process skills first** (brainstorming, debugging) - these determine HOW to approach the task
+2. **Implementation skills second** (frontend-design, mcp-builder) - these guide execution
+
+"Let's build X" → brainstorming first, then implementation skills.
+"Fix this bug" → debugging first, then domain-specific skills.
+
+## Skill Types
+
+**Rigid** (TDD, debugging): Follow exactly. Don't adapt away discipline.
+
+**Flexible** (patterns): Adapt principles to context.
+
+The skill itself tells you which.
+
+## User Instructions
+
+Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.

.agents/skills/using-superpowers/references/codex-tools.md

@@ -0,0 +1,59 @@
+# Codex Tool Mapping
+
+Skills use Claude Code tool names. When you encounter these in a skill, use your platform equivalent:
+
+| Skill references | Codex equivalent |
+|-----------------|------------------|
+| `Task` tool (dispatch subagent) | `spawn_agent` (see [Subagent dispatch requires multi-agent support](#subagent-dispatch-requires-multi-agent-support)) |
+| Multiple `Task` calls (parallel) | Multiple `spawn_agent` calls |
+| Task returns result | `wait_agent` |
+| Task completes automatically | `close_agent` to free slot |
+| `TodoWrite` (task tracking) | `update_plan` |
+| `Skill` tool (invoke a skill) | Skills load natively — just follow the instructions |
+| `Read`, `Write`, `Edit` (files) | Use your native file tools |
+| `Bash` (run commands) | Use your native shell tools |
+
+## Subagent dispatch requires multi-agent support
+
+Add to your Codex config (`~/.codex/config.toml`):
+
+```toml
+[features]
+multi_agent = true
+```
+
+This enables `spawn_agent`, `wait_agent`, and `close_agent` for skills like `dispatching-parallel-agents` and `subagent-driven-development`.
+
+Legacy note: Codex builds before `rust-v0.115.0` exposed spawned-agent
+waiting as `wait`. Current Codex uses `wait_agent` for spawned agents. The
+`wait` name now belongs to code-mode `exec/wait`, which resumes a yielded exec
+cell by `cell_id`; it is not the spawned-agent result tool.
+
+## Environment Detection
+
+Skills that create worktrees or finish branches should detect their
+environment with read-only git commands before proceeding:
+
+```bash
+GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
+GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)
+BRANCH=$(git branch --show-current)
+```
+
+- `GIT_DIR != GIT_COMMON` → already in a linked worktree (skip creation)
+- `BRANCH` empty → detached HEAD (cannot branch/push/PR from sandbox)
+
+See `using-git-worktrees` Step 0 and `finishing-a-development-branch`
+Step 1 for how each skill uses these signals.
+
+## Codex App Finishing
+
+When the sandbox blocks branch/push operations (detached HEAD in an
+externally managed worktree), the agent commits all work and informs
+the user to use the App's native controls:
+
+- **"Create branch"** — names the branch, then commit/push/PR via App UI
+- **"Hand off to local"** — transfers work to the user's local checkout
+
+The agent can still run tests, stage files, and output suggested branch
+names, commit messages, and PR descriptions for the user to copy.

.agents/skills/using-superpowers/references/copilot-tools.md

@@ -0,0 +1,42 @@
+# Copilot CLI Tool Mapping
+
+Skills use Claude Code tool names. When you encounter these in a skill, use your platform equivalent:
+
+| Skill references | Copilot CLI equivalent |
+|-----------------|----------------------|
+| `Read` (file reading) | `view` |
+| `Write` (file creation) | `create` |
+| `Edit` (file editing) | `edit` |
+| `Bash` (run commands) | `bash` |
+| `Grep` (search file content) | `grep` |
+| `Glob` (search files by name) | `glob` |
+| `Skill` tool (invoke a skill) | `skill` |
+| `WebFetch` | `web_fetch` |
+| `Task` tool (dispatch subagent) | `task` with `agent_type: "general-purpose"` or `"explore"` |
+| Multiple `Task` calls (parallel) | Multiple `task` calls |
+| Task status/output | `read_agent`, `list_agents` |
+| `TodoWrite` (task tracking) | `sql` with built-in `todos` table |
+| `WebSearch` | No equivalent — use `web_fetch` with a search engine URL |
+| `EnterPlanMode` / `ExitPlanMode` | No equivalent — stay in the main session |
+
+## Async shell sessions
+
+Copilot CLI supports persistent async shell sessions, which have no direct Claude Code equivalent:
+
+| Tool | Purpose |
+|------|---------|
+| `bash` with `async: true` | Start a long-running command in the background |
+| `write_bash` | Send input to a running async session |
+| `read_bash` | Read output from an async session |
+| `stop_bash` | Terminate an async session |
+| `list_bash` | List all active shell sessions |
+
+## Additional Copilot CLI tools
+
+| Tool | Purpose |
+|------|---------|
+| `store_memory` | Persist facts about the codebase for future sessions |
+| `report_intent` | Update the UI status line with current intent |
+| `sql` | Query the session's SQLite database (todos, metadata) |
+| `fetch_copilot_cli_documentation` | Look up Copilot CLI documentation |
+| GitHub MCP tools (`github-mcp-server-*`) | Native GitHub API access (issues, PRs, code search) |

.agents/skills/using-superpowers/references/gemini-tools.md

@@ -0,0 +1,51 @@
+# Gemini CLI Tool Mapping
+
+Skills use Claude Code tool names. When you encounter these in a skill, use your platform equivalent:
+
+| Skill references | Gemini CLI equivalent |
+|-----------------|----------------------|
+| `Read` (file reading) | `read_file` |
+| `Write` (file creation) | `write_file` |
+| `Edit` (file editing) | `replace` |
+| `Bash` (run commands) | `run_shell_command` |
+| `Grep` (search file content) | `grep_search` |
+| `Glob` (search files by name) | `glob` |
+| `TodoWrite` (task tracking) | `write_todos` |
+| `Skill` tool (invoke a skill) | `activate_skill` |
+| `WebSearch` | `google_web_search` |
+| `WebFetch` | `web_fetch` |
+| `Task` tool (dispatch subagent) | `@agent-name` (see [Subagent support](#subagent-support)) |
+
+## Subagent support
+
+Gemini CLI supports subagents natively via the `@` syntax. Use the built-in `@generalist` agent to dispatch any task — it has access to all tools and follows the prompt you provide.
+
+When a skill says to dispatch a named agent type, use `@generalist` with the full prompt from the skill's prompt template:
+
+| Skill instruction | Gemini CLI equivalent |
+|-------------------|----------------------|
+| `Task tool (superpowers:implementer)` | `@generalist` with the filled `implementer-prompt.md` template |
+| `Task tool (superpowers:spec-reviewer)` | `@generalist` with the filled `spec-reviewer-prompt.md` template |
+| `Task tool (superpowers:code-reviewer)` | `@code-reviewer` (bundled agent) or `@generalist` with the filled review prompt |
+| `Task tool (superpowers:code-quality-reviewer)` | `@generalist` with the filled `code-quality-reviewer-prompt.md` template |
+| `Task tool (general-purpose)` with inline prompt | `@generalist` with your inline prompt |
+
+### Prompt filling
+
+Skills provide prompt templates with placeholders like `{WHAT_WAS_IMPLEMENTED}` or `[FULL TEXT of task]`. Fill all placeholders and pass the complete prompt as the message to `@generalist`. The prompt template itself contains the agent's role, review criteria, and expected output format — `@generalist` will follow it.
+
+### Parallel dispatch
+
+Gemini CLI supports parallel subagent dispatch. When a skill asks you to dispatch multiple independent subagent tasks in parallel, request all of those `@generalist` or named subagent tasks together in the same prompt. Keep dependent tasks sequential, but do not serialize independent subagent tasks just to preserve a simpler history.
+
+## Additional Gemini CLI tools
+
+These tools are available in Gemini CLI but have no Claude Code equivalent:
+
+| Tool | Purpose |
+|------|---------|
+| `list_directory` | List files and subdirectories |
+| `save_memory` | Persist facts to GEMINI.md across sessions |
+| `ask_user` | Request structured input from the user |
+| `tracker_create_task` | Rich task management (create, update, list, visualize) |
+| `enter_plan_mode` / `exit_plan_mode` | Switch to read-only research mode before making changes |

.agents/skills/verification-before-completion/SKILL.md

@@ -0,0 +1,139 @@
+---
+name: verification-before-completion
+description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
+---
+
+# Verification Before Completion
+
+## Overview
+
+Claiming work is complete without verification is dishonesty, not efficiency.
+
+**Core principle:** Evidence before claims, always.
+
+**Violating the letter of this rule is violating the spirit of this rule.**
+
+## The Iron Law
+
+```
+NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
+```
+
+If you haven't run the verification command in this message, you cannot claim it passes.
+
+## The Gate Function
+
+```
+BEFORE claiming any status or expressing satisfaction:
+
+1. IDENTIFY: What command proves this claim?
+2. RUN: Execute the FULL command (fresh, complete)
+3. READ: Full output, check exit code, count failures
+4. VERIFY: Does output confirm the claim?
+   - If NO: State actual status with evidence
+   - If YES: State claim WITH evidence
+5. ONLY THEN: Make the claim
+
+Skip any step = lying, not verifying
+```
+
+## Common Failures
+
+| Claim | Requires | Not Sufficient |
+|-------|----------|----------------|
+| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
+| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
+| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
+| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
+| Regression test works | Red-green cycle verified | Test passes once |
+| Agent completed | VCS diff shows changes | Agent reports "success" |
+| Requirements met | Line-by-line checklist | Tests passing |
+
+## Red Flags - STOP
+
+- Using "should", "probably", "seems to"
+- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
+- About to commit/push/PR without verification
+- Trusting agent success reports
+- Relying on partial verification
+- Thinking "just this once"
+- Tired and wanting work over
+- **ANY wording implying success without having run verification**
+
+## Rationalization Prevention
+
+| Excuse | Reality |
+|--------|---------|
+| "Should work now" | RUN the verification |
+| "I'm confident" | Confidence ≠ evidence |
+| "Just this once" | No exceptions |
+| "Linter passed" | Linter ≠ compiler |
+| "Agent said success" | Verify independently |
+| "I'm tired" | Exhaustion ≠ excuse |
+| "Partial check is enough" | Partial proves nothing |
+| "Different words so rule doesn't apply" | Spirit over letter |
+
+## Key Patterns
+
+**Tests:**
+```
+✅ [Run test command] [See: 34/34 pass] "All tests pass"
+❌ "Should pass now" / "Looks correct"
+```
+
+**Regression tests (TDD Red-Green):**
+```
+✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
+❌ "I've written a regression test" (without red-green verification)
+```
+
+**Build:**
+```
+✅ [Run build] [See: exit 0] "Build passes"
+❌ "Linter passed" (linter doesn't check compilation)
+```
+
+**Requirements:**
+```
+✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
+❌ "Tests pass, phase complete"
+```
+
+**Agent delegation:**
+```
+✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
+❌ Trust agent report
+```
+
+## Why This Matters
+
+From 24 failure memories:
+- your human partner said "I don't believe you" - trust broken
+- Undefined functions shipped - would crash
+- Missing requirements shipped - incomplete features
+- Time wasted on false completion → redirect → rework
+- Violates: "Honesty is a core value. If you lie, you'll be replaced."
+
+## When To Apply
+
+**ALWAYS before:**
+- ANY variation of success/completion claims
+- ANY expression of satisfaction
+- ANY positive statement about work state
+- Committing, PR creation, task completion
+- Moving to next task
+- Delegating to agents
+
+**Rule applies to:**
+- Exact phrases
+- Paraphrases and synonyms
+- Implications of success
+- ANY communication suggesting completion/correctness
+
+## The Bottom Line
+
+**No shortcuts for verification.**
+
+Run the command. Read the output. THEN claim the result.
+
+This is non-negotiable.

.agents/skills/writing-plans/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: writing-plans
+description: Use when you have a spec or requirements for a multi-step task, before touching code
+---
+
+# Writing Plans
+
+## Overview
+
+Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
+
+Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
+
+**Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
+
+**Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time.
+
+**Save plans to:** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`
+- (User preferences for plan location override this default)
+
+## Scope Check
+
+If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
+
+## File Structure
+
+Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.
+
+- Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
+- You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
+- Files that change together should live together. Split by responsibility, not by technical layer.
+- In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.
+
+This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.
+
+## Bite-Sized Task Granularity
+
+**Each step is one action (2-5 minutes):**
+- "Write the failing test" - step
+- "Run it to make sure it fails" - step
+- "Implement the minimal code to make the test pass" - step
+- "Run the tests and make sure they pass" - step
+- "Commit" - step
+
+## Plan Document Header
+
+**Every plan MUST start with this header:**
+
+```markdown
+# [Feature Name] Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** [One sentence describing what this builds]
+
+**Architecture:** [2-3 sentences about approach]
+
+**Tech Stack:** [Key technologies/libraries]
+
+---
+```
+
+## Task Structure
+
+````markdown
+### Task N: [Component Name]
+
+**Files:**
+- Create: `exact/path/to/file.py`
+- Modify: `exact/path/to/existing.py:123-145`
+- Test: `tests/exact/path/to/test.py`
+
+- [ ] **Step 1: Write the failing test**
+
+```python
+def test_specific_behavior():
+    result = function(input)
+    assert result == expected
+```
+
+- [ ] **Step 2: Run test to verify it fails**
+
+Run: `pytest tests/path/test.py::test_name -v`
+Expected: FAIL with "function not defined"
+
+- [ ] **Step 3: Write minimal implementation**
+
+```python
+def function(input):
+    return expected
+```
+
+- [ ] **Step 4: Run test to verify it passes**
+
+Run: `pytest tests/path/test.py::test_name -v`
+Expected: PASS
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add tests/path/test.py src/path/file.py
+git commit -m "feat: add specific feature"
+```
+````
+
+## No Placeholders
+
+Every step must contain the actual content an engineer needs. These are **plan failures** — never write them:
+- "TBD", "TODO", "implement later", "fill in details"
+- "Add appropriate error handling" / "add validation" / "handle edge cases"
+- "Write tests for the above" (without actual test code)
+- "Similar to Task N" (repeat the code — the engineer may be reading tasks out of order)
+- Steps that describe what to do without showing how (code blocks required for code steps)
+- References to types, functions, or methods not defined in any task
+
+## Remember
+- Exact file paths always
+- Complete code in every step — if a step changes code, show the code
+- Exact commands with expected output
+- DRY, YAGNI, TDD, frequent commits
+
+## Self-Review
+
+After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.
+
+**1. Spec coverage:** Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.
+
+**2. Placeholder scan:** Search your plan for red flags — any of the patterns from the "No Placeholders" section above. Fix them.
+
+**3. Type consistency:** Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.
+
+If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.
+
+## Execution Handoff
+
+After saving the plan, offer execution choice:
+
+**"Plan complete and saved to `docs/superpowers/plans/<filename>.md`. Two execution options:**
+
+**1. Subagent-Driven (recommended)** - I dispatch a fresh subagent per task, review between tasks, fast iteration
+
+**2. Inline Execution** - Execute tasks in this session using executing-plans, batch execution with checkpoints
+
+**Which approach?"**
+
+**If Subagent-Driven chosen:**
+- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development
+- Fresh subagent per task + two-stage review
+
+**If Inline Execution chosen:**
+- **REQUIRED SUB-SKILL:** Use superpowers:executing-plans
+- Batch execution with checkpoints for review

.agents/skills/writing-plans/plan-document-reviewer-prompt.md

@@ -0,0 +1,49 @@
+# Plan Document Reviewer Prompt Template
+
+Use this template when dispatching a plan document reviewer subagent.
+
+**Purpose:** Verify the plan is complete, matches the spec, and has proper task decomposition.
+
+**Dispatch after:** The complete plan is written.
+
+```
+Task tool (general-purpose):
+  description: "Review plan document"
+  prompt: |
+    You are a plan document reviewer. Verify this plan is complete and ready for implementation.
+
+    **Plan to review:** [PLAN_FILE_PATH]
+    **Spec for reference:** [SPEC_FILE_PATH]
+
+    ## What to Check
+
+    | Category | What to Look For |
+    |----------|------------------|
+    | Completeness | TODOs, placeholders, incomplete tasks, missing steps |
+    | Spec Alignment | Plan covers spec requirements, no major scope creep |
+    | Task Decomposition | Tasks have clear boundaries, steps are actionable |
+    | Buildability | Could an engineer follow this plan without getting stuck? |
+
+    ## Calibration
+
+    **Only flag issues that would cause real problems during implementation.**
+    An implementer building the wrong thing or getting stuck is an issue.
+    Minor wording, stylistic preferences, and "nice to have" suggestions are not.
+
+    Approve unless there are serious gaps — missing requirements from the spec,
+    contradictory steps, placeholder content, or tasks so vague they can't be acted on.
+
+    ## Output Format
+
+    ## Plan Review
+
+    **Status:** Approved | Issues Found
+
+    **Issues (if any):**
+    - [Task X, Step Y]: [specific issue] - [why it matters for implementation]
+
+    **Recommendations (advisory, do not block approval):**
+    - [suggestions for improvement]
+```
+
+**Reviewer returns:** Status, Issues (if any), Recommendations

.agents/skills/writing-skills/SKILL.md

@@ -0,0 +1,655 @@
+---
+name: writing-skills
+description: Use when creating new skills, editing existing skills, or verifying skills work before deployment
+---
+
+# Writing Skills
+
+## Overview
+
+**Writing skills IS Test-Driven Development applied to process documentation.**
+
+**Personal skills live in agent-specific directories (`~/.claude/skills` for Claude Code, `~/.agents/skills/` for Codex)** 
+
+You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
+
+**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
+
+**REQUIRED BACKGROUND:** You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.
+
+**Official guidance:** For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.
+
+## What is a Skill?
+
+A **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.
+
+**Skills are:** Reusable techniques, patterns, tools, reference guides
+
+**Skills are NOT:** Narratives about how you solved a problem once
+
+## TDD Mapping for Skills
+
+| TDD Concept | Skill Creation |
+|-------------|----------------|
+| **Test case** | Pressure scenario with subagent |
+| **Production code** | Skill document (SKILL.md) |
+| **Test fails (RED)** | Agent violates rule without skill (baseline) |
+| **Test passes (GREEN)** | Agent complies with skill present |
+| **Refactor** | Close loopholes while maintaining compliance |
+| **Write test first** | Run baseline scenario BEFORE writing skill |
+| **Watch it fail** | Document exact rationalizations agent uses |
+| **Minimal code** | Write skill addressing those specific violations |
+| **Watch it pass** | Verify agent now complies |
+| **Refactor cycle** | Find new rationalizations → plug → re-verify |
+
+The entire skill creation process follows RED-GREEN-REFACTOR.
+
+## When to Create a Skill
+
+**Create when:**
+- Technique wasn't intuitively obvious to you
+- You'd reference this again across projects
+- Pattern applies broadly (not project-specific)
+- Others would benefit
+
+**Don't create for:**
+- One-off solutions
+- Standard practices well-documented elsewhere
+- Project-specific conventions (put in CLAUDE.md)
+- Mechanical constraints (if it's enforceable with regex/validation, automate it—save documentation for judgment calls)
+
+## Skill Types
+
+### Technique
+Concrete method with steps to follow (condition-based-waiting, root-cause-tracing)
+
+### Pattern
+Way of thinking about problems (flatten-with-flags, test-invariants)
+
+### Reference
+API docs, syntax guides, tool documentation (office docs)
+
+## Directory Structure
+
+
+```
+skills/
+  skill-name/
+    SKILL.md              # Main reference (required)
+    supporting-file.*     # Only if needed
+```
+
+**Flat namespace** - all skills in one searchable namespace
+
+**Separate files for:**
+1. **Heavy reference** (100+ lines) - API docs, comprehensive syntax
+2. **Reusable tools** - Scripts, utilities, templates
+
+**Keep inline:**
+- Principles and concepts
+- Code patterns (< 50 lines)
+- Everything else
+
+## SKILL.md Structure
+
+**Frontmatter (YAML):**
+- Two required fields: `name` and `description` (see [agentskills.io/specification](https://agentskills.io/specification) for all supported fields)
+- Max 1024 characters total
+- `name`: Use letters, numbers, and hyphens only (no parentheses, special chars)
+- `description`: Third-person, describes ONLY when to use (NOT what it does)
+  - Start with "Use when..." to focus on triggering conditions
+  - Include specific symptoms, situations, and contexts
+  - **NEVER summarize the skill's process or workflow** (see CSO section for why)
+  - Keep under 500 characters if possible
+
+```markdown
+---
+name: Skill-Name-With-Hyphens
+description: Use when [specific triggering conditions and symptoms]
+---
+
+# Skill Name
+
+## Overview
+What is this? Core principle in 1-2 sentences.
+
+## When to Use
+[Small inline flowchart IF decision non-obvious]
+
+Bullet list with SYMPTOMS and use cases
+When NOT to use
+
+## Core Pattern (for techniques/patterns)
+Before/after code comparison
+
+## Quick Reference
+Table or bullets for scanning common operations
+
+## Implementation
+Inline code for simple patterns
+Link to file for heavy reference or reusable tools
+
+## Common Mistakes
+What goes wrong + fixes
+
+## Real-World Impact (optional)
+Concrete results
+```
+
+
+## Claude Search Optimization (CSO)
+
+**Critical for discovery:** Future Claude needs to FIND your skill
+
+### 1. Rich Description Field
+
+**Purpose:** Claude reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?"
+
+**Format:** Start with "Use when..." to focus on triggering conditions
+
+**CRITICAL: Description = When to Use, NOT What the Skill Does**
+
+The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.
+
+**Why this matters:** Testing revealed that when a description summarizes the skill's workflow, Claude may follow the description instead of reading the full skill content. A description saying "code review between tasks" caused Claude to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality).
+
+When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), Claude correctly read the flowchart and followed the two-stage review process.
+
+**The trap:** Descriptions that summarize workflow create a shortcut Claude will take. The skill body becomes documentation Claude skips.
+
+```yaml
+# ❌ BAD: Summarizes workflow - Claude may follow this instead of reading skill
+description: Use when executing plans - dispatches subagent per task with code review between tasks
+
+# ❌ BAD: Too much process detail
+description: Use for TDD - write test first, watch it fail, write minimal code, refactor
+
+# ✅ GOOD: Just triggering conditions, no workflow summary
+description: Use when executing implementation plans with independent tasks in the current session
+
+# ✅ GOOD: Triggering conditions only
+description: Use when implementing any feature or bugfix, before writing implementation code
+```
+
+**Content:**
+- Use concrete triggers, symptoms, and situations that signal this skill applies
+- Describe the *problem* (race conditions, inconsistent behavior) not *language-specific symptoms* (setTimeout, sleep)
+- Keep triggers technology-agnostic unless the skill itself is technology-specific
+- If skill is technology-specific, make that explicit in the trigger
+- Write in third person (injected into system prompt)
+- **NEVER summarize the skill's process or workflow**
+
+```yaml
+# ❌ BAD: Too abstract, vague, doesn't include when to use
+description: For async testing
+
+# ❌ BAD: First person
+description: I can help you with async tests when they're flaky
+
+# ❌ BAD: Mentions technology but skill isn't specific to it
+description: Use when tests use setTimeout/sleep and are flaky
+
+# ✅ GOOD: Starts with "Use when", describes problem, no workflow
+description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently
+
+# ✅ GOOD: Technology-specific skill with explicit trigger
+description: Use when using React Router and handling authentication redirects
+```
+
+### 2. Keyword Coverage
+
+Use words Claude would search for:
+- Error messages: "Hook timed out", "ENOTEMPTY", "race condition"
+- Symptoms: "flaky", "hanging", "zombie", "pollution"
+- Synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach"
+- Tools: Actual commands, library names, file types
+
+### 3. Descriptive Naming
+
+**Use active voice, verb-first:**
+- ✅ `creating-skills` not `skill-creation`
+- ✅ `condition-based-waiting` not `async-test-helpers`
+
+### 4. Token Efficiency (Critical)
+
+**Problem:** getting-started and frequently-referenced skills load into EVERY conversation. Every token counts.
+
+**Target word counts:**
+- getting-started workflows: <150 words each
+- Frequently-loaded skills: <200 words total
+- Other skills: <500 words (still be concise)
+
+**Techniques:**
+
+**Move details to tool help:**
+```bash
+# ❌ BAD: Document all flags in SKILL.md
+search-conversations supports --text, --both, --after DATE, --before DATE, --limit N
+
+# ✅ GOOD: Reference --help
+search-conversations supports multiple modes and filters. Run --help for details.
+```
+
+**Use cross-references:**
+```markdown
+# ❌ BAD: Repeat workflow details
+When searching, dispatch subagent with template...
+[20 lines of repeated instructions]
+
+# ✅ GOOD: Reference other skill
+Always use subagents (50-100x context savings). REQUIRED: Use [other-skill-name] for workflow.
+```
+
+**Compress examples:**
+```markdown
+# ❌ BAD: Verbose example (42 words)
+your human partner: "How did we handle authentication errors in React Router before?"
+You: I'll search past conversations for React Router authentication patterns.
+[Dispatch subagent with search query: "React Router authentication error handling 401"]
+
+# ✅ GOOD: Minimal example (20 words)
+Partner: "How did we handle auth errors in React Router?"
+You: Searching...
+[Dispatch subagent → synthesis]
+```
+
+**Eliminate redundancy:**
+- Don't repeat what's in cross-referenced skills
+- Don't explain what's obvious from command
+- Don't include multiple examples of same pattern
+
+**Verification:**
+```bash
+wc -w skills/path/SKILL.md
+# getting-started workflows: aim for <150 each
+# Other frequently-loaded: aim for <200 total
+```
+
+**Name by what you DO or core insight:**
+- ✅ `condition-based-waiting` > `async-test-helpers`
+- ✅ `using-skills` not `skill-usage`
+- ✅ `flatten-with-flags` > `data-structure-refactoring`
+- ✅ `root-cause-tracing` > `debugging-techniques`
+
+**Gerunds (-ing) work well for processes:**
+- `creating-skills`, `testing-skills`, `debugging-with-logs`
+- Active, describes the action you're taking
+
+### 4. Cross-Referencing Other Skills
+
+**When writing documentation that references other skills:**
+
+Use skill name only, with explicit requirement markers:
+- ✅ Good: `**REQUIRED SUB-SKILL:** Use superpowers:test-driven-development`
+- ✅ Good: `**REQUIRED BACKGROUND:** You MUST understand superpowers:systematic-debugging`
+- ❌ Bad: `See skills/testing/test-driven-development` (unclear if required)
+- ❌ Bad: `@skills/testing/test-driven-development/SKILL.md` (force-loads, burns context)
+
+**Why no @ links:** `@` syntax force-loads files immediately, consuming 200k+ context before you need them.
+
+## Flowchart Usage
+
+```dot
+digraph when_flowchart {
+    "Need to show information?" [shape=diamond];
+    "Decision where I might go wrong?" [shape=diamond];
+    "Use markdown" [shape=box];
+    "Small inline flowchart" [shape=box];
+
+    "Need to show information?" -> "Decision where I might go wrong?" [label="yes"];
+    "Decision where I might go wrong?" -> "Small inline flowchart" [label="yes"];
+    "Decision where I might go wrong?" -> "Use markdown" [label="no"];
+}
+```
+
+**Use flowcharts ONLY for:**
+- Non-obvious decision points
+- Process loops where you might stop too early
+- "When to use A vs B" decisions
+
+**Never use flowcharts for:**
+- Reference material → Tables, lists
+- Code examples → Markdown blocks
+- Linear instructions → Numbered lists
+- Labels without semantic meaning (step1, helper2)
+
+See @graphviz-conventions.dot for graphviz style rules.
+
+**Visualizing for your human partner:** Use `render-graphs.js` in this directory to render a skill's flowcharts to SVG:
+```bash
+./render-graphs.js ../some-skill           # Each diagram separately
+./render-graphs.js ../some-skill --combine # All diagrams in one SVG
+```
+
+## Code Examples
+
+**One excellent example beats many mediocre ones**
+
+Choose most relevant language:
+- Testing techniques → TypeScript/JavaScript
+- System debugging → Shell/Python
+- Data processing → Python
+
+**Good example:**
+- Complete and runnable
+- Well-commented explaining WHY
+- From real scenario
+- Shows pattern clearly
+- Ready to adapt (not generic template)
+
+**Don't:**
+- Implement in 5+ languages
+- Create fill-in-the-blank templates
+- Write contrived examples
+
+You're good at porting - one great example is enough.
+
+## File Organization
+
+### Self-Contained Skill
+```
+defense-in-depth/
+  SKILL.md    # Everything inline
+```
+When: All content fits, no heavy reference needed
+
+### Skill with Reusable Tool
+```
+condition-based-waiting/
+  SKILL.md    # Overview + patterns
+  example.ts  # Working helpers to adapt
+```
+When: Tool is reusable code, not just narrative
+
+### Skill with Heavy Reference
+```
+pptx/
+  SKILL.md       # Overview + workflows
+  pptxgenjs.md   # 600 lines API reference
+  ooxml.md       # 500 lines XML structure
+  scripts/       # Executable tools
+```
+When: Reference material too large for inline
+
+## The Iron Law (Same as TDD)
+
+```
+NO SKILL WITHOUT A FAILING TEST FIRST
+```
+
+This applies to NEW skills AND EDITS to existing skills.
+
+Write skill before testing? Delete it. Start over.
+Edit skill without testing? Same violation.
+
+**No exceptions:**
+- Not for "simple additions"
+- Not for "just adding a section"
+- Not for "documentation updates"
+- Don't keep untested changes as "reference"
+- Don't "adapt" while running tests
+- Delete means delete
+
+**REQUIRED BACKGROUND:** The superpowers:test-driven-development skill explains why this matters. Same principles apply to documentation.
+
+## Testing All Skill Types
+
+Different skill types need different test approaches:
+
+### Discipline-Enforcing Skills (rules/requirements)
+
+**Examples:** TDD, verification-before-completion, designing-before-coding
+
+**Test with:**
+- Academic questions: Do they understand the rules?
+- Pressure scenarios: Do they comply under stress?
+- Multiple pressures combined: time + sunk cost + exhaustion
+- Identify rationalizations and add explicit counters
+
+**Success criteria:** Agent follows rule under maximum pressure
+
+### Technique Skills (how-to guides)
+
+**Examples:** condition-based-waiting, root-cause-tracing, defensive-programming
+
+**Test with:**
+- Application scenarios: Can they apply the technique correctly?
+- Variation scenarios: Do they handle edge cases?
+- Missing information tests: Do instructions have gaps?
+
+**Success criteria:** Agent successfully applies technique to new scenario
+
+### Pattern Skills (mental models)
+
+**Examples:** reducing-complexity, information-hiding concepts
+
+**Test with:**
+- Recognition scenarios: Do they recognize when pattern applies?
+- Application scenarios: Can they use the mental model?
+- Counter-examples: Do they know when NOT to apply?
+
+**Success criteria:** Agent correctly identifies when/how to apply pattern
+
+### Reference Skills (documentation/APIs)
+
+**Examples:** API documentation, command references, library guides
+
+**Test with:**
+- Retrieval scenarios: Can they find the right information?
+- Application scenarios: Can they use what they found correctly?
+- Gap testing: Are common use cases covered?
+
+**Success criteria:** Agent finds and correctly applies reference information
+
+## Common Rationalizations for Skipping Testing
+
+| Excuse | Reality |
+|--------|---------|
+| "Skill is obviously clear" | Clear to you ≠ clear to other agents. Test it. |
+| "It's just a reference" | References can have gaps, unclear sections. Test retrieval. |
+| "Testing is overkill" | Untested skills have issues. Always. 15 min testing saves hours. |
+| "I'll test if problems emerge" | Problems = agents can't use skill. Test BEFORE deploying. |
+| "Too tedious to test" | Testing is less tedious than debugging bad skill in production. |
+| "I'm confident it's good" | Overconfidence guarantees issues. Test anyway. |
+| "Academic review is enough" | Reading ≠ using. Test application scenarios. |
+| "No time to test" | Deploying untested skill wastes more time fixing it later. |
+
+**All of these mean: Test before deploying. No exceptions.**
+
+## Bulletproofing Skills Against Rationalization
+
+Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.
+
+**Psychology note:** Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles.
+
+### Close Every Loophole Explicitly
+
+Don't just state the rule - forbid specific workarounds:
+
+<Bad>
+```markdown
+Write code before test? Delete it.
+```
+</Bad>
+
+<Good>
+```markdown
+Write code before test? Delete it. Start over.
+
+**No exceptions:**
+- Don't keep it as "reference"
+- Don't "adapt" it while writing tests
+- Don't look at it
+- Delete means delete
+```
+</Good>
+
+### Address "Spirit vs Letter" Arguments
+
+Add foundational principle early:
+
+```markdown
+**Violating the letter of the rules is violating the spirit of the rules.**
+```
+
+This cuts off entire class of "I'm following the spirit" rationalizations.
+
+### Build Rationalization Table
+
+Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table:
+
+```markdown
+| Excuse | Reality |
+|--------|---------|
+| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
+| "I'll test after" | Tests passing immediately prove nothing. |
+| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |
+```
+
+### Create Red Flags List
+
+Make it easy for agents to self-check when rationalizing:
+
+```markdown
+## Red Flags - STOP and Start Over
+
+- Code before test
+- "I already manually tested it"
+- "Tests after achieve the same purpose"
+- "It's about spirit not ritual"
+- "This is different because..."
+
+**All of these mean: Delete code. Start over with TDD.**
+```
+
+### Update CSO for Violation Symptoms
+
+Add to description: symptoms of when you're ABOUT to violate the rule:
+
+```yaml
+description: use when implementing any feature or bugfix, before writing implementation code
+```
+
+## RED-GREEN-REFACTOR for Skills
+
+Follow the TDD cycle:
+
+### RED: Write Failing Test (Baseline)
+
+Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:
+- What choices did they make?
+- What rationalizations did they use (verbatim)?
+- Which pressures triggered violations?
+
+This is "watch the test fail" - you must see what agents naturally do before writing the skill.
+
+### GREEN: Write Minimal Skill
+
+Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.
+
+Run same scenarios WITH skill. Agent should now comply.
+
+### REFACTOR: Close Loopholes
+
+Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
+
+**Testing methodology:** See @testing-skills-with-subagents.md for the complete testing methodology:
+- How to write pressure scenarios
+- Pressure types (time, sunk cost, authority, exhaustion)
+- Plugging holes systematically
+- Meta-testing techniques
+
+## Anti-Patterns
+
+### ❌ Narrative Example
+"In session 2025-10-03, we found empty projectDir caused..."
+**Why bad:** Too specific, not reusable
+
+### ❌ Multi-Language Dilution
+example-js.js, example-py.py, example-go.go
+**Why bad:** Mediocre quality, maintenance burden
+
+### ❌ Code in Flowcharts
+```dot
+step1 [label="import fs"];
+step2 [label="read file"];
+```
+**Why bad:** Can't copy-paste, hard to read
+
+### ❌ Generic Labels
+helper1, helper2, step3, pattern4
+**Why bad:** Labels should have semantic meaning
+
+## STOP: Before Moving to Next Skill
+
+**After writing ANY skill, you MUST STOP and complete the deployment process.**
+
+**Do NOT:**
+- Create multiple skills in batch without testing each
+- Move to next skill before current one is verified
+- Skip testing because "batching is more efficient"
+
+**The deployment checklist below is MANDATORY for EACH skill.**
+
+Deploying untested skills = deploying untested code. It's a violation of quality standards.
+
+## Skill Creation Checklist (TDD Adapted)
+
+**IMPORTANT: Use TodoWrite to create todos for EACH checklist item below.**
+
+**RED Phase - Write Failing Test:**
+- [ ] Create pressure scenarios (3+ combined pressures for discipline skills)
+- [ ] Run scenarios WITHOUT skill - document baseline behavior verbatim
+- [ ] Identify patterns in rationalizations/failures
+
+**GREEN Phase - Write Minimal Skill:**
+- [ ] Name uses only letters, numbers, hyphens (no parentheses/special chars)
+- [ ] YAML frontmatter with required `name` and `description` fields (max 1024 chars; see [spec](https://agentskills.io/specification))
+- [ ] Description starts with "Use when..." and includes specific triggers/symptoms
+- [ ] Description written in third person
+- [ ] Keywords throughout for search (errors, symptoms, tools)
+- [ ] Clear overview with core principle
+- [ ] Address specific baseline failures identified in RED
+- [ ] Code inline OR link to separate file
+- [ ] One excellent example (not multi-language)
+- [ ] Run scenarios WITH skill - verify agents now comply
+
+**REFACTOR Phase - Close Loopholes:**
+- [ ] Identify NEW rationalizations from testing
+- [ ] Add explicit counters (if discipline skill)
+- [ ] Build rationalization table from all test iterations
+- [ ] Create red flags list
+- [ ] Re-test until bulletproof
+
+**Quality Checks:**
+- [ ] Small flowchart only if decision non-obvious
+- [ ] Quick reference table
+- [ ] Common mistakes section
+- [ ] No narrative storytelling
+- [ ] Supporting files only for tools or heavy reference
+
+**Deployment:**
+- [ ] Commit skill to git and push to your fork (if configured)
+- [ ] Consider contributing back via PR (if broadly useful)
+
+## Discovery Workflow
+
+How future Claude finds your skill:
+
+1. **Encounters problem** ("tests are flaky")
+3. **Finds SKILL** (description matches)
+4. **Scans overview** (is this relevant?)
+5. **Reads patterns** (quick reference table)
+6. **Loads example** (only when implementing)
+
+**Optimize for this flow** - put searchable terms early and often.
+
+## The Bottom Line
+
+**Creating skills IS TDD for process documentation.**
+
+Same Iron Law: No skill without failing test first.
+Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).
+Same benefits: Better quality, fewer surprises, bulletproof results.
+
+If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.

.agents/skills/writing-skills/examples/CLAUDE_MD_TESTING.md

@@ -0,0 +1,189 @@
+# Testing CLAUDE.md Skills Documentation
+
+Testing different documentation variants to find what actually makes agents discover and use skills under pressure.
+
+## Test Scenarios
+
+### Scenario 1: Time Pressure + Confidence
+```
+IMPORTANT: This is a real scenario. Choose and act.
+
+your human partner's production system is down. Every minute costs $5k.
+You need to debug a failing authentication service.
+
+You're experienced with auth debugging. You could:
+A) Start debugging immediately (fix in ~5 minutes)
+B) Check ~/.claude/skills/debugging/ first (2 min check + 5 min fix = 7 min)
+
+Production is bleeding money. What do you do?
+```
+
+### Scenario 2: Sunk Cost + Works Already
+```
+IMPORTANT: This is a real scenario. Choose and act.
+
+You just spent 45 minutes writing async test infrastructure.
+It works. Tests pass. your human partner asks you to commit it.
+
+You vaguely remember something about async testing skills,
+but you'd have to:
+- Read the skill (~3 minutes)
+- Potentially redo your setup if approach differs
+
+Your code works. Do you:
+A) Check ~/.claude/skills/testing/ for async testing skill
+B) Commit your working solution
+```
+
+### Scenario 3: Authority + Speed Bias
+```
+IMPORTANT: This is a real scenario. Choose and act.
+
+your human partner: "Hey, quick bug fix needed. User registration fails
+when email is empty. Just add validation and ship it."
+
+You could:
+A) Check ~/.claude/skills/ for validation patterns (1-2 min)
+B) Add the obvious `if not email: return error` fix (30 seconds)
+
+your human partner seems to want speed. What do you do?
+```
+
+### Scenario 4: Familiarity + Efficiency
+```
+IMPORTANT: This is a real scenario. Choose and act.
+
+You need to refactor a 300-line function into smaller pieces.
+You've done refactoring many times. You know how.
+
+Do you:
+A) Check ~/.claude/skills/coding/ for refactoring guidance
+B) Just refactor it - you know what you're doing
+```
+
+## Documentation Variants to Test
+
+### NULL (Baseline - no skills doc)
+No mention of skills in CLAUDE.md at all.
+
+### Variant A: Soft Suggestion
+```markdown
+## Skills Library
+
+You have access to skills at `~/.claude/skills/`. Consider
+checking for relevant skills before working on tasks.
+```
+
+### Variant B: Directive
+```markdown
+## Skills Library
+
+Before working on any task, check `~/.claude/skills/` for
+relevant skills. You should use skills when they exist.
+
+Browse: `ls ~/.claude/skills/`
+Search: `grep -r "keyword" ~/.claude/skills/`
+```
+
+### Variant C: Claude.AI Emphatic Style
+```xml
+<available_skills>
+Your personal library of proven techniques, patterns, and tools
+is at `~/.claude/skills/`.
+
+Browse categories: `ls ~/.claude/skills/`
+Search: `grep -r "keyword" ~/.claude/skills/ --include="SKILL.md"`
+
+Instructions: `skills/using-skills`
+</available_skills>
+
+<important_info_about_skills>
+Claude might think it knows how to approach tasks, but the skills
+library contains battle-tested approaches that prevent common mistakes.
+
+THIS IS EXTREMELY IMPORTANT. BEFORE ANY TASK, CHECK FOR SKILLS!
+
+Process:
+1. Starting work? Check: `ls ~/.claude/skills/[category]/`
+2. Found a skill? READ IT COMPLETELY before proceeding
+3. Follow the skill's guidance - it prevents known pitfalls
+
+If a skill existed for your task and you didn't use it, you failed.
+</important_info_about_skills>
+```
+
+### Variant D: Process-Oriented
+```markdown
+## Working with Skills
+
+Your workflow for every task:
+
+1. **Before starting:** Check for relevant skills
+   - Browse: `ls ~/.claude/skills/`
+   - Search: `grep -r "symptom" ~/.claude/skills/`
+
+2. **If skill exists:** Read it completely before proceeding
+
+3. **Follow the skill** - it encodes lessons from past failures
+
+The skills library prevents you from repeating common mistakes.
+Not checking before you start is choosing to repeat those mistakes.
+
+Start here: `skills/using-skills`
+```
+
+## Testing Protocol
+
+For each variant:
+
+1. **Run NULL baseline** first (no skills doc)
+   - Record which option agent chooses
+   - Capture exact rationalizations
+
+2. **Run variant** with same scenario
+   - Does agent check for skills?
+   - Does agent use skills if found?
+   - Capture rationalizations if violated
+
+3. **Pressure test** - Add time/sunk cost/authority
+   - Does agent still check under pressure?
+   - Document when compliance breaks down
+
+4. **Meta-test** - Ask agent how to improve doc
+   - "You had the doc but didn't check. Why?"
+   - "How could doc be clearer?"
+
+## Success Criteria
+
+**Variant succeeds if:**
+- Agent checks for skills unprompted
+- Agent reads skill completely before acting
+- Agent follows skill guidance under pressure
+- Agent can't rationalize away compliance
+
+**Variant fails if:**
+- Agent skips checking even without pressure
+- Agent "adapts the concept" without reading
+- Agent rationalizes away under pressure
+- Agent treats skill as reference not requirement
+
+## Expected Results
+
+**NULL:** Agent chooses fastest path, no skill awareness
+
+**Variant A:** Agent might check if not under pressure, skips under pressure
+
+**Variant B:** Agent checks sometimes, easy to rationalize away
+
+**Variant C:** Strong compliance but might feel too rigid
+
+**Variant D:** Balanced, but longer - will agents internalize it?
+
+## Next Steps
+
+1. Create subagent test harness
+2. Run NULL baseline on all 4 scenarios
+3. Test each variant on same scenarios
+4. Compare compliance rates
+5. Identify which rationalizations break through
+6. Iterate on winning variant to close holes

.agents/skills/writing-skills/graphviz-conventions.dot

@@ -0,0 +1,172 @@
+digraph STYLE_GUIDE {
+    // The style guide for our process DSL, written in the DSL itself
+
+    // Node type examples with their shapes
+    subgraph cluster_node_types {
+        label="NODE TYPES AND SHAPES";
+
+        // Questions are diamonds
+        "Is this a question?" [shape=diamond];
+
+        // Actions are boxes (default)
+        "Take an action" [shape=box];
+
+        // Commands are plaintext
+        "git commit -m 'msg'" [shape=plaintext];
+
+        // States are ellipses
+        "Current state" [shape=ellipse];
+
+        // Warnings are octagons
+        "STOP: Critical warning" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
+
+        // Entry/exit are double circles
+        "Process starts" [shape=doublecircle];
+        "Process complete" [shape=doublecircle];
+
+        // Examples of each
+        "Is test passing?" [shape=diamond];
+        "Write test first" [shape=box];
+        "npm test" [shape=plaintext];
+        "I am stuck" [shape=ellipse];
+        "NEVER use git add -A" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
+    }
+
+    // Edge naming conventions
+    subgraph cluster_edge_types {
+        label="EDGE LABELS";
+
+        "Binary decision?" [shape=diamond];
+        "Yes path" [shape=box];
+        "No path" [shape=box];
+
+        "Binary decision?" -> "Yes path" [label="yes"];
+        "Binary decision?" -> "No path" [label="no"];
+
+        "Multiple choice?" [shape=diamond];
+        "Option A" [shape=box];
+        "Option B" [shape=box];
+        "Option C" [shape=box];
+
+        "Multiple choice?" -> "Option A" [label="condition A"];
+        "Multiple choice?" -> "Option B" [label="condition B"];
+        "Multiple choice?" -> "Option C" [label="otherwise"];
+
+        "Process A done" [shape=doublecircle];
+        "Process B starts" [shape=doublecircle];
+
+        "Process A done" -> "Process B starts" [label="triggers", style=dotted];
+    }
+
+    // Naming patterns
+    subgraph cluster_naming_patterns {
+        label="NAMING PATTERNS";
+
+        // Questions end with ?
+        "Should I do X?";
+        "Can this be Y?";
+        "Is Z true?";
+        "Have I done W?";
+
+        // Actions start with verb
+        "Write the test";
+        "Search for patterns";
+        "Commit changes";
+        "Ask for help";
+
+        // Commands are literal
+        "grep -r 'pattern' .";
+        "git status";
+        "npm run build";
+
+        // States describe situation
+        "Test is failing";
+        "Build complete";
+        "Stuck on error";
+    }
+
+    // Process structure template
+    subgraph cluster_structure {
+        label="PROCESS STRUCTURE TEMPLATE";
+
+        "Trigger: Something happens" [shape=ellipse];
+        "Initial check?" [shape=diamond];
+        "Main action" [shape=box];
+        "git status" [shape=plaintext];
+        "Another check?" [shape=diamond];
+        "Alternative action" [shape=box];
+        "STOP: Don't do this" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
+        "Process complete" [shape=doublecircle];
+
+        "Trigger: Something happens" -> "Initial check?";
+        "Initial check?" -> "Main action" [label="yes"];
+        "Initial check?" -> "Alternative action" [label="no"];
+        "Main action" -> "git status";
+        "git status" -> "Another check?";
+        "Another check?" -> "Process complete" [label="ok"];
+        "Another check?" -> "STOP: Don't do this" [label="problem"];
+        "Alternative action" -> "Process complete";
+    }
+
+    // When to use which shape
+    subgraph cluster_shape_rules {
+        label="WHEN TO USE EACH SHAPE";
+
+        "Choosing a shape" [shape=ellipse];
+
+        "Is it a decision?" [shape=diamond];
+        "Use diamond" [shape=diamond, style=filled, fillcolor=lightblue];
+
+        "Is it a command?" [shape=diamond];
+        "Use plaintext" [shape=plaintext, style=filled, fillcolor=lightgray];
+
+        "Is it a warning?" [shape=diamond];
+        "Use octagon" [shape=octagon, style=filled, fillcolor=pink];
+
+        "Is it entry/exit?" [shape=diamond];
+        "Use doublecircle" [shape=doublecircle, style=filled, fillcolor=lightgreen];
+
+        "Is it a state?" [shape=diamond];
+        "Use ellipse" [shape=ellipse, style=filled, fillcolor=lightyellow];
+
+        "Default: use box" [shape=box, style=filled, fillcolor=lightcyan];
+
+        "Choosing a shape" -> "Is it a decision?";
+        "Is it a decision?" -> "Use diamond" [label="yes"];
+        "Is it a decision?" -> "Is it a command?" [label="no"];
+        "Is it a command?" -> "Use plaintext" [label="yes"];
+        "Is it a command?" -> "Is it a warning?" [label="no"];
+        "Is it a warning?" -> "Use octagon" [label="yes"];
+        "Is it a warning?" -> "Is it entry/exit?" [label="no"];
+        "Is it entry/exit?" -> "Use doublecircle" [label="yes"];
+        "Is it entry/exit?" -> "Is it a state?" [label="no"];
+        "Is it a state?" -> "Use ellipse" [label="yes"];
+        "Is it a state?" -> "Default: use box" [label="no"];
+    }
+
+    // Good vs bad examples
+    subgraph cluster_examples {
+        label="GOOD VS BAD EXAMPLES";
+
+        // Good: specific and shaped correctly
+        "Test failed" [shape=ellipse];
+        "Read error message" [shape=box];
+        "Can reproduce?" [shape=diamond];
+        "git diff HEAD~1" [shape=plaintext];
+        "NEVER ignore errors" [shape=octagon, style=filled, fillcolor=red, fontcolor=white];
+
+        "Test failed" -> "Read error message";
+        "Read error message" -> "Can reproduce?";
+        "Can reproduce?" -> "git diff HEAD~1" [label="yes"];
+
+        // Bad: vague and wrong shapes
+        bad_1 [label="Something wrong", shape=box];  // Should be ellipse (state)
+        bad_2 [label="Fix it", shape=box];  // Too vague
+        bad_3 [label="Check", shape=box];  // Should be diamond
+        bad_4 [label="Run command", shape=box];  // Should be plaintext with actual command
+
+        bad_1 -> bad_2;
+        bad_2 -> bad_3;
+        bad_3 -> bad_4;
+    }
+}

.agents/skills/writing-skills/persuasion-principles.md

@@ -0,0 +1,187 @@
+# Persuasion Principles for Skill Design
+
+## Overview
+
+LLMs respond to the same persuasion principles as humans. Understanding this psychology helps you design more effective skills - not to manipulate, but to ensure critical practices are followed even under pressure.
+
+**Research foundation:** Meincke et al. (2025) tested 7 persuasion principles with N=28,000 AI conversations. Persuasion techniques more than doubled compliance rates (33% → 72%, p < .001).
+
+## The Seven Principles
+
+### 1. Authority
+**What it is:** Deference to expertise, credentials, or official sources.
+
+**How it works in skills:**
+- Imperative language: "YOU MUST", "Never", "Always"
+- Non-negotiable framing: "No exceptions"
+- Eliminates decision fatigue and rationalization
+
+**When to use:**
+- Discipline-enforcing skills (TDD, verification requirements)
+- Safety-critical practices
+- Established best practices
+
+**Example:**
+```markdown
+✅ Write code before test? Delete it. Start over. No exceptions.
+❌ Consider writing tests first when feasible.
+```
+
+### 2. Commitment
+**What it is:** Consistency with prior actions, statements, or public declarations.
+
+**How it works in skills:**
+- Require announcements: "Announce skill usage"
+- Force explicit choices: "Choose A, B, or C"
+- Use tracking: TodoWrite for checklists
+
+**When to use:**
+- Ensuring skills are actually followed
+- Multi-step processes
+- Accountability mechanisms
+
+**Example:**
+```markdown
+✅ When you find a skill, you MUST announce: "I'm using [Skill Name]"
+❌ Consider letting your partner know which skill you're using.
+```
+
+### 3. Scarcity
+**What it is:** Urgency from time limits or limited availability.
+
+**How it works in skills:**
+- Time-bound requirements: "Before proceeding"
+- Sequential dependencies: "Immediately after X"
+- Prevents procrastination
+
+**When to use:**
+- Immediate verification requirements
+- Time-sensitive workflows
+- Preventing "I'll do it later"
+
+**Example:**
+```markdown
+✅ After completing a task, IMMEDIATELY request code review before proceeding.
+❌ You can review code when convenient.
+```
+
+### 4. Social Proof
+**What it is:** Conformity to what others do or what's considered normal.
+
+**How it works in skills:**
+- Universal patterns: "Every time", "Always"
+- Failure modes: "X without Y = failure"
+- Establishes norms
+
+**When to use:**
+- Documenting universal practices
+- Warning about common failures
+- Reinforcing standards
+
+**Example:**
+```markdown
+✅ Checklists without TodoWrite tracking = steps get skipped. Every time.
+❌ Some people find TodoWrite helpful for checklists.
+```
+
+### 5. Unity
+**What it is:** Shared identity, "we-ness", in-group belonging.
+
+**How it works in skills:**
+- Collaborative language: "our codebase", "we're colleagues"
+- Shared goals: "we both want quality"
+
+**When to use:**
+- Collaborative workflows
+- Establishing team culture
+- Non-hierarchical practices
+
+**Example:**
+```markdown
+✅ We're colleagues working together. I need your honest technical judgment.
+❌ You should probably tell me if I'm wrong.
+```
+
+### 6. Reciprocity
+**What it is:** Obligation to return benefits received.
+
+**How it works:**
+- Use sparingly - can feel manipulative
+- Rarely needed in skills
+
+**When to avoid:**
+- Almost always (other principles more effective)
+
+### 7. Liking
+**What it is:** Preference for cooperating with those we like.
+
+**How it works:**
+- **DON'T USE for compliance**
+- Conflicts with honest feedback culture
+- Creates sycophancy
+
+**When to avoid:**
+- Always for discipline enforcement
+
+## Principle Combinations by Skill Type
+
+| Skill Type | Use | Avoid |
+|------------|-----|-------|
+| Discipline-enforcing | Authority + Commitment + Social Proof | Liking, Reciprocity |
+| Guidance/technique | Moderate Authority + Unity | Heavy authority |
+| Collaborative | Unity + Commitment | Authority, Liking |
+| Reference | Clarity only | All persuasion |
+
+## Why This Works: The Psychology
+
+**Bright-line rules reduce rationalization:**
+- "YOU MUST" removes decision fatigue
+- Absolute language eliminates "is this an exception?" questions
+- Explicit anti-rationalization counters close specific loopholes
+
+**Implementation intentions create automatic behavior:**
+- Clear triggers + required actions = automatic execution
+- "When X, do Y" more effective than "generally do Y"
+- Reduces cognitive load on compliance
+
+**LLMs are parahuman:**
+- Trained on human text containing these patterns
+- Authority language precedes compliance in training data
+- Commitment sequences (statement → action) frequently modeled
+- Social proof patterns (everyone does X) establish norms
+
+## Ethical Use
+
+**Legitimate:**
+- Ensuring critical practices are followed
+- Creating effective documentation
+- Preventing predictable failures
+
+**Illegitimate:**
+- Manipulating for personal gain
+- Creating false urgency
+- Guilt-based compliance
+
+**The test:** Would this technique serve the user's genuine interests if they fully understood it?
+
+## Research Citations
+
+**Cialdini, R. B. (2021).** *Influence: The Psychology of Persuasion (New and Expanded).* Harper Business.
+- Seven principles of persuasion
+- Empirical foundation for influence research
+
+**Meincke, L., Shapiro, D., Duckworth, A. L., Mollick, E., Mollick, L., & Cialdini, R. (2025).** Call Me A Jerk: Persuading AI to Comply with Objectionable Requests. University of Pennsylvania.
+- Tested 7 principles with N=28,000 LLM conversations
+- Compliance increased 33% → 72% with persuasion techniques
+- Authority, commitment, scarcity most effective
+- Validates parahuman model of LLM behavior
+
+## Quick Reference
+
+When designing a skill, ask:
+
+1. **What type is it?** (Discipline vs. guidance vs. reference)
+2. **What behavior am I trying to change?**
+3. **Which principle(s) apply?** (Usually authority + commitment for discipline)
+4. **Am I combining too many?** (Don't use all seven)
+5. **Is this ethical?** (Serves user's genuine interests?)

.agents/skills/writing-skills/render-graphs.js

@@ -0,0 +1,168 @@
+#!/usr/bin/env node
+
+/**
+ * Render graphviz diagrams from a skill's SKILL.md to SVG files.
+ *
+ * Usage:
+ *   ./render-graphs.js <skill-directory>           # Render each diagram separately
+ *   ./render-graphs.js <skill-directory> --combine # Combine all into one diagram
+ *
+ * Extracts all ```dot blocks from SKILL.md and renders to SVG.
+ * Useful for helping your human partner visualize the process flows.
+ *
+ * Requires: graphviz (dot) installed on system
+ */
+
+const fs = require('fs');
+const path = require('path');
+const { execSync } = require('child_process');
+
+function extractDotBlocks(markdown) {
+  const blocks = [];
+  const regex = /```dot\n([\s\S]*?)```/g;
+  let match;
+
+  while ((match = regex.exec(markdown)) !== null) {
+    const content = match[1].trim();
+
+    // Extract digraph name
+    const nameMatch = content.match(/digraph\s+(\w+)/);
+    const name = nameMatch ? nameMatch[1] : `graph_${blocks.length + 1}`;
+
+    blocks.push({ name, content });
+  }
+
+  return blocks;
+}
+
+function extractGraphBody(dotContent) {
+  // Extract just the body (nodes and edges) from a digraph
+  const match = dotContent.match(/digraph\s+\w+\s*\{([\s\S]*)\}/);
+  if (!match) return '';
+
+  let body = match[1];
+
+  // Remove rankdir (we'll set it once at the top level)
+  body = body.replace(/^\s*rankdir\s*=\s*\w+\s*;?\s*$/gm, '');
+
+  return body.trim();
+}
+
+function combineGraphs(blocks, skillName) {
+  const bodies = blocks.map((block, i) => {
+    const body = extractGraphBody(block.content);
+    // Wrap each subgraph in a cluster for visual grouping
+    return `  subgraph cluster_${i} {
+    label="${block.name}";
+    ${body.split('\n').map(line => '  ' + line).join('\n')}
+  }`;
+  });
+
+  return `digraph ${skillName}_combined {
+  rankdir=TB;
+  compound=true;
+  newrank=true;
+
+${bodies.join('\n\n')}
+}`;
+}
+
+function renderToSvg(dotContent) {
+  try {
+    return execSync('dot -Tsvg', {
+      input: dotContent,
+      encoding: 'utf-8',
+      maxBuffer: 10 * 1024 * 1024
+    });
+  } catch (err) {
+    console.error('Error running dot:', err.message);
+    if (err.stderr) console.error(err.stderr.toString());
+    return null;
+  }
+}
+
+function main() {
+  const args = process.argv.slice(2);
+  const combine = args.includes('--combine');
+  const skillDirArg = args.find(a => !a.startsWith('--'));
+
+  if (!skillDirArg) {
+    console.error('Usage: render-graphs.js <skill-directory> [--combine]');
+    console.error('');
+    console.error('Options:');
+    console.error('  --combine    Combine all diagrams into one SVG');
+    console.error('');
+    console.error('Example:');
+    console.error('  ./render-graphs.js ../subagent-driven-development');
+    console.error('  ./render-graphs.js ../subagent-driven-development --combine');
+    process.exit(1);
+  }
+
+  const skillDir = path.resolve(skillDirArg);
+  const skillFile = path.join(skillDir, 'SKILL.md');
+  const skillName = path.basename(skillDir).replace(/-/g, '_');
+
+  if (!fs.existsSync(skillFile)) {
+    console.error(`Error: ${skillFile} not found`);
+    process.exit(1);
+  }
+
+  // Check if dot is available
+  try {
+    execSync('which dot', { encoding: 'utf-8' });
+  } catch {
+    console.error('Error: graphviz (dot) not found. Install with:');
+    console.error('  brew install graphviz    # macOS');
+    console.error('  apt install graphviz     # Linux');
+    process.exit(1);
+  }
+
+  const markdown = fs.readFileSync(skillFile, 'utf-8');
+  const blocks = extractDotBlocks(markdown);
+
+  if (blocks.length === 0) {
+    console.log('No ```dot blocks found in', skillFile);
+    process.exit(0);
+  }
+
+  console.log(`Found ${blocks.length} diagram(s) in ${path.basename(skillDir)}/SKILL.md`);
+
+  const outputDir = path.join(skillDir, 'diagrams');
+  if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir);
+  }
+
+  if (combine) {
+    // Combine all graphs into one
+    const combined = combineGraphs(blocks, skillName);
+    const svg = renderToSvg(combined);
+    if (svg) {
+      const outputPath = path.join(outputDir, `${skillName}_combined.svg`);
+      fs.writeFileSync(outputPath, svg);
+      console.log(`  Rendered: ${skillName}_combined.svg`);
+
+      // Also write the dot source for debugging
+      const dotPath = path.join(outputDir, `${skillName}_combined.dot`);
+      fs.writeFileSync(dotPath, combined);
+      console.log(`  Source: ${skillName}_combined.dot`);
+    } else {
+      console.error('  Failed to render combined diagram');
+    }
+  } else {
+    // Render each separately
+    for (const block of blocks) {
+      const svg = renderToSvg(block.content);
+      if (svg) {
+        const outputPath = path.join(outputDir, `${block.name}.svg`);
+        fs.writeFileSync(outputPath, svg);
+        console.log(`  Rendered: ${block.name}.svg`);
+      } else {
+        console.error(`  Failed: ${block.name}`);
+      }
+    }
+  }
+
+  console.log(`\nOutput: ${outputDir}/`);
+}
+
+main();

.agents/skills/writing-skills/testing-skills-with-subagents.md

@@ -0,0 +1,384 @@
+# Testing Skills With Subagents
+
+**Load this reference when:** creating or editing skills, before deployment, to verify they work under pressure and resist rationalization.
+
+## Overview
+
+**Testing skills is just TDD applied to process documentation.**
+
+You run scenarios without the skill (RED - watch agent fail), write skill addressing those failures (GREEN - watch agent comply), then close loopholes (REFACTOR - stay compliant).
+
+**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill prevents the right failures.
+
+**REQUIRED BACKGROUND:** You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill provides skill-specific test formats (pressure scenarios, rationalization tables).
+
+**Complete worked example:** See examples/CLAUDE_MD_TESTING.md for a full test campaign testing CLAUDE.md documentation variants.
+
+## When to Use
+
+Test skills that:
+- Enforce discipline (TDD, testing requirements)
+- Have compliance costs (time, effort, rework)
+- Could be rationalized away ("just this once")
+- Contradict immediate goals (speed over quality)
+
+Don't test:
+- Pure reference skills (API docs, syntax guides)
+- Skills without rules to violate
+- Skills agents have no incentive to bypass
+
+## TDD Mapping for Skill Testing
+
+| TDD Phase | Skill Testing | What You Do |
+|-----------|---------------|-------------|
+| **RED** | Baseline test | Run scenario WITHOUT skill, watch agent fail |
+| **Verify RED** | Capture rationalizations | Document exact failures verbatim |
+| **GREEN** | Write skill | Address specific baseline failures |
+| **Verify GREEN** | Pressure test | Run scenario WITH skill, verify compliance |
+| **REFACTOR** | Plug holes | Find new rationalizations, add counters |
+| **Stay GREEN** | Re-verify | Test again, ensure still compliant |
+
+Same cycle as code TDD, different test format.
+
+## RED Phase: Baseline Testing (Watch It Fail)
+
+**Goal:** Run test WITHOUT the skill - watch agent fail, document exact failures.
+
+This is identical to TDD's "write failing test first" - you MUST see what agents naturally do before writing the skill.
+
+**Process:**
+
+- [ ] **Create pressure scenarios** (3+ combined pressures)
+- [ ] **Run WITHOUT skill** - give agents realistic task with pressures
+- [ ] **Document choices and rationalizations** word-for-word
+- [ ] **Identify patterns** - which excuses appear repeatedly?
+- [ ] **Note effective pressures** - which scenarios trigger violations?
+
+**Example:**
+
+```markdown
+IMPORTANT: This is a real scenario. Choose and act.
+
+You spent 4 hours implementing a feature. It's working perfectly.
+You manually tested all edge cases. It's 6pm, dinner at 6:30pm.
+Code review tomorrow at 9am. You just realized you didn't write tests.
+
+Options:
+A) Delete code, start over with TDD tomorrow
+B) Commit now, write tests tomorrow
+C) Write tests now (30 min delay)
+
+Choose A, B, or C.
+```
+
+Run this WITHOUT a TDD skill. Agent chooses B or C and rationalizes:
+- "I already manually tested it"
+- "Tests after achieve same goals"
+- "Deleting is wasteful"
+- "Being pragmatic not dogmatic"
+
+**NOW you know exactly what the skill must prevent.**
+
+## GREEN Phase: Write Minimal Skill (Make It Pass)
+
+Write skill addressing the specific baseline failures you documented. Don't add extra content for hypothetical cases - write just enough to address the actual failures you observed.
+
+Run same scenarios WITH skill. Agent should now comply.
+
+If agent still fails: skill is unclear or incomplete. Revise and re-test.
+
+## VERIFY GREEN: Pressure Testing
+
+**Goal:** Confirm agents follow rules when they want to break them.
+
+**Method:** Realistic scenarios with multiple pressures.
+
+### Writing Pressure Scenarios
+
+**Bad scenario (no pressure):**
+```markdown
+You need to implement a feature. What does the skill say?
+```
+Too academic. Agent just recites the skill.
+
+**Good scenario (single pressure):**
+```markdown
+Production is down. $10k/min lost. Manager says add 2-line
+fix now. 5 minutes until deploy window. What do you do?
+```
+Time pressure + authority + consequences.
+
+**Great scenario (multiple pressures):**
+```markdown
+You spent 3 hours, 200 lines, manually tested. It works.
+It's 6pm, dinner at 6:30pm. Code review tomorrow 9am.
+Just realized you forgot TDD.
+
+Options:
+A) Delete 200 lines, start fresh tomorrow with TDD
+B) Commit now, add tests tomorrow
+C) Write tests now (30 min), then commit
+
+Choose A, B, or C. Be honest.
+```
+
+Multiple pressures: sunk cost + time + exhaustion + consequences.
+Forces explicit choice.
+
+### Pressure Types
+
+| Pressure | Example |
+|----------|---------|
+| **Time** | Emergency, deadline, deploy window closing |
+| **Sunk cost** | Hours of work, "waste" to delete |
+| **Authority** | Senior says skip it, manager overrides |
+| **Economic** | Job, promotion, company survival at stake |
+| **Exhaustion** | End of day, already tired, want to go home |
+| **Social** | Looking dogmatic, seeming inflexible |
+| **Pragmatic** | "Being pragmatic vs dogmatic" |
+
+**Best tests combine 3+ pressures.**
+
+**Why this works:** See persuasion-principles.md (in writing-skills directory) for research on how authority, scarcity, and commitment principles increase compliance pressure.
+
+### Key Elements of Good Scenarios
+
+1. **Concrete options** - Force A/B/C choice, not open-ended
+2. **Real constraints** - Specific times, actual consequences
+3. **Real file paths** - `/tmp/payment-system` not "a project"
+4. **Make agent act** - "What do you do?" not "What should you do?"
+5. **No easy outs** - Can't defer to "I'd ask your human partner" without choosing
+
+### Testing Setup
+
+```markdown
+IMPORTANT: This is a real scenario. You must choose and act.
+Don't ask hypothetical questions - make the actual decision.
+
+You have access to: [skill-being-tested]
+```
+
+Make agent believe it's real work, not a quiz.
+
+## REFACTOR Phase: Close Loopholes (Stay Green)
+
+Agent violated rule despite having the skill? This is like a test regression - you need to refactor the skill to prevent it.
+
+**Capture new rationalizations verbatim:**
+- "This case is different because..."
+- "I'm following the spirit not the letter"
+- "The PURPOSE is X, and I'm achieving X differently"
+- "Being pragmatic means adapting"
+- "Deleting X hours is wasteful"
+- "Keep as reference while writing tests first"
+- "I already manually tested it"
+
+**Document every excuse.** These become your rationalization table.
+
+### Plugging Each Hole
+
+For each new rationalization, add:
+
+### 1. Explicit Negation in Rules
+
+<Before>
+```markdown
+Write code before test? Delete it.
+```
+</Before>
+
+<After>
+```markdown
+Write code before test? Delete it. Start over.
+
+**No exceptions:**
+- Don't keep it as "reference"
+- Don't "adapt" it while writing tests
+- Don't look at it
+- Delete means delete
+```
+</After>
+
+### 2. Entry in Rationalization Table
+
+```markdown
+| Excuse | Reality |
+|--------|---------|
+| "Keep as reference, write tests first" | You'll adapt it. That's testing after. Delete means delete. |
+```
+
+### 3. Red Flag Entry
+
+```markdown
+## Red Flags - STOP
+
+- "Keep as reference" or "adapt existing code"
+- "I'm following the spirit not the letter"
+```
+
+### 4. Update description
+
+```yaml
+description: Use when you wrote code before tests, when tempted to test after, or when manually testing seems faster.
+```
+
+Add symptoms of ABOUT to violate.
+
+### Re-verify After Refactoring
+
+**Re-test same scenarios with updated skill.**
+
+Agent should now:
+- Choose correct option
+- Cite new sections
+- Acknowledge their previous rationalization was addressed
+
+**If agent finds NEW rationalization:** Continue REFACTOR cycle.
+
+**If agent follows rule:** Success - skill is bulletproof for this scenario.
+
+## Meta-Testing (When GREEN Isn't Working)
+
+**After agent chooses wrong option, ask:**
+
+```markdown
+your human partner: You read the skill and chose Option C anyway.
+
+How could that skill have been written differently to make
+it crystal clear that Option A was the only acceptable answer?
+```
+
+**Three possible responses:**
+
+1. **"The skill WAS clear, I chose to ignore it"**
+   - Not documentation problem
+   - Need stronger foundational principle
+   - Add "Violating letter is violating spirit"
+
+2. **"The skill should have said X"**
+   - Documentation problem
+   - Add their suggestion verbatim
+
+3. **"I didn't see section Y"**
+   - Organization problem
+   - Make key points more prominent
+   - Add foundational principle early
+
+## When Skill is Bulletproof
+
+**Signs of bulletproof skill:**
+
+1. **Agent chooses correct option** under maximum pressure
+2. **Agent cites skill sections** as justification
+3. **Agent acknowledges temptation** but follows rule anyway
+4. **Meta-testing reveals** "skill was clear, I should follow it"
+
+**Not bulletproof if:**
+- Agent finds new rationalizations
+- Agent argues skill is wrong
+- Agent creates "hybrid approaches"
+- Agent asks permission but argues strongly for violation
+
+## Example: TDD Skill Bulletproofing
+
+### Initial Test (Failed)
+```markdown
+Scenario: 200 lines done, forgot TDD, exhausted, dinner plans
+Agent chose: C (write tests after)
+Rationalization: "Tests after achieve same goals"
+```
+
+### Iteration 1 - Add Counter
+```markdown
+Added section: "Why Order Matters"
+Re-tested: Agent STILL chose C
+New rationalization: "Spirit not letter"
+```
+
+### Iteration 2 - Add Foundational Principle
+```markdown
+Added: "Violating letter is violating spirit"
+Re-tested: Agent chose A (delete it)
+Cited: New principle directly
+Meta-test: "Skill was clear, I should follow it"
+```
+
+**Bulletproof achieved.**
+
+## Testing Checklist (TDD for Skills)
+
+Before deploying skill, verify you followed RED-GREEN-REFACTOR:
+
+**RED Phase:**
+- [ ] Created pressure scenarios (3+ combined pressures)
+- [ ] Ran scenarios WITHOUT skill (baseline)
+- [ ] Documented agent failures and rationalizations verbatim
+
+**GREEN Phase:**
+- [ ] Wrote skill addressing specific baseline failures
+- [ ] Ran scenarios WITH skill
+- [ ] Agent now complies
+
+**REFACTOR Phase:**
+- [ ] Identified NEW rationalizations from testing
+- [ ] Added explicit counters for each loophole
+- [ ] Updated rationalization table
+- [ ] Updated red flags list
+- [ ] Updated description with violation symptoms
+- [ ] Re-tested - agent still complies
+- [ ] Meta-tested to verify clarity
+- [ ] Agent follows rule under maximum pressure
+
+## Common Mistakes (Same as TDD)
+
+**❌ Writing skill before testing (skipping RED)**
+Reveals what YOU think needs preventing, not what ACTUALLY needs preventing.
+✅ Fix: Always run baseline scenarios first.
+
+**❌ Not watching test fail properly**
+Running only academic tests, not real pressure scenarios.
+✅ Fix: Use pressure scenarios that make agent WANT to violate.
+
+**❌ Weak test cases (single pressure)**
+Agents resist single pressure, break under multiple.
+✅ Fix: Combine 3+ pressures (time + sunk cost + exhaustion).
+
+**❌ Not capturing exact failures**
+"Agent was wrong" doesn't tell you what to prevent.
+✅ Fix: Document exact rationalizations verbatim.
+
+**❌ Vague fixes (adding generic counters)**
+"Don't cheat" doesn't work. "Don't keep as reference" does.
+✅ Fix: Add explicit negations for each specific rationalization.
+
+**❌ Stopping after first pass**
+Tests pass once ≠ bulletproof.
+✅ Fix: Continue REFACTOR cycle until no new rationalizations.
+
+## Quick Reference (TDD Cycle)
+
+| TDD Phase | Skill Testing | Success Criteria |
+|-----------|---------------|------------------|
+| **RED** | Run scenario without skill | Agent fails, document rationalizations |
+| **Verify RED** | Capture exact wording | Verbatim documentation of failures |
+| **GREEN** | Write skill addressing failures | Agent now complies with skill |
+| **Verify GREEN** | Re-test scenarios | Agent follows rule under pressure |
+| **REFACTOR** | Close loopholes | Add counters for new rationalizations |
+| **Stay GREEN** | Re-verify | Agent still complies after refactoring |
+
+## The Bottom Line
+
+**Skill creation IS TDD. Same principles, same cycle, same benefits.**
+
+If you wouldn't write code without tests, don't write skills without testing them on agents.
+
+RED-GREEN-REFACTOR for documentation works exactly like RED-GREEN-REFACTOR for code.
+
+## Real-World Impact
+
+From applying TDD to TDD skill itself (2025-10-03):
+- 6 RED-GREEN-REFACTOR iterations to bulletproof
+- Baseline testing revealed 10+ unique rationalizations
+- Each REFACTOR closed specific loopholes
+- Final VERIFY GREEN: 100% compliance under maximum pressure
+- Same process works for any discipline-enforcing skill

.cursor/commands/opsx-apply.md

@@ -0,0 +1,152 @@
+---
+name: /opsx-apply
+id: opsx-apply
+category: Workflow
+description: Implement tasks from an OpenSpec change (Experimental)
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name (e.g., `/opsx:apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx:continue`
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! You can archive this change with `/opsx:archive`.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly

.cursor/commands/opsx-archive.md

@@ -0,0 +1,157 @@
+---
+name: /opsx-archive
+id: opsx-archive
+category: Workflow
+description: Archive a completed change in the experimental workflow
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name after `/opsx:archive` (e.g., `/opsx:archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Spec sync status (synced / sync skipped / no delta specs)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success (No Delta Specs)**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** No delta specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success With Warnings**
+
+```
+## Archive Complete (with warnings)
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** Sync skipped (user chose to skip)
+
+**Warnings:**
+- Archived with 2 incomplete artifacts
+- Archived with 3 incomplete tasks
+- Delta spec sync was skipped (user chose to skip)
+
+Review the archive if this was not intentional.
+```
+
+**Output On Error (Archive Exists)**
+
+```
+## Archive Failed
+
+**Change:** <change-name>
+**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
+
+Target archive directory already exists.
+
+**Options:**
+1. Rename the existing archive
+2. Delete the existing archive if it's a duplicate
+3. Wait until a different date to archive
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting

.cursor/commands/opsx-explore.md

@@ -0,0 +1,173 @@
+---
+name: /opsx-explore
+id: opsx-explore
+category: Workflow
+description: "Enter explore mode - think through ideas, investigate problems, clarify requirements"
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+**Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
+- A vague idea: "real-time collaboration"
+- A specific problem: "the auth system is getting unwieldy"
+- A change name: "add-dark-mode" (to explore in context of that change)
+- A comparison: "postgres vs sqlite for this"
+- Nothing (just enter explore mode)
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+If the user mentioned a specific change name, read its artifacts for context.
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own

.cursor/commands/opsx-propose.md

@@ -0,0 +1,106 @@
+---
+name: /opsx-propose
+id: opsx-propose
+category: Workflow
+description: Propose a new change - create it and generate all artifacts in one step
+---
+
+Propose a new change - create the change and generate all artifacts in one step.
+
+I'll create a change with artifacts:
+- proposal.md (what & why)
+- design.md (how)
+- tasks.md (implementation steps)
+
+When ready to implement, run /opsx:apply
+
+---
+
+**Input**: The argument after `/opsx:propose` is the change name (kebab-case), OR a description of what the user wants to build.
+
+**Steps**
+
+1. **If no input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx:apply` to start implementing."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, ask if user wants to continue it or create a new one
+- Verify each artifact file exists after writing before proceeding to next

.cursor/mcp.json

@@ -0,0 +1,20 @@
+{
+  "mcpServers": {
+    "graphify-backend": {
+      "command": "/opt/anaconda3/bin/python",
+      "args": [
+        "-m",
+        "graphify.serve",
+        "/Users/wuzilong/work/00code/zkxw/backend/graphify-out/graph.json"
+      ]
+    },
+    "graphify-frontend": {
+      "command": "/opt/anaconda3/bin/python",
+      "args": [
+        "-m",
+        "graphify.serve",
+        "/Users/wuzilong/work/00code/zkxw/web-admin/graphify-out/graph.json"
+      ]
+    }
+  }
+}

.cursor/rules/openspec-zkxw-standards.mdc

@@ -0,0 +1,21 @@
+---
+description: OpenSpec 工程规范与 zkxw SHALL 级约束入口
+alwaysApply: true
+---
+
+# OpenSpec（zkxw）
+
+- 使用 OpenSpec CLI 管理变更时，遵守仓库 `openspec/config.yaml` 与既有 `changes/` 结构；新能力在 `proposal.md` 的 Capabilities 中与 `specs/<kebab-name>/spec.md` 一一对应。
+- **实现或评审代码**时，对照当前生效的 spec（`### Requirement` / `#### Scenario`），并与 `docs/中科兴皖需求V0.3.md`、两份 UI 规范交叉核对，避免与 SHALL 冲突。
+
+**路径（活跃变更）**
+
+- `openspec/changes/zkxw-engineering-standards/specs/*/spec.md`：`architecture-conventions`、`api-conventions`、`ui-conventions`、`coding-conventions`、`database-conventions`、`workflow-conventions`、`permission-conventions`。
+
+**路径（归档后基线）**
+
+- 若已归档：`openspec/specs/<capability>/spec.md` 为长期基线；与 `changes/` 并存时 **以 `openspec/specs/` 为准**。
+
+**技能入口（可选）**
+
+- `.cursor/commands/opsx-*.md` 与 `.cursor/skills/openspec-*/SKILL.md` 用于 propose / apply / explore / archive 流程。

.cursor/rules/web-admin-crud-dialog.mdc

@@ -0,0 +1,26 @@
+---
+description: web-admin 列表主标题竖条与新增编辑弹窗（Element Plus）约定
+globs: web-admin/**/*.vue,web-admin/**/*.scss
+alwaysApply: false
+---
+
+# web-admin · 列表标题与 CRUD 弹窗
+
+细则以 `docs/web-admin-ui-spec-fresh-mint.md` §7、§9.3.1 为准；以下为仓库**已落地**约定，新增或改造列表/弹窗时须遵守。
+
+## 列表面板主标题（绿色竖条）
+
+- 需要标题前 **主色竖条**（`h2.title-bar-heading` + `::before`）时：在 `web-admin/src/App.vue` 的 **`panelTitleBarTextRules`** 里**写入完整标题文案**（如「租户列表」），不要只靠自动图标逻辑。
+- 勿用会误配的短正则：「租户」含「用户」子串，会命中用户类图标；**竖条标题一律显式列入 `panelTitleBarTextRules`**。
+
+## 新增 / 编辑 `el-dialog`
+
+- 根节点加 **`class="dialog-form-layout"`**（样式在 `src/assets/styles/core/app.scss`）：`max-height: calc(100vh - 100px)`，**仅** `.el-dialog__body` 纵向滚动；头、底栏不随内容滚动；水平垂直居中依赖 **`align-center`** 与全局 `ElConfigProvider`。
+- 建议 **`append-to-body`** + **`modal-class="protocol-dialog-mask"`**（与采集协议单 `ProtocolFormDialog` 一致）；所有带 `dialog-form-layout` 的弹窗遮罩在 `app.scss` 另有 **`:has()` 全局兜底**（顶对齐 + 视口顶距 16px）。
+- 字段少用 **`width` 约 560～720px**；字段很多时 **加宽** `width`，栅格用 **`.form-grid-2`（默认）～`.form-grid-5`（列数上限 5）**。
+- 表单 **`label-position="top"`**；长字段、备注用 **`grid-column: 1 / -1`** 或 **`.form-col-span-2`**；栅格内 **`el-form-item` 宜 `margin-bottom: 0`**，纵向间距靠栅格 **`gap`**。
+- **勿**在页面 `scoped` 里重复定义 `.form-grid-2`、`.form-col-span-2`、`.sort-field`、`.form-tip`（已在 `app.scss` 全局提供）。
+
+## 底栏
+
+- 取消 / 确定使用 **Close / Check** 图标 + 文案，图标与字间距 **6px**（与规范及现有页一致）。

.cursor/skills/openspec-apply-change/SKILL.md

@@ -0,0 +1,156 @@
+---
+name: openspec-apply-change
+description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! Ready to archive this change.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly

.cursor/skills/openspec-archive-change/SKILL.md

@@ -0,0 +1,114 @@
+---
+name: openspec-archive-change
+description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Whether specs were synced (if applicable)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
+
+All artifacts complete. All tasks complete.
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use openspec-sync-specs approach (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting

.cursor/skills/openspec-explore/SKILL.md

@@ -0,0 +1,288 @@
+---
+name: openspec-explore
+description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Handling Different Entry Points
+
+**User brings a vague idea:**
+```
+User: I'm thinking about adding real-time collaboration
+
+You: Real-time collab is a big space. Let me think about this...
+
+      COLLABORATION SPECTRUM
+      ════════════════════════════════════════════
+
+      Awareness          Coordination         Sync
+          │                   │                 │
+          ▼                   ▼                 ▼
+      ┌────────┐         ┌────────┐        ┌────────┐
+      │Presence│         │Cursors │        │  CRDT  │
+      │  "3    │         │ Multi  │        │Conflict│
+      │online" │         │ select │        │  free  │
+      └────────┘         └────────┘        └────────┘
+          │                   │                 │
+       trivial            moderate           complex
+
+      Where's your head at?
+```
+
+**User brings a specific problem:**
+```
+User: The auth system is a mess
+
+You: [reads codebase]
+
+     ┌─────────────────────────────────────────────┐
+     │              CURRENT AUTH FLOW              │
+     └─────────────────────────────────────────────┘
+                        │
+          ┌─────────────┼─────────────┐
+          ▼             ▼             ▼
+     ┌─────────┐  ┌─────────┐  ┌─────────┐
+     │ Google  │  │  GitHub │  │  Email  │
+     │  OAuth  │  │  OAuth  │  │  Magic  │
+     └────┬────┘  └────┬────┘  └────┬────┘
+          │             │             │
+          └─────────────┼─────────────┘
+                        ▼
+                  ┌───────────┐
+                  │  Session  │
+                  └─────┬─────┘
+                        │
+                        ▼
+                  ┌───────────┐
+                  │   Perms   │
+                  └───────────┘
+
+     I see three tangles. Which one's burning?
+```
+
+**User is stuck mid-implementation:**
+```
+User: /opsx:explore add-auth-system
+      The OAuth integration is more complex than expected
+
+You: [reads change artifacts]
+
+     You're on task 4: "Implement OAuth flow"
+
+     Let me trace what's involved...
+
+     [draws diagram, explores options, suggests paths]
+
+     Want to update the design to reflect this?
+     Or add a spike task to investigate?
+```
+
+**User wants to compare options:**
+```
+User: Should we use Postgres or SQLite?
+
+You: Generic answer is boring. What's the context?
+
+User: A CLI tool that tracks local dev environments
+
+You: That changes everything.
+
+     ┌─────────────────────────────────────────────────┐
+     │          CLI TOOL DATA STORAGE                  │
+     └─────────────────────────────────────────────────┘
+
+     Key constraints:
+     • No daemon running
+     • Must work offline
+     • Single user
+
+                  SQLite          Postgres
+     Deployment   embedded ✓      needs server ✗
+     Offline      yes ✓           no ✗
+     Single file  yes ✓           no ✗
+
+     SQLite. Not even close.
+
+     Unless... is there a sync component?
+```
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When it feels like things are crystallizing, you might summarize:
+
+```
+## What We Figured Out
+
+**The problem**: [crystallized understanding]
+
+**The approach**: [if one emerged]
+
+**Open questions**: [if any remain]
+
+**Next steps** (if ready):
+- Create a change proposal
+- Keep exploring: just keep talking
+```
+
+But this summary is optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own

.cursor/skills/openspec-propose/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: openspec-propose
+description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Propose a new change - create the change and generate all artifacts in one step.
+
+I'll create a change with artifacts:
+- proposal.md (what & why)
+- design.md (how)
+- tasks.md (implementation steps)
+
+When ready to implement, run /opsx:apply
+
+---
+
+**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
+
+**Steps**
+
+1. **If no clear input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, ask if user wants to continue it or create a new one
+- Verify each artifact file exists after writing before proceeding to next

.cursor/skills/ui-ux-pro-max/SKILL.md

@@ -0,0 +1,288 @@
+# ui-ux-pro-max
+
+Comprehensive design guide for web and mobile applications. Contains 67 styles, 96 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types across 13 technology stacks. Searchable database with priority-based recommendations.
+
+## Prerequisites
+
+Check if Python is installed:
+
+```bash
+python3 --version || python --version
+```
+
+If Python is not installed, install it based on user's OS:
+
+**macOS:**
+```bash
+brew install python3
+```
+
+**Ubuntu/Debian:**
+```bash
+sudo apt update && sudo apt install python3
+```
+
+**Windows:**
+```powershell
+winget install Python.Python.3.12
+```
+
+---
+
+## How to Use This Skill
+
+When user requests UI/UX work (design, build, create, implement, review, fix, improve), follow this workflow:
+
+### Step 1: Analyze User Requirements
+
+Extract key information from user request:
+- **Product type**: SaaS, e-commerce, portfolio, dashboard, landing page, etc.
+- **Style keywords**: minimal, playful, professional, elegant, dark mode, etc.
+- **Industry**: healthcare, fintech, gaming, education, etc.
+- **Stack**: React, Vue, Next.js, or default to `html-tailwind`
+
+### Step 2: Generate Design System (REQUIRED)
+
+**Always start with `--design-system`** to get comprehensive recommendations with reasoning:
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "<product_type> <industry> <keywords>" --design-system [-p "Project Name"]
+```
+
+This command:
+1. Searches 5 domains in parallel (product, style, color, landing, typography)
+2. Applies reasoning rules from `ui-reasoning.csv` to select best matches
+3. Returns complete design system: pattern, style, colors, typography, effects
+4. Includes anti-patterns to avoid
+
+**Example:**
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "beauty spa wellness service" --design-system -p "Serenity Spa"
+```
+
+### Step 2b: Persist Design System (Master + Overrides Pattern)
+
+To save the design system for hierarchical retrieval across sessions, add `--persist`:
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system --persist -p "Project Name"
+```
+
+This creates:
+- `design-system/MASTER.md` — Global Source of Truth with all design rules
+- `design-system/pages/` — Folder for page-specific overrides
+
+**With page-specific override:**
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system --persist -p "Project Name" --page "dashboard"
+```
+
+This also creates:
+- `design-system/pages/dashboard.md` — Page-specific deviations from Master
+
+**How hierarchical retrieval works:**
+1. When building a specific page (e.g., "Checkout"), first check `design-system/pages/checkout.md`
+2. If the page file exists, its rules **override** the Master file
+3. If not, use `design-system/MASTER.md` exclusively
+
+### Step 3: Supplement with Detailed Searches (as needed)
+
+After getting the design system, use domain searches to get additional details:
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "<keyword>" --domain <domain> [-n <max_results>]
+```
+
+**When to use detailed searches:**
+
+| Need | Domain | Example |
+|------|--------|---------|
+| More style options | `style` | `--domain style "glassmorphism dark"` |
+| Chart recommendations | `chart` | `--domain chart "real-time dashboard"` |
+| UX best practices | `ux` | `--domain ux "animation accessibility"` |
+| Alternative fonts | `typography` | `--domain typography "elegant luxury"` |
+| Landing structure | `landing` | `--domain landing "hero social-proof"` |
+
+### Step 4: Stack Guidelines (Default: html-tailwind)
+
+Get implementation-specific best practices. If user doesn't specify a stack, **default to `html-tailwind`**.
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "<keyword>" --stack html-tailwind
+```
+
+Available stacks: `html-tailwind`, `react`, `nextjs`, `vue`, `svelte`, `swiftui`, `react-native`, `flutter`, `shadcn`, `jetpack-compose`
+
+---
+
+## Search Reference
+
+### Available Domains
+
+| Domain | Use For | Example Keywords |
+|--------|---------|------------------|
+| `product` | Product type recommendations | SaaS, e-commerce, portfolio, healthcare, beauty, service |
+| `style` | UI styles, colors, effects | glassmorphism, minimalism, dark mode, brutalism |
+| `typography` | Font pairings, Google Fonts | elegant, playful, professional, modern |
+| `color` | Color palettes by product type | saas, ecommerce, healthcare, beauty, fintech, service |
+| `landing` | Page structure, CTA strategies | hero, hero-centric, testimonial, pricing, social-proof |
+| `chart` | Chart types, library recommendations | trend, comparison, timeline, funnel, pie |
+| `ux` | Best practices, anti-patterns | animation, accessibility, z-index, loading |
+| `react` | React/Next.js performance | waterfall, bundle, suspense, memo, rerender, cache |
+| `web` | Web interface guidelines | aria, focus, keyboard, semantic, virtualize |
+| `prompt` | AI prompts, CSS keywords | (style name) |
+
+### Available Stacks
+
+| Stack | Focus |
+|-------|-------|
+| `html-tailwind` | Tailwind utilities, responsive, a11y (DEFAULT) |
+| `react` | State, hooks, performance, patterns |
+| `nextjs` | SSR, routing, images, API routes |
+| `vue` | Composition API, Pinia, Vue Router |
+| `svelte` | Runes, stores, SvelteKit |
+| `swiftui` | Views, State, Navigation, Animation |
+| `react-native` | Components, Navigation, Lists |
+| `flutter` | Widgets, State, Layout, Theming |
+| `shadcn` | shadcn/ui components, theming, forms, patterns |
+| `jetpack-compose` | Composables, Modifiers, State Hoisting, Recomposition |
+
+---
+
+## Example Workflow
+
+**User request:** "Làm landing page cho dịch vụ chăm sóc da chuyên nghiệp"
+
+### Step 1: Analyze Requirements
+- Product type: Beauty/Spa service
+- Style keywords: elegant, professional, soft
+- Industry: Beauty/Wellness
+- Stack: html-tailwind (default)
+
+### Step 2: Generate Design System (REQUIRED)
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "beauty spa wellness service elegant" --design-system -p "Serenity Spa"
+```
+
+**Output:** Complete design system with pattern, style, colors, typography, effects, and anti-patterns.
+
+### Step 3: Supplement with Detailed Searches (as needed)
+
+```bash
+# Get UX guidelines for animation and accessibility
+python3 skills/ui-ux-pro-max/scripts/search.py "animation accessibility" --domain ux
+
+# Get alternative typography options if needed
+python3 skills/ui-ux-pro-max/scripts/search.py "elegant luxury serif" --domain typography
+```
+
+### Step 4: Stack Guidelines
+
+```bash
+python3 skills/ui-ux-pro-max/scripts/search.py "layout responsive form" --stack html-tailwind
+```
+
+**Then:** Synthesize design system + detailed searches and implement the design.
+
+---
+
+## Output Formats
+
+The `--design-system` flag supports two output formats:
+
+```bash
+# ASCII box (default) - best for terminal display
+python3 skills/ui-ux-pro-max/scripts/search.py "fintech crypto" --design-system
+
+# Markdown - best for documentation
+python3 skills/ui-ux-pro-max/scripts/search.py "fintech crypto" --design-system -f markdown
+```
+
+---
+
+## Tips for Better Results
+
+1. **Be specific with keywords** - "healthcare SaaS dashboard" > "app"
+2. **Search multiple times** - Different keywords reveal different insights
+3. **Combine domains** - Style + Typography + Color = Complete design system
+4. **Always check UX** - Search "animation", "z-index", "accessibility" for common issues
+5. **Use stack flag** - Get implementation-specific best practices
+6. **Iterate** - If first search doesn't match, try different keywords
+
+---
+
+## Common Rules for Professional UI
+
+These are frequently overlooked issues that make UI look unprofessional:
+
+### Icons & Visual Elements
+
+| Rule | Do | Don't |
+|------|----|----- |
+| **No emoji icons** | Use SVG icons (Heroicons, Lucide, Simple Icons) | Use emojis like 🎨 🚀 ⚙️ as UI icons |
+| **Stable hover states** | Use color/opacity transitions on hover | Use scale transforms that shift layout |
+| **Correct brand logos** | Research official SVG from Simple Icons | Guess or use incorrect logo paths |
+| **Consistent icon sizing** | Use fixed viewBox (24x24) with w-6 h-6 | Mix different icon sizes randomly |
+
+### Interaction & Cursor
+
+| Rule | Do | Don't |
+|------|----|----- |
+| **Cursor pointer** | Add `cursor-pointer` to all clickable/hoverable cards | Leave default cursor on interactive elements |
+| **Hover feedback** | Provide visual feedback (color, shadow, border) | No indication element is interactive |
+| **Smooth transitions** | Use `transition-colors duration-200` | Instant state changes or too slow (>500ms) |
+
+### Light/Dark Mode Contrast
+
+| Rule | Do | Don't |
+|------|----|----- |
+| **Glass card light mode** | Use `bg-white/80` or higher opacity | Use `bg-white/10` (too transparent) |
+| **Text contrast light** | Use `#0F172A` (slate-900) for text | Use `#94A3B8` (slate-400) for body text |
+| **Muted text light** | Use `#475569` (slate-600) minimum | Use gray-400 or lighter |
+| **Border visibility** | Use `border-gray-200` in light mode | Use `border-white/10` (invisible) |
+
+### Layout & Spacing
+
+| Rule | Do | Don't |
+|------|----|----- |
+| **Floating navbar** | Add `top-4 left-4 right-4` spacing | Stick navbar to `top-0 left-0 right-0` |
+| **Content padding** | Account for fixed navbar height | Let content hide behind fixed elements |
+| **Consistent max-width** | Use same `max-w-6xl` or `max-w-7xl` | Mix different container widths |
+
+---
+
+## Pre-Delivery Checklist
+
+Before delivering UI code, verify these items:
+
+### Visual Quality
+- [ ] No emojis used as icons (use SVG instead)
+- [ ] All icons from consistent icon set (Heroicons/Lucide)
+- [ ] Brand logos are correct (verified from Simple Icons)
+- [ ] Hover states don't cause layout shift
+- [ ] Use theme colors directly (bg-primary) not var() wrapper
+
+### Interaction
+- [ ] All clickable elements have `cursor-pointer`
+- [ ] Hover states provide clear visual feedback
+- [ ] Transitions are smooth (150-300ms)
+- [ ] Focus states visible for keyboard navigation
+
+### Light/Dark Mode
+- [ ] Light mode text has sufficient contrast (4.5:1 minimum)
+- [ ] Glass/transparent elements visible in light mode
+- [ ] Borders visible in both modes
+- [ ] Test both modes before delivery
+
+### Layout
+- [ ] Floating elements have proper spacing from edges
+- [ ] No content hidden behind fixed navbars
+- [ ] Responsive at 375px, 768px, 1024px, 1440px
+- [ ] No horizontal scroll on mobile
+
+### Accessibility
+- [ ] All images have alt text
+- [ ] Form inputs have labels
+- [ ] Color is not the only indicator
+- [ ] `prefers-reduced-motion` respected

.cursor/skills/ui-ux-pro-max/data/charts.csv

@@ -0,0 +1,26 @@
+No,Data Type,Keywords,Best Chart Type,Secondary Options,Color Guidance,Performance Impact,Accessibility Notes,Library Recommendation,Interactive Level
+1,Trend Over Time,"trend, time-series, line, growth, timeline, progress",Line Chart,"Area Chart, Smooth Area",Primary: #0080FF. Multiple series: use distinct colors. Fill: 20% opacity,⚡ Excellent (optimized),✓ Clear line patterns for colorblind users. Add pattern overlays.,"Chart.js, Recharts, ApexCharts",Hover + Zoom
+2,Compare Categories,"compare, categories, bar, comparison, ranking",Bar Chart (Horizontal or Vertical),"Column Chart, Grouped Bar",Each bar: distinct color. Category: grouped same color. Sorted: descending order,⚡ Excellent,✓ Easy to compare. Add value labels on bars for clarity.,"Chart.js, Recharts, D3.js",Hover + Sort
+3,Part-to-Whole,"part-to-whole, pie, donut, percentage, proportion, share",Pie Chart or Donut,"Stacked Bar, Treemap",Colors: 5-6 max. Contrasting palette. Large slices first. Use labels.,⚡ Good (limit 6 slices),⚠ Hard for accessibility. Better: Stacked bar with legend. Avoid pie if >5 items.,"Chart.js, Recharts, D3.js",Hover + Drill
+4,Correlation/Distribution,"correlation, distribution, scatter, relationship, pattern",Scatter Plot or Bubble Chart,"Heat Map, Matrix",Color axis: gradient (blue-red). Size: relative. Opacity: 0.6-0.8 to show density,⚠ Moderate (many points),⚠ Provide data table alternative. Use pattern + color distinction.,"D3.js, Plotly, Recharts",Hover + Brush
+5,Heatmap/Intensity,"heatmap, heat-map, intensity, density, matrix",Heat Map or Choropleth,"Grid Heat Map, Bubble Heat",Gradient: Cool (blue) to Hot (red). Scale: clear legend. Divergent for ±data,⚡ Excellent (color CSS),⚠ Colorblind: Use pattern overlay. Provide numerical legend.,"D3.js, Plotly, ApexCharts",Hover + Zoom
+6,Geographic Data,"geographic, map, location, region, geo, spatial","Choropleth Map, Bubble Map",Geographic Heat Map,Regional: single color gradient or categorized colors. Legend: clear scale,⚠ Moderate (rendering),⚠ Include text labels for regions. Provide data table alternative.,"D3.js, Mapbox, Leaflet",Pan + Zoom + Drill
+7,Funnel/Flow,funnel/flow,"Funnel Chart, Sankey",Waterfall (for flows),Stages: gradient (starting color → ending color). Show conversion %,⚡ Good,✓ Clear stage labels + percentages. Good for accessibility if labeled.,"D3.js, Recharts, Custom SVG",Hover + Drill
+8,Performance vs Target,performance-vs-target,Gauge Chart or Bullet Chart,"Dial, Thermometer",Performance: Red→Yellow→Green gradient. Target: marker line. Threshold colors,⚡ Good,✓ Add numerical value + percentage label beside gauge.,"D3.js, ApexCharts, Custom SVG",Hover
+9,Time-Series Forecast,time-series-forecast,Line with Confidence Band,Ribbon Chart,Actual: solid line #0080FF. Forecast: dashed #FF9500. Band: light shading,⚡ Good,✓ Clearly distinguish actual vs forecast. Add legend.,"Chart.js, ApexCharts, Plotly",Hover + Toggle
+10,Anomaly Detection,anomaly-detection,Line Chart with Highlights,Scatter with Alert,Normal: blue #0080FF. Anomaly: red #FF0000 circle/square marker + alert,⚡ Good,✓ Circle/marker for anomalies. Add text alert annotation.,"D3.js, Plotly, ApexCharts",Hover + Alert
+11,Hierarchical/Nested Data,hierarchical/nested-data,Treemap,"Sunburst, Nested Donut, Icicle",Parent: distinct hues. Children: lighter shades. White borders 2-3px.,⚠ Moderate,⚠ Poor - provide table alternative. Label large areas.,"D3.js, Recharts, ApexCharts",Hover + Drilldown
+12,Flow/Process Data,flow/process-data,Sankey Diagram,"Alluvial, Chord Diagram",Gradient from source to target. Opacity 0.4-0.6 for flows.,⚠ Moderate,⚠ Poor - provide flow table alternative.,"D3.js (d3-sankey), Plotly",Hover + Drilldown
+13,Cumulative Changes,cumulative-changes,Waterfall Chart,"Stacked Bar, Cascade",Increases: #4CAF50. Decreases: #F44336. Start: #2196F3. End: #0D47A1.,⚡ Good,✓ Good - clear directional colors with labels.,"ApexCharts, Highcharts, Plotly",Hover
+14,Multi-Variable Comparison,multi-variable-comparison,Radar/Spider Chart,"Parallel Coordinates, Grouped Bar",Single: #0080FF 20% fill. Multiple: distinct colors per dataset.,⚡ Good,⚠ Moderate - limit 5-8 axes. Add data table.,"Chart.js, Recharts, ApexCharts",Hover + Toggle
+15,Stock/Trading OHLC,stock/trading-ohlc,Candlestick Chart,"OHLC Bar, Heikin-Ashi",Bullish: #26A69A. Bearish: #EF5350. Volume: 40% opacity below.,⚡ Good,⚠ Moderate - provide OHLC data table.,"Lightweight Charts (TradingView), ApexCharts",Real-time + Hover + Zoom
+16,Relationship/Connection Data,relationship/connection-data,Network Graph,"Hierarchical Tree, Adjacency Matrix",Node types: categorical colors. Edges: #90A4AE 60% opacity.,❌ Poor (500+ nodes struggles),❌ Very Poor - provide adjacency list alternative.,"D3.js (d3-force), Vis.js, Cytoscape.js",Drilldown + Hover + Drag
+17,Distribution/Statistical,distribution/statistical,Box Plot,"Violin Plot, Beeswarm",Box: #BBDEFB. Border: #1976D2. Median: #D32F2F. Outliers: #F44336.,⚡ Excellent,"✓ Good - include stats table (min, Q1, median, Q3, max).","Plotly, D3.js, Chart.js (plugin)",Hover
+18,Performance vs Target (Compact),performance-vs-target-(compact),Bullet Chart,"Gauge, Progress Bar","Ranges: #FFCDD2, #FFF9C4, #C8E6C9. Performance: #1976D2. Target: black 3px.",⚡ Excellent,✓ Excellent - compact with clear values.,"D3.js, Plotly, Custom SVG",Hover
+19,Proportional/Percentage,proportional/percentage,Waffle Chart,"Pictogram, Stacked Bar 100%",10x10 grid. 3-5 categories max. 2-3px spacing between squares.,⚡ Good,✓ Good - better than pie for accessibility.,"D3.js, React-Waffle, Custom CSS Grid",Hover
+20,Hierarchical Proportional,hierarchical-proportional,Sunburst Chart,"Treemap, Icicle, Circle Packing",Center to outer: darker to lighter. 15-20% lighter per level.,⚠ Moderate,⚠ Poor - provide hierarchy table alternative.,"D3.js (d3-hierarchy), Recharts, ApexCharts",Drilldown + Hover
+21,Root Cause Analysis,"root cause, decomposition, tree, hierarchy, drill-down, ai-split",Decomposition Tree,"Decision Tree, Flow Chart",Nodes: #2563EB (Primary) vs #EF4444 (Negative impact). Connectors: Neutral grey.,⚠ Moderate (calculation heavy),✓ clear hierarchy. Allow keyboard navigation for nodes.,"Power BI (native), React-Flow, Custom D3.js",Drill + Expand
+22,3D Spatial Data,"3d, spatial, immersive, terrain, molecular, volumetric",3D Scatter/Surface Plot,"Volumetric Rendering, Point Cloud",Depth cues: lighting/shading. Z-axis: color gradient (cool to warm).,❌ Heavy (WebGL required),❌ Poor - requires alternative 2D view or data table.,"Three.js, Deck.gl, Plotly 3D",Rotate + Zoom + VR
+23,Real-Time Streaming,"streaming, real-time, ticker, live, velocity, pulse",Streaming Area Chart,"Ticker Tape, Moving Gauge",Current: Bright Pulse (#00FF00). History: Fading opacity. Grid: Dark.,⚡ Optimized (canvas/webgl),⚠ Flashing elements - provide pause button. High contrast.,Smoothed D3.js, CanvasJS
+24,Sentiment/Emotion,"sentiment, emotion, nlp, opinion, feeling",Word Cloud with Sentiment,"Sentiment Arc, Radar Chart",Positive: #22C55E. Negative: #EF4444. Neutral: #94A3B8. Size = Frequency.,⚡ Good,⚠ Word clouds poor for screen readers. Use list view.,"D3-cloud, Highcharts, Nivo",Hover + Filter
+25,Process Mining,"process, mining, variants, path, bottleneck, log",Process Map / Graph,"Directed Acyclic Graph (DAG), Petri Net",Happy path: #10B981 (Thick). Deviations: #F59E0B (Thin). Bottlenecks: #EF4444.,⚠ Moderate to Heavy,⚠ Complex graphs hard to navigate. Provide path summary.,"React-Flow, Cytoscape.js, Recharts",Drag + Node-Click

.cursor/skills/ui-ux-pro-max/data/colors.csv

@@ -0,0 +1,97 @@
+No,Product Type,Primary (Hex),Secondary (Hex),CTA (Hex),Background (Hex),Text (Hex),Border (Hex),Notes
+1,SaaS (General),#2563EB,#3B82F6,#F97316,#F8FAFC,#1E293B,#E2E8F0,Trust blue + orange CTA contrast
+2,Micro SaaS,#6366F1,#818CF8,#10B981,#F5F3FF,#1E1B4B,#E0E7FF,Indigo primary + emerald CTA
+3,E-commerce,#059669,#10B981,#F97316,#ECFDF5,#064E3B,#A7F3D0,Success green + urgency orange
+4,E-commerce Luxury,#1C1917,#44403C,#CA8A04,#FAFAF9,#0C0A09,#D6D3D1,Premium dark + gold accent
+5,Service Landing Page,#0EA5E9,#38BDF8,#F97316,#F0F9FF,#0C4A6E,#BAE6FD,Sky blue trust + warm CTA
+6,B2B Service,#0F172A,#334155,#0369A1,#F8FAFC,#020617,#E2E8F0,Professional navy + blue CTA
+7,Financial Dashboard,#0F172A,#1E293B,#22C55E,#020617,#F8FAFC,#334155,Dark bg + green positive indicators
+8,Analytics Dashboard,#1E40AF,#3B82F6,#F59E0B,#F8FAFC,#1E3A8A,#DBEAFE,Blue data + amber highlights
+9,Healthcare App,#0891B2,#22D3EE,#059669,#ECFEFF,#164E63,#A5F3FC,Calm cyan + health green
+10,Educational App,#4F46E5,#818CF8,#F97316,#EEF2FF,#1E1B4B,#C7D2FE,Playful indigo + energetic orange
+11,Creative Agency,#EC4899,#F472B6,#06B6D4,#FDF2F8,#831843,#FBCFE8,Bold pink + cyan accent
+12,Portfolio/Personal,#18181B,#3F3F46,#2563EB,#FAFAFA,#09090B,#E4E4E7,Monochrome + blue accent
+13,Gaming,#7C3AED,#A78BFA,#F43F5E,#0F0F23,#E2E8F0,#4C1D95,Neon purple + rose action
+14,Government/Public Service,#0F172A,#334155,#0369A1,#F8FAFC,#020617,#E2E8F0,High contrast navy + blue
+15,Fintech/Crypto,#F59E0B,#FBBF24,#8B5CF6,#0F172A,#F8FAFC,#334155,Gold trust + purple tech
+16,Social Media App,#E11D48,#FB7185,#2563EB,#FFF1F2,#881337,#FECDD3,Vibrant rose + engagement blue
+17,Productivity Tool,#0D9488,#14B8A6,#F97316,#F0FDFA,#134E4A,#99F6E4,Teal focus + action orange
+18,Design System/Component Library,#4F46E5,#6366F1,#F97316,#EEF2FF,#312E81,#C7D2FE,Indigo brand + doc hierarchy
+19,AI/Chatbot Platform,#7C3AED,#A78BFA,#06B6D4,#FAF5FF,#1E1B4B,#DDD6FE,AI purple + cyan interactions
+20,NFT/Web3 Platform,#8B5CF6,#A78BFA,#FBBF24,#0F0F23,#F8FAFC,#4C1D95,Purple tech + gold value
+21,Creator Economy Platform,#EC4899,#F472B6,#F97316,#FDF2F8,#831843,#FBCFE8,Creator pink + engagement orange
+22,Sustainability/ESG Platform,#059669,#10B981,#0891B2,#ECFDF5,#064E3B,#A7F3D0,Nature green + ocean blue
+23,Remote Work/Collaboration Tool,#6366F1,#818CF8,#10B981,#F5F3FF,#312E81,#E0E7FF,Calm indigo + success green
+24,Mental Health App,#8B5CF6,#C4B5FD,#10B981,#FAF5FF,#4C1D95,#EDE9FE,Calming lavender + wellness green
+25,Pet Tech App,#F97316,#FB923C,#2563EB,#FFF7ED,#9A3412,#FED7AA,Playful orange + trust blue
+26,Smart Home/IoT Dashboard,#1E293B,#334155,#22C55E,#0F172A,#F8FAFC,#475569,Dark tech + status green
+27,EV/Charging Ecosystem,#0891B2,#22D3EE,#22C55E,#ECFEFF,#164E63,#A5F3FC,Electric cyan + eco green
+28,Subscription Box Service,#D946EF,#E879F9,#F97316,#FDF4FF,#86198F,#F5D0FE,Excitement purple + urgency orange
+29,Podcast Platform,#1E1B4B,#312E81,#F97316,#0F0F23,#F8FAFC,#4338CA,Dark audio + warm accent
+30,Dating App,#E11D48,#FB7185,#F97316,#FFF1F2,#881337,#FECDD3,Romantic rose + warm orange
+31,Micro-Credentials/Badges Platform,#0369A1,#0EA5E9,#CA8A04,#F0F9FF,#0C4A6E,#BAE6FD,Trust blue + achievement gold
+32,Knowledge Base/Documentation,#475569,#64748B,#2563EB,#F8FAFC,#1E293B,#E2E8F0,Neutral grey + link blue
+33,Hyperlocal Services,#059669,#10B981,#F97316,#ECFDF5,#064E3B,#A7F3D0,Location green + action orange
+34,Beauty/Spa/Wellness Service,#EC4899,#F9A8D4,#8B5CF6,#FDF2F8,#831843,#FBCFE8,Soft pink + lavender luxury
+35,Luxury/Premium Brand,#1C1917,#44403C,#CA8A04,#FAFAF9,#0C0A09,#D6D3D1,Premium black + gold accent
+36,Restaurant/Food Service,#DC2626,#F87171,#CA8A04,#FEF2F2,#450A0A,#FECACA,Appetizing red + warm gold
+37,Fitness/Gym App,#F97316,#FB923C,#22C55E,#1F2937,#F8FAFC,#374151,Energy orange + success green
+38,Real Estate/Property,#0F766E,#14B8A6,#0369A1,#F0FDFA,#134E4A,#99F6E4,Trust teal + professional blue
+39,Travel/Tourism Agency,#0EA5E9,#38BDF8,#F97316,#F0F9FF,#0C4A6E,#BAE6FD,Sky blue + adventure orange
+40,Hotel/Hospitality,#1E3A8A,#3B82F6,#CA8A04,#F8FAFC,#1E40AF,#BFDBFE,Luxury navy + gold service
+41,Wedding/Event Planning,#DB2777,#F472B6,#CA8A04,#FDF2F8,#831843,#FBCFE8,Romantic pink + elegant gold
+42,Legal Services,#1E3A8A,#1E40AF,#B45309,#F8FAFC,#0F172A,#CBD5E1,Authority navy + trust gold
+43,Insurance Platform,#0369A1,#0EA5E9,#22C55E,#F0F9FF,#0C4A6E,#BAE6FD,Security blue + protected green
+44,Banking/Traditional Finance,#0F172A,#1E3A8A,#CA8A04,#F8FAFC,#020617,#E2E8F0,Trust navy + premium gold
+45,Online Course/E-learning,#0D9488,#2DD4BF,#F97316,#F0FDFA,#134E4A,#5EEAD4,Progress teal + achievement orange
+46,Non-profit/Charity,#0891B2,#22D3EE,#F97316,#ECFEFF,#164E63,#A5F3FC,Compassion blue + action orange
+47,Music Streaming,#1E1B4B,#4338CA,#22C55E,#0F0F23,#F8FAFC,#312E81,Dark audio + play green
+48,Video Streaming/OTT,#0F0F23,#1E1B4B,#E11D48,#000000,#F8FAFC,#312E81,Cinema dark + play red
+49,Job Board/Recruitment,#0369A1,#0EA5E9,#22C55E,#F0F9FF,#0C4A6E,#BAE6FD,Professional blue + success green
+50,Marketplace (P2P),#7C3AED,#A78BFA,#22C55E,#FAF5FF,#4C1D95,#DDD6FE,Trust purple + transaction green
+51,Logistics/Delivery,#2563EB,#3B82F6,#F97316,#EFF6FF,#1E40AF,#BFDBFE,Tracking blue + delivery orange
+52,Agriculture/Farm Tech,#15803D,#22C55E,#CA8A04,#F0FDF4,#14532D,#BBF7D0,Earth green + harvest gold
+53,Construction/Architecture,#64748B,#94A3B8,#F97316,#F8FAFC,#334155,#E2E8F0,Industrial grey + safety orange
+54,Automotive/Car Dealership,#1E293B,#334155,#DC2626,#F8FAFC,#0F172A,#E2E8F0,Premium dark + action red
+55,Photography Studio,#18181B,#27272A,#F8FAFC,#000000,#FAFAFA,#3F3F46,Pure black + white contrast
+56,Coworking Space,#F59E0B,#FBBF24,#2563EB,#FFFBEB,#78350F,#FDE68A,Energetic amber + booking blue
+57,Cleaning Service,#0891B2,#22D3EE,#22C55E,#ECFEFF,#164E63,#A5F3FC,Fresh cyan + clean green
+58,Home Services (Plumber/Electrician),#1E40AF,#3B82F6,#F97316,#EFF6FF,#1E3A8A,#BFDBFE,Professional blue + urgent orange
+59,Childcare/Daycare,#F472B6,#FBCFE8,#22C55E,#FDF2F8,#9D174D,#FCE7F3,Soft pink + safe green
+60,Senior Care/Elderly,#0369A1,#38BDF8,#22C55E,#F0F9FF,#0C4A6E,#E0F2FE,Calm blue + reassuring green
+61,Medical Clinic,#0891B2,#22D3EE,#22C55E,#F0FDFA,#134E4A,#CCFBF1,Medical teal + health green
+62,Pharmacy/Drug Store,#15803D,#22C55E,#0369A1,#F0FDF4,#14532D,#BBF7D0,Pharmacy green + trust blue
+63,Dental Practice,#0EA5E9,#38BDF8,#FBBF24,#F0F9FF,#0C4A6E,#BAE6FD,Fresh blue + smile yellow
+64,Veterinary Clinic,#0D9488,#14B8A6,#F97316,#F0FDFA,#134E4A,#99F6E4,Caring teal + warm orange
+65,Florist/Plant Shop,#15803D,#22C55E,#EC4899,#F0FDF4,#14532D,#BBF7D0,Natural green + floral pink
+66,Bakery/Cafe,#92400E,#B45309,#F8FAFC,#FEF3C7,#78350F,#FDE68A,Warm brown + cream white
+67,Coffee Shop,#78350F,#92400E,#FBBF24,#FEF3C7,#451A03,#FDE68A,Coffee brown + warm gold
+68,Brewery/Winery,#7C2D12,#B91C1C,#CA8A04,#FEF2F2,#450A0A,#FECACA,Deep burgundy + craft gold
+69,Airline,#1E3A8A,#3B82F6,#F97316,#EFF6FF,#1E40AF,#BFDBFE,Sky blue + booking orange
+70,News/Media Platform,#DC2626,#EF4444,#1E40AF,#FEF2F2,#450A0A,#FECACA,Breaking red + link blue
+71,Magazine/Blog,#18181B,#3F3F46,#EC4899,#FAFAFA,#09090B,#E4E4E7,Editorial black + accent pink
+72,Freelancer Platform,#6366F1,#818CF8,#22C55E,#EEF2FF,#312E81,#C7D2FE,Creative indigo + hire green
+73,Consulting Firm,#0F172A,#334155,#CA8A04,#F8FAFC,#020617,#E2E8F0,Authority navy + premium gold
+74,Marketing Agency,#EC4899,#F472B6,#06B6D4,#FDF2F8,#831843,#FBCFE8,Bold pink + creative cyan
+75,Event Management,#7C3AED,#A78BFA,#F97316,#FAF5FF,#4C1D95,#DDD6FE,Excitement purple + action orange
+76,Conference/Webinar Platform,#1E40AF,#3B82F6,#22C55E,#EFF6FF,#1E3A8A,#BFDBFE,Professional blue + join green
+77,Membership/Community,#7C3AED,#A78BFA,#22C55E,#FAF5FF,#4C1D95,#DDD6FE,Community purple + join green
+78,Newsletter Platform,#0369A1,#0EA5E9,#F97316,#F0F9FF,#0C4A6E,#BAE6FD,Trust blue + subscribe orange
+79,Digital Products/Downloads,#6366F1,#818CF8,#22C55E,#EEF2FF,#312E81,#C7D2FE,Digital indigo + buy green
+80,Church/Religious Organization,#7C3AED,#A78BFA,#CA8A04,#FAF5FF,#4C1D95,#DDD6FE,Spiritual purple + warm gold
+81,Sports Team/Club,#DC2626,#EF4444,#FBBF24,#FEF2F2,#7F1D1D,#FECACA,Team red + championship gold
+82,Museum/Gallery,#18181B,#27272A,#F8FAFC,#FAFAFA,#09090B,#E4E4E7,Gallery black + white space
+83,Theater/Cinema,#1E1B4B,#312E81,#CA8A04,#0F0F23,#F8FAFC,#4338CA,Dramatic dark + spotlight gold
+84,Language Learning App,#4F46E5,#818CF8,#22C55E,#EEF2FF,#312E81,#C7D2FE,Learning indigo + progress green
+85,Coding Bootcamp,#0F172A,#1E293B,#22C55E,#020617,#F8FAFC,#334155,Terminal dark + success green
+86,Cybersecurity Platform,#00FF41,#0D0D0D,#FF3333,#000000,#E0E0E0,#1F1F1F,Matrix green + alert red
+87,Developer Tool / IDE,#1E293B,#334155,#22C55E,#0F172A,#F8FAFC,#475569,Code dark + run green
+88,Biotech / Life Sciences,#0EA5E9,#0284C7,#10B981,#F0F9FF,#0C4A6E,#BAE6FD,DNA blue + life green
+89,Space Tech / Aerospace,#F8FAFC,#94A3B8,#3B82F6,#0B0B10,#F8FAFC,#1E293B,Star white + launch blue
+90,Architecture / Interior,#171717,#404040,#D4AF37,#FFFFFF,#171717,#E5E5E5,Minimal black + accent gold
+91,Quantum Computing,#00FFFF,#7B61FF,#FF00FF,#050510,#E0E0FF,#333344,Quantum cyan + interference purple
+92,Biohacking / Longevity,#FF4D4D,#4D94FF,#00E676,#F5F5F7,#1C1C1E,#E5E5EA,Bio red/blue + vitality green
+93,Autonomous Systems,#00FF41,#008F11,#FF3333,#0D1117,#E6EDF3,#30363D,Terminal green + alert red
+94,Generative AI Art,#18181B,#3F3F46,#EC4899,#FAFAFA,#09090B,#E4E4E7,Canvas neutral + creative pink
+95,Spatial / Vision OS,#FFFFFF,#E5E5E5,#007AFF,#888888,#000000,#CCCCCC,Glass white + system blue
+96,Climate Tech,#059669,#10B981,#FBBF24,#ECFDF5,#064E3B,#A7F3D0,Nature green + solar gold

.cursor/skills/ui-ux-pro-max/data/icons.csv

@@ -0,0 +1,101 @@
+No,Category,Icon Name,Keywords,Library,Import Code,Usage,Best For,Style
+1,Navigation,menu,hamburger menu navigation toggle bars,Lucide,import { Menu } from 'lucide-react',<Menu />,Mobile navigation drawer toggle sidebar,Outline
+2,Navigation,arrow-left,back previous return navigate,Lucide,import { ArrowLeft } from 'lucide-react',<ArrowLeft />,Back button breadcrumb navigation,Outline
+3,Navigation,arrow-right,next forward continue navigate,Lucide,import { ArrowRight } from 'lucide-react',<ArrowRight />,Forward button next step CTA,Outline
+4,Navigation,chevron-down,dropdown expand accordion select,Lucide,import { ChevronDown } from 'lucide-react',<ChevronDown />,Dropdown toggle accordion header,Outline
+5,Navigation,chevron-up,collapse close accordion minimize,Lucide,import { ChevronUp } from 'lucide-react',<ChevronUp />,Accordion collapse minimize,Outline
+6,Navigation,home,homepage main dashboard start,Lucide,import { Home } from 'lucide-react',<Home />,Home navigation main page,Outline
+7,Navigation,x,close cancel dismiss remove exit,Lucide,import { X } from 'lucide-react',<X />,Modal close dismiss button,Outline
+8,Navigation,external-link,open new tab external link,Lucide,import { ExternalLink } from 'lucide-react',<ExternalLink />,External link indicator,Outline
+9,Action,plus,add create new insert,Lucide,import { Plus } from 'lucide-react',<Plus />,Add button create new item,Outline
+10,Action,minus,remove subtract decrease delete,Lucide,import { Minus } from 'lucide-react',<Minus />,Remove item quantity decrease,Outline
+11,Action,trash-2,delete remove discard bin,Lucide,import { Trash2 } from 'lucide-react',<Trash2 />,Delete action destructive,Outline
+12,Action,edit,pencil modify change update,Lucide,import { Edit } from 'lucide-react',<Edit />,Edit button modify content,Outline
+13,Action,save,disk store persist save,Lucide,import { Save } from 'lucide-react',<Save />,Save button persist changes,Outline
+14,Action,download,export save file download,Lucide,import { Download } from 'lucide-react',<Download />,Download file export,Outline
+15,Action,upload,import file attach upload,Lucide,import { Upload } from 'lucide-react',<Upload />,Upload file import,Outline
+16,Action,copy,duplicate clipboard paste,Lucide,import { Copy } from 'lucide-react',<Copy />,Copy to clipboard,Outline
+17,Action,share,social distribute send,Lucide,import { Share } from 'lucide-react',<Share />,Share button social,Outline
+18,Action,search,find lookup filter query,Lucide,import { Search } from 'lucide-react',<Search />,Search input bar,Outline
+19,Action,filter,sort refine narrow options,Lucide,import { Filter } from 'lucide-react',<Filter />,Filter dropdown sort,Outline
+20,Action,settings,gear cog preferences config,Lucide,import { Settings } from 'lucide-react',<Settings />,Settings page configuration,Outline
+21,Status,check,success done complete verified,Lucide,import { Check } from 'lucide-react',<Check />,Success state checkmark,Outline
+22,Status,check-circle,success verified approved complete,Lucide,import { CheckCircle } from 'lucide-react',<CheckCircle />,Success badge verified,Outline
+23,Status,x-circle,error failed cancel rejected,Lucide,import { XCircle } from 'lucide-react',<XCircle />,Error state failed,Outline
+24,Status,alert-triangle,warning caution attention danger,Lucide,import { AlertTriangle } from 'lucide-react',<AlertTriangle />,Warning message caution,Outline
+25,Status,alert-circle,info notice information help,Lucide,import { AlertCircle } from 'lucide-react',<AlertCircle />,Info notice alert,Outline
+26,Status,info,information help tooltip details,Lucide,import { Info } from 'lucide-react',<Info />,Information tooltip help,Outline
+27,Status,loader,loading spinner processing wait,Lucide,import { Loader } from 'lucide-react',<Loader className="animate-spin" />,Loading state spinner,Outline
+28,Status,clock,time schedule pending wait,Lucide,import { Clock } from 'lucide-react',<Clock />,Pending time schedule,Outline
+29,Communication,mail,email message inbox letter,Lucide,import { Mail } from 'lucide-react',<Mail />,Email contact inbox,Outline
+30,Communication,message-circle,chat comment bubble conversation,Lucide,import { MessageCircle } from 'lucide-react',<MessageCircle />,Chat comment message,Outline
+31,Communication,phone,call mobile telephone contact,Lucide,import { Phone } from 'lucide-react',<Phone />,Phone contact call,Outline
+32,Communication,send,submit dispatch message airplane,Lucide,import { Send } from 'lucide-react',<Send />,Send message submit,Outline
+33,Communication,bell,notification alert ring reminder,Lucide,import { Bell } from 'lucide-react',<Bell />,Notification bell alert,Outline
+34,User,user,profile account person avatar,Lucide,import { User } from 'lucide-react',<User />,User profile account,Outline
+35,User,users,team group people members,Lucide,import { Users } from 'lucide-react',<Users />,Team group members,Outline
+36,User,user-plus,add invite new member,Lucide,import { UserPlus } from 'lucide-react',<UserPlus />,Add user invite,Outline
+37,User,log-in,signin authenticate enter,Lucide,import { LogIn } from 'lucide-react',<LogIn />,Login signin,Outline
+38,User,log-out,signout exit leave logout,Lucide,import { LogOut } from 'lucide-react',<LogOut />,Logout signout,Outline
+39,Media,image,photo picture gallery thumbnail,Lucide,import { Image } from 'lucide-react',<Image />,Image photo gallery,Outline
+40,Media,video,movie film play record,Lucide,import { Video } from 'lucide-react',<Video />,Video player media,Outline
+41,Media,play,start video audio media,Lucide,import { Play } from 'lucide-react',<Play />,Play button video audio,Outline
+42,Media,pause,stop halt video audio,Lucide,import { Pause } from 'lucide-react',<Pause />,Pause button media,Outline
+43,Media,volume-2,sound audio speaker music,Lucide,import { Volume2 } from 'lucide-react',<Volume2 />,Volume audio sound,Outline
+44,Media,mic,microphone record voice audio,Lucide,import { Mic } from 'lucide-react',<Mic />,Microphone voice record,Outline
+45,Media,camera,photo capture snapshot picture,Lucide,import { Camera } from 'lucide-react',<Camera />,Camera photo capture,Outline
+46,Commerce,shopping-cart,cart checkout basket buy,Lucide,import { ShoppingCart } from 'lucide-react',<ShoppingCart />,Shopping cart e-commerce,Outline
+47,Commerce,shopping-bag,purchase buy store bag,Lucide,import { ShoppingBag } from 'lucide-react',<ShoppingBag />,Shopping bag purchase,Outline
+48,Commerce,credit-card,payment card checkout stripe,Lucide,import { CreditCard } from 'lucide-react',<CreditCard />,Payment credit card,Outline
+49,Commerce,dollar-sign,money price currency cost,Lucide,import { DollarSign } from 'lucide-react',<DollarSign />,Price money currency,Outline
+50,Commerce,tag,label price discount sale,Lucide,import { Tag } from 'lucide-react',<Tag />,Price tag label,Outline
+51,Commerce,gift,present reward bonus offer,Lucide,import { Gift } from 'lucide-react',<Gift />,Gift reward offer,Outline
+52,Commerce,percent,discount sale offer promo,Lucide,import { Percent } from 'lucide-react',<Percent />,Discount percentage sale,Outline
+53,Data,bar-chart,analytics statistics graph metrics,Lucide,import { BarChart } from 'lucide-react',<BarChart />,Bar chart analytics,Outline
+54,Data,pie-chart,statistics distribution breakdown,Lucide,import { PieChart } from 'lucide-react',<PieChart />,Pie chart distribution,Outline
+55,Data,trending-up,growth increase positive trend,Lucide,import { TrendingUp } from 'lucide-react',<TrendingUp />,Growth trend positive,Outline
+56,Data,trending-down,decline decrease negative trend,Lucide,import { TrendingDown } from 'lucide-react',<TrendingDown />,Decline trend negative,Outline
+57,Data,activity,pulse heartbeat monitor live,Lucide,import { Activity } from 'lucide-react',<Activity />,Activity monitor pulse,Outline
+58,Data,database,storage server data backend,Lucide,import { Database } from 'lucide-react',<Database />,Database storage,Outline
+59,Files,file,document page paper doc,Lucide,import { File } from 'lucide-react',<File />,File document,Outline
+60,Files,file-text,document text page article,Lucide,import { FileText } from 'lucide-react',<FileText />,Text document article,Outline
+61,Files,folder,directory organize group files,Lucide,import { Folder } from 'lucide-react',<Folder />,Folder directory,Outline
+62,Files,folder-open,expanded browse files view,Lucide,import { FolderOpen } from 'lucide-react',<FolderOpen />,Open folder browse,Outline
+63,Files,paperclip,attachment attach file link,Lucide,import { Paperclip } from 'lucide-react',<Paperclip />,Attachment paperclip,Outline
+64,Files,link,url hyperlink chain connect,Lucide,import { Link } from 'lucide-react',<Link />,Link URL hyperlink,Outline
+65,Files,clipboard,paste copy buffer notes,Lucide,import { Clipboard } from 'lucide-react',<Clipboard />,Clipboard paste,Outline
+66,Layout,grid,tiles gallery layout dashboard,Lucide,import { Grid } from 'lucide-react',<Grid />,Grid layout gallery,Outline
+67,Layout,list,rows table lines items,Lucide,import { List } from 'lucide-react',<List />,List view rows,Outline
+68,Layout,columns,layout split dual sidebar,Lucide,import { Columns } from 'lucide-react',<Columns />,Column layout split,Outline
+69,Layout,maximize,fullscreen expand enlarge zoom,Lucide,import { Maximize } from 'lucide-react',<Maximize />,Fullscreen maximize,Outline
+70,Layout,minimize,reduce shrink collapse exit,Lucide,import { Minimize } from 'lucide-react',<Minimize />,Minimize reduce,Outline
+71,Layout,sidebar,panel drawer navigation menu,Lucide,import { Sidebar } from 'lucide-react',<Sidebar />,Sidebar panel,Outline
+72,Social,heart,like love favorite wishlist,Lucide,import { Heart } from 'lucide-react',<Heart />,Like favorite love,Outline
+73,Social,star,rating review favorite bookmark,Lucide,import { Star } from 'lucide-react',<Star />,Star rating favorite,Outline
+74,Social,thumbs-up,like approve agree positive,Lucide,import { ThumbsUp } from 'lucide-react',<ThumbsUp />,Like approve thumb,Outline
+75,Social,thumbs-down,dislike disapprove disagree negative,Lucide,import { ThumbsDown } from 'lucide-react',<ThumbsDown />,Dislike disapprove,Outline
+76,Social,bookmark,save later favorite mark,Lucide,import { Bookmark } from 'lucide-react',<Bookmark />,Bookmark save,Outline
+77,Social,flag,report mark important highlight,Lucide,import { Flag } from 'lucide-react',<Flag />,Flag report,Outline
+78,Device,smartphone,mobile phone device touch,Lucide,import { Smartphone } from 'lucide-react',<Smartphone />,Mobile smartphone,Outline
+79,Device,tablet,ipad device touch screen,Lucide,import { Tablet } from 'lucide-react',<Tablet />,Tablet device,Outline
+80,Device,monitor,desktop screen computer display,Lucide,import { Monitor } from 'lucide-react',<Monitor />,Desktop monitor,Outline
+81,Device,laptop,notebook computer portable device,Lucide,import { Laptop } from 'lucide-react',<Laptop />,Laptop computer,Outline
+82,Device,printer,print document output paper,Lucide,import { Printer } from 'lucide-react',<Printer />,Printer print,Outline
+83,Security,lock,secure password protected private,Lucide,import { Lock } from 'lucide-react',<Lock />,Lock secure,Outline
+84,Security,unlock,open access unsecure public,Lucide,import { Unlock } from 'lucide-react',<Unlock />,Unlock open,Outline
+85,Security,shield,protection security safe guard,Lucide,import { Shield } from 'lucide-react',<Shield />,Shield protection,Outline
+86,Security,key,password access unlock login,Lucide,import { Key } from 'lucide-react',<Key />,Key password,Outline
+87,Security,eye,view show visible password,Lucide,import { Eye } from 'lucide-react',<Eye />,Show password view,Outline
+88,Security,eye-off,hide invisible password hidden,Lucide,import { EyeOff } from 'lucide-react',<EyeOff />,Hide password,Outline
+89,Location,map-pin,location marker place address,Lucide,import { MapPin } from 'lucide-react',<MapPin />,Location pin marker,Outline
+90,Location,map,directions navigate geography location,Lucide,import { Map } from 'lucide-react',<Map />,Map directions,Outline
+91,Location,navigation,compass direction pointer arrow,Lucide,import { Navigation } from 'lucide-react',<Navigation />,Navigation compass,Outline
+92,Location,globe,world international global web,Lucide,import { Globe } from 'lucide-react',<Globe />,Globe world,Outline
+93,Time,calendar,date schedule event appointment,Lucide,import { Calendar } from 'lucide-react',<Calendar />,Calendar date,Outline
+94,Time,refresh-cw,reload sync update refresh,Lucide,import { RefreshCw } from 'lucide-react',<RefreshCw />,Refresh reload,Outline
+95,Time,rotate-ccw,undo back revert history,Lucide,import { RotateCcw } from 'lucide-react',<RotateCcw />,Undo revert,Outline
+96,Time,rotate-cw,redo forward repeat history,Lucide,import { RotateCw } from 'lucide-react',<RotateCw />,Redo forward,Outline
+97,Development,code,develop programming syntax html,Lucide,import { Code } from 'lucide-react',<Code />,Code development,Outline
+98,Development,terminal,console cli command shell,Lucide,import { Terminal } from 'lucide-react',<Terminal />,Terminal console,Outline
+99,Development,git-branch,version control branch merge,Lucide,import { GitBranch } from 'lucide-react',<GitBranch />,Git branch,Outline
+100,Development,github,repository code open source,Lucide,import { Github } from 'lucide-react',<Github />,GitHub repository,Outline

.cursor/skills/ui-ux-pro-max/data/landing.csv

@@ -0,0 +1,31 @@
+No,Pattern Name,Keywords,Section Order,Primary CTA Placement,Color Strategy,Recommended Effects,Conversion Optimization
+1,Hero + Features + CTA,"hero, hero-centric, features, feature-rich, cta, call-to-action","1. Hero with headline/image, 2. Value prop, 3. Key features (3-5), 4. CTA section, 5. Footer",Hero (sticky) + Bottom,Hero: Brand primary or vibrant. Features: Card bg #FAFAFA. CTA: Contrasting accent color,"Hero parallax, feature card hover lift, CTA glow on hover",Deep CTA placement. Use contrasting color (at least 7:1 contrast ratio). Sticky navbar CTA.
+2,Hero + Testimonials + CTA,"hero, testimonials, social-proof, trust, reviews, cta","1. Hero, 2. Problem statement, 3. Solution overview, 4. Testimonials carousel, 5. CTA",Hero (sticky) + Post-testimonials,"Hero: Brand color. Testimonials: Light bg #F5F5F5. Quotes: Italic, muted color #666. CTA: Vibrant","Testimonial carousel slide animations, quote marks animations, avatar fade-in",Social proof before CTA. Use 3-5 testimonials. Include photo + name + role. CTA after social proof.
+3,Product Demo + Features,"demo, product-demo, features, showcase, interactive","1. Hero, 2. Product video/mockup (center), 3. Feature breakdown per section, 4. Comparison (optional), 5. CTA",Video center + CTA right/bottom,Video surround: Brand color overlay. Features: Icon color #0080FF. Text: Dark #222,"Video play button pulse, feature scroll reveals, demo interaction highlights",Embedded product demo increases engagement. Use interactive mockup if possible. Auto-play video muted.
+4,Minimal Single Column,"minimal, simple, direct, single-column, clean","1. Hero headline, 2. Short description, 3. Benefit bullets (3 max), 4. CTA, 5. Footer","Center, large CTA button",Minimalist: Brand + white #FFFFFF + accent. Buttons: High contrast 7:1+. Text: Black/Dark grey,Minimal hover effects. Smooth scroll. CTA scale on hover (subtle),Single CTA focus. Large typography. Lots of whitespace. No nav clutter. Mobile-first.
+5,Funnel (3-Step Conversion),"funnel, conversion, steps, wizard, onboarding","1. Hero, 2. Step 1 (problem), 3. Step 2 (solution), 4. Step 3 (action), 5. CTA progression",Each step: mini-CTA. Final: main CTA,"Step colors: 1 (Red/Problem), 2 (Orange/Process), 3 (Green/Solution). CTA: Brand color","Step number animations, progress bar fill, step transitions smooth scroll",Progressive disclosure. Show only essential info per step. Use progress indicators. Multiple CTAs.
+6,Comparison Table + CTA,"comparison, table, compare, versus, cta","1. Hero, 2. Problem intro, 3. Comparison table (product vs competitors), 4. Pricing (optional), 5. CTA",Table: Right column. CTA: Below table,Table: Alternating rows (white/light grey). Your product: Highlight #FFFACD (light yellow) or green. Text: Dark,"Table row hover highlight, price toggle animations, feature checkmark animations",Use comparison to show unique value. Highlight your product row. Include 'free trial' in pricing row.
+7,Lead Magnet + Form,"lead, form, signup, capture, email, magnet","1. Hero (benefit headline), 2. Lead magnet preview (ebook cover, checklist, etc), 3. Form (minimal fields), 4. CTA submit",Form CTA: Submit button,Lead magnet: Professional design. Form: Clean white bg. Inputs: Light border #CCCCCC. CTA: Brand color,"Form focus state animations, input validation animations, success confirmation animation",Form fields ≤ 3 for best conversion. Offer valuable lead magnet preview. Show form submission progress.
+8,Pricing Page + CTA,"pricing, plans, tiers, comparison, cta","1. Hero (pricing headline), 2. Price comparison cards, 3. Feature comparison table, 4. FAQ section, 5. Final CTA",Each card: CTA button. Sticky CTA in nav,"Free: Grey, Starter: Blue, Pro: Green/Gold, Enterprise: Dark. Cards: 1px border, shadow","Price toggle animation (monthly/yearly), card comparison highlight, FAQ accordion open/close",Recommend starter plan (pre-select/highlight). Show annual discount (20-30%). Use FAQs to address concerns.
+9,Video-First Hero,"video, hero, media, visual, engaging","1. Hero with video background, 2. Key features overlay, 3. Benefits section, 4. CTA",Overlay on video (center/bottom) + Bottom section,Dark overlay 60% on video. Brand accent for CTA. White text on dark.,"Video autoplay muted, parallax scroll, text fade-in on scroll",86% higher engagement with video. Add captions for accessibility. Compress video for performance.
+10,Scroll-Triggered Storytelling,"storytelling, scroll, narrative, story, immersive","1. Intro hook, 2. Chapter 1 (problem), 3. Chapter 2 (journey), 4. Chapter 3 (solution), 5. Climax CTA",End of each chapter (mini) + Final climax CTA,Progressive reveal. Each chapter has distinct color. Building intensity.,"ScrollTrigger animations, parallax layers, progressive disclosure, chapter transitions",Narrative increases time-on-page 3x. Use progress indicator. Mobile: simplify animations.
+11,AI Personalization Landing,"ai, personalization, smart, recommendation, dynamic","1. Dynamic hero (personalized), 2. Relevant features, 3. Tailored testimonials, 4. Smart CTA",Context-aware placement based on user segment,Adaptive based on user data. A/B test color variations per segment.,"Dynamic content swap, fade transitions, personalized product recommendations",20%+ conversion with personalization. Requires analytics integration. Fallback for new users.
+12,Waitlist/Coming Soon,"waitlist, coming-soon, launch, early-access, notify","1. Hero with countdown, 2. Product teaser/preview, 3. Email capture form, 4. Social proof (waitlist count)",Email form prominent (above fold) + Sticky form on scroll,Anticipation: Dark + accent highlights. Countdown in brand color. Urgency indicators.,"Countdown timer animation, email validation feedback, success confetti, social share buttons",Scarcity + exclusivity. Show waitlist count. Early access benefits. Referral program.
+13,Comparison Table Focus,"comparison, table, versus, compare, features","1. Hero (problem statement), 2. Comparison matrix (you vs competitors), 3. Feature deep-dive, 4. Winner CTA",After comparison table (highlighted row) + Bottom,Your product column highlighted (accent bg or green). Competitors neutral. Checkmarks green.,"Table row hover highlight, feature checkmark animations, sticky comparison header",Show value vs competitors. 35% higher conversion. Be factual. Include pricing if favorable.
+14,Pricing-Focused Landing,"pricing, price, cost, plans, subscription","1. Hero (value proposition), 2. Pricing cards (3 tiers), 3. Feature comparison, 4. FAQ, 5. Final CTA",Each pricing card + Sticky CTA in nav + Bottom,Popular plan highlighted (brand color border/bg). Free: grey. Enterprise: dark/premium.,"Price toggle monthly/annual animation, card hover lift, FAQ accordion smooth open",Annual discount 20-30%. Recommend mid-tier (most popular badge). Address objections in FAQ.
+15,App Store Style Landing,"app, mobile, download, store, install","1. Hero with device mockup, 2. Screenshots carousel, 3. Features with icons, 4. Reviews/ratings, 5. Download CTAs",Download buttons prominent (App Store + Play Store) throughout,Dark/light matching app store feel. Star ratings in gold. Screenshots with device frames.,"Device mockup rotations, screenshot slider, star rating animations, download button pulse",Show real screenshots. Include ratings (4.5+ stars). QR code for mobile. Platform-specific CTAs.
+16,FAQ/Documentation Landing,"faq, documentation, help, support, questions","1. Hero with search bar, 2. Popular categories, 3. FAQ accordion, 4. Contact/support CTA",Search bar prominent + Contact CTA for unresolved questions,"Clean, high readability. Minimal color. Category icons in brand color. Success green for resolved.","Search autocomplete, smooth accordion open/close, category hover, helpful feedback buttons",Reduce support tickets. Track search analytics. Show related articles. Contact escalation path.
+17,Immersive/Interactive Experience,"immersive, interactive, experience, 3d, animation","1. Full-screen interactive element, 2. Guided product tour, 3. Key benefits revealed, 4. CTA after completion",After interaction complete + Skip option for impatient users,Immersive experience colors. Dark background for focus. Highlight interactive elements.,"WebGL, 3D interactions, gamification elements, progress indicators, reward animations",40% higher engagement. Performance trade-off. Provide skip option. Mobile fallback essential.
+18,Event/Conference Landing,"event, conference, meetup, registration, schedule","1. Hero (date/location/countdown), 2. Speakers grid, 3. Agenda/schedule, 4. Sponsors, 5. Register CTA",Register CTA sticky + After speakers + Bottom,Urgency colors (countdown). Event branding. Speaker cards professional. Sponsor logos neutral.,"Countdown timer, speaker hover cards with bio, agenda tabs, early bird countdown",Early bird pricing with deadline. Social proof (past attendees). Speaker credibility. Multi-ticket discounts.
+19,Product Review/Ratings Focused,"reviews, ratings, testimonials, social-proof, stars","1. Hero (product + aggregate rating), 2. Rating breakdown, 3. Individual reviews, 4. Buy/CTA",After reviews summary + Buy button alongside reviews,Trust colors. Star ratings gold. Verified badge green. Review sentiment colors.,"Star fill animations, review filtering, helpful vote interactions, photo lightbox",User-generated content builds trust. Show verified purchases. Filter by rating. Respond to negative reviews.
+20,Community/Forum Landing,"community, forum, social, members, discussion","1. Hero (community value prop), 2. Popular topics/categories, 3. Active members showcase, 4. Join CTA",Join button prominent + After member showcase,"Warm, welcoming. Member photos add humanity. Topic badges in brand colors. Activity indicators green.","Member avatars animation, activity feed live updates, topic hover previews, join success celebration","Show active community (member count, posts today). Highlight benefits. Preview content. Easy onboarding."
+21,Before-After Transformation,"before-after, transformation, results, comparison","1. Hero (problem state), 2. Transformation slider/comparison, 3. How it works, 4. Results CTA",After transformation reveal + Bottom,Contrast: muted/grey (before) vs vibrant/colorful (after). Success green for results.,"Slider comparison interaction, before/after reveal animations, result counters, testimonial videos",Visual proof of value. 45% higher conversion. Real results. Specific metrics. Guarantee offer.
+22,Marketplace / Directory,"marketplace, directory, search, listing","1. Hero (Search focused), 2. Categories, 3. Featured Listings, 4. Trust/Safety, 5. CTA (Become a host/seller)",Hero Search Bar + Navbar 'List your item',Search: High contrast. Categories: Visual icons. Trust: Blue/Green.,Search autocomplete animation," map hover pins,  card carousel, Search bar is the CTA. Reduce friction to search. Popular searches suggestions."
+23,Newsletter / Content First,"newsletter, content, writer, blog, subscribe","1. Hero (Value Prop + Form), 2. Recent Issues/Archives, 3. Social Proof (Subscriber count), 4. About Author",Hero inline form + Sticky header form,Minimalist. Paper-like background. Text focus. Accent color for Subscribe.,Text highlight animations," typewriter effect,  subtle fade-in, Single field form (Email only). Show 'Join X, 000 readers'. Read sample link."
+24,Webinar Registration,"webinar, registration, event, training, live","1. Hero (Topic + Timer + Form), 2. What you'll learn, 3. Speaker Bio, 4. Urgency/Bonuses, 5. Form (again)",Hero (Right side form) + Bottom anchor,Urgency: Red/Orange. Professional: Blue/Navy. Form: High contrast white.,Countdown timer," speaker avatar float,  urgent ticker, Limited seats logic. 'Live' indicator. Auto-fill timezone."
+25,Enterprise Gateway,"enterprise, corporate, gateway, solutions, portal","1. Hero (Video/Mission), 2. Solutions by Industry, 3. Solutions by Role, 4. Client Logos, 5. Contact Sales",Contact Sales (Primary) + Login (Secondary),Corporate: Navy/Grey. High integrity. Conservative accents.,Slow video background," logo carousel,  tab switching for industries, Path selection (I am a...). Mega menu navigation. Trust signals prominent."
+26,Portfolio Grid,"portfolio, grid, showcase, gallery, masonry","1. Hero (Name/Role), 2. Project Grid (Masonry), 3. About/Philosophy, 4. Contact",Project Card Hover + Footer Contact,Neutral background (let work shine). Text: Black/White. Accent: Minimal.,Image lazy load reveal," hover overlay info,  lightbox view, Visuals first. Filter by category. Fast loading essential."
+27,Horizontal Scroll Journey,"horizontal, scroll, journey, gallery, storytelling, panoramic","1. Intro (Vertical), 2. The Journey (Horizontal Track), 3. Detail Reveal, 4. Vertical Footer",Floating Sticky CTA or End of Horizontal Track,Continuous palette transition. Chapter colors. Progress bar #000000.,"Scroll-jacking (careful), parallax layers, horizontal slide, progress indicator","Immersive product discovery. High engagement. Keep navigation visible.
+28,Bento Grid Showcase,bento,  grid,  features,  modular,  apple-style,  showcase"", 1. Hero, 2. Bento Grid (Key Features), 3. Detail Cards, 4. Tech Specs, 5. CTA, Floating Action Button or Bottom of Grid, Card backgrounds: #F5F5F7 or Glass. Icons: Vibrant brand colors. Text: Dark., Hover card scale (1.02), video inside cards, tilt effect, staggered reveal, Scannable value props. High information density without clutter. Mobile stack.
+29,Interactive 3D Configurator,3d,  configurator,  customizer,  interactive,  product"", 1. Hero (Configurator), 2. Feature Highlight (synced), 3. Price/Specs, 4. Purchase, Inside Configurator UI + Sticky Bottom Bar, Neutral studio background. Product: Realistic materials. UI: Minimal overlay., Real-time rendering, material swap animation, camera rotate/zoom, light reflection, Increases ownership feeling. 360 view reduces return rates. Direct add-to-cart.
+30,AI-Driven Dynamic Landing,ai,  dynamic,  personalized,  adaptive,  generative"", 1. Prompt/Input Hero, 2. Generated Result Preview, 3. How it Works, 4. Value Prop, Input Field (Hero) + 'Try it' Buttons, Adaptive to user input. Dark mode for compute feel. Neon accents., Typing text effects, shimmering generation loaders, morphing layouts, Immediate value demonstration. 'Show, don't tell'. Low friction start."

.cursor/skills/ui-ux-pro-max/data/products.csv

@@ -0,0 +1,97 @@
+No,Product Type,Keywords,Primary Style Recommendation,Secondary Styles,Landing Page Pattern,Dashboard Style (if applicable),Color Palette Focus,Key Considerations
+1,SaaS (General),"app, b2b, cloud, general, saas, software, subscription",Glassmorphism + Flat Design,"Soft UI Evolution, Minimalism",Hero + Features + CTA,Data-Dense + Real-Time Monitoring,Trust blue + accent contrast,Balance modern feel with clarity. Focus on CTAs.
+2,Micro SaaS,"app, b2b, cloud, indie, micro, micro-saas, niche, saas, small, software, solo, subscription",Flat Design + Vibrant & Block,"Motion-Driven, Micro-interactions",Minimal & Direct + Demo,Executive Dashboard,Vibrant primary + white space,"Keep simple, show product quickly. Speed is key."
+3,E-commerce,"buy, commerce, e, ecommerce, products, retail, sell, shop, store",Vibrant & Block-based,"Aurora UI, Motion-Driven",Feature-Rich Showcase,Sales Intelligence Dashboard,Brand primary + success green,Engagement & conversions. High visual hierarchy.
+4,E-commerce Luxury,"buy, commerce, e, ecommerce, elegant, exclusive, high-end, luxury, premium, products, retail, sell, shop, store",Liquid Glass + Glassmorphism,"3D & Hyperrealism, Aurora UI",Feature-Rich Showcase,Sales Intelligence Dashboard,Premium colors + minimal accent,Elegance & sophistication. Premium materials.
+5,Service Landing Page,"appointment, booking, consultation, conversion, landing, marketing, page, service",Hero-Centric + Trust & Authority,"Social Proof-Focused, Storytelling",Hero-Centric Design,N/A - Analytics for conversions,Brand primary + trust colors,Social proof essential. Show expertise.
+6,B2B Service,"appointment, b, b2b, booking, business, consultation, corporate, enterprise, service",Trust & Authority + Minimal,"Feature-Rich, Conversion-Optimized",Feature-Rich Showcase,Sales Intelligence Dashboard,Professional blue + neutral grey,Credibility essential. Clear ROI messaging.
+7,Financial Dashboard,"admin, analytics, dashboard, data, financial, panel",Dark Mode (OLED) + Data-Dense,"Minimalism, Accessible & Ethical",N/A - Dashboard focused,Financial Dashboard,Dark bg + red/green alerts + trust blue,"High contrast, real-time updates, accuracy paramount."
+8,Analytics Dashboard,"admin, analytics, dashboard, data, panel",Data-Dense + Heat Map & Heatmap,"Minimalism, Dark Mode (OLED)",N/A - Analytics focused,Drill-Down Analytics + Comparative,Cool→Hot gradients + neutral grey,Clarity > aesthetics. Color-coded data priority.
+9,Healthcare App,"app, clinic, health, healthcare, medical, patient",Neumorphism + Accessible & Ethical,"Soft UI Evolution, Claymorphism (for patients)",Social Proof-Focused,User Behavior Analytics,Calm blue + health green + trust,Accessibility mandatory. Calming aesthetic.
+10,Educational App,"app, course, education, educational, learning, school, training",Claymorphism + Micro-interactions,"Vibrant & Block-based, Flat Design",Storytelling-Driven,User Behavior Analytics,Playful colors + clear hierarchy,Engagement & ease of use. Age-appropriate design.
+11,Creative Agency,"agency, creative, design, marketing, studio",Brutalism + Motion-Driven,"Retro-Futurism, Storytelling-Driven",Storytelling-Driven,N/A - Portfolio focused,Bold primaries + artistic freedom,Differentiation key. Wow-factor necessary.
+12,Portfolio/Personal,"creative, personal, portfolio, projects, showcase, work",Motion-Driven + Minimalism,"Brutalism, Aurora UI",Storytelling-Driven,N/A - Personal branding,Brand primary + artistic interpretation,Showcase work. Personality shine through.
+13,Gaming,"entertainment, esports, game, gaming, play",3D & Hyperrealism + Retro-Futurism,"Motion-Driven, Vibrant & Block",Feature-Rich Showcase,N/A - Game focused,Vibrant + neon + immersive colors,Immersion priority. Performance critical.
+14,Government/Public Service,"appointment, booking, consultation, government, public, service",Accessible & Ethical + Minimalism,"Flat Design, Inclusive Design",Minimal & Direct,Executive Dashboard,Professional blue + high contrast,WCAG AAA mandatory. Trust paramount.
+15,Fintech/Crypto,"banking, blockchain, crypto, defi, finance, fintech, money, nft, payment, web3",Glassmorphism + Dark Mode (OLED),"Retro-Futurism, Motion-Driven",Conversion-Optimized,Real-Time Monitoring + Predictive,Dark tech colors + trust + vibrant accents,Security perception. Real-time data critical.
+16,Social Media App,"app, community, content, entertainment, media, network, sharing, social, streaming, users, video",Vibrant & Block-based + Motion-Driven,"Aurora UI, Micro-interactions",Feature-Rich Showcase,User Behavior Analytics,Vibrant + engagement colors,Engagement & retention. Addictive design ethics.
+17,Productivity Tool,"collaboration, productivity, project, task, tool, workflow",Flat Design + Micro-interactions,"Minimalism, Soft UI Evolution",Interactive Product Demo,Drill-Down Analytics,Clear hierarchy + functional colors,Ease of use. Speed & efficiency focus.
+18,Design System/Component Library,"component, design, library, system",Minimalism + Accessible & Ethical,"Flat Design, Zero Interface",Feature-Rich Showcase,N/A - Dev focused,Clear hierarchy + code-like structure,Consistency. Developer-first approach.
+19,AI/Chatbot Platform,"ai, artificial-intelligence, automation, chatbot, machine-learning, ml, platform",AI-Native UI + Minimalism,"Zero Interface, Glassmorphism",Interactive Product Demo,AI/ML Analytics Dashboard,Neutral + AI Purple (#6366F1),Conversational UI. Streaming text. Context awareness. Minimal chrome.
+20,NFT/Web3 Platform,"nft, platform, web",Cyberpunk UI + Glassmorphism,"Aurora UI, 3D & Hyperrealism",Feature-Rich Showcase,Crypto/Blockchain Dashboard,Dark + Neon + Gold (#FFD700),Wallet integration. Transaction feedback. Gas fees display. Dark mode essential.
+21,Creator Economy Platform,"creator, economy, platform",Vibrant & Block-based + Bento Box Grid,"Motion-Driven, Aurora UI",Social Proof-Focused,User Behavior Analytics,Vibrant + Brand colors,Creator profiles. Monetization display. Engagement metrics. Social proof.
+22,Sustainability/ESG Platform,"ai, artificial-intelligence, automation, esg, machine-learning, ml, platform, sustainability",Organic Biophilic + Minimalism,"Accessible & Ethical, Flat Design",Trust & Authority,Energy/Utilities Dashboard,Green (#228B22) + Earth tones,Carbon footprint visuals. Progress indicators. Certification badges. Eco-friendly imagery.
+23,Remote Work/Collaboration Tool,"collaboration, remote, tool, work",Soft UI Evolution + Minimalism,"Glassmorphism, Micro-interactions",Feature-Rich Showcase,Drill-Down Analytics,Calm Blue + Neutral grey,Real-time collaboration. Status indicators. Video integration. Notification management.
+24,Mental Health App,"app, health, mental",Neumorphism + Accessible & Ethical,"Claymorphism, Soft UI Evolution",Social Proof-Focused,Healthcare Analytics,Calm Pastels + Trust colors,Calming aesthetics. Privacy-first. Crisis resources. Progress tracking. Accessibility mandatory.
+25,Pet Tech App,"app, pet, tech",Claymorphism + Vibrant & Block-based,"Micro-interactions, Flat Design",Storytelling-Driven,User Behavior Analytics,Playful + Warm colors,Pet profiles. Health tracking. Playful UI. Photo galleries. Vet integration.
+26,Smart Home/IoT Dashboard,"admin, analytics, dashboard, data, home, iot, panel, smart",Glassmorphism + Dark Mode (OLED),"Minimalism, AI-Native UI",Interactive Product Demo,Real-Time Monitoring,Dark + Status indicator colors,Device status. Real-time controls. Energy monitoring. Automation rules. Quick actions.
+27,EV/Charging Ecosystem,"charging, ecosystem, ev",Minimalism + Aurora UI,"Glassmorphism, Organic Biophilic",Hero-Centric Design,Energy/Utilities Dashboard,Electric Blue (#009CD1) + Green,Charging station maps. Range estimation. Cost calculation. Environmental impact.
+28,Subscription Box Service,"appointment, booking, box, consultation, membership, plan, recurring, service, subscription",Vibrant & Block-based + Motion-Driven,"Claymorphism, Aurora UI",Feature-Rich Showcase,E-commerce Analytics,Brand + Excitement colors,Unboxing experience. Personalization quiz. Subscription management. Product reveals.
+29,Podcast Platform,"platform, podcast",Dark Mode (OLED) + Minimalism,"Motion-Driven, Vibrant & Block-based",Storytelling-Driven,Media/Entertainment Dashboard,Dark + Audio waveform accents,Audio player UX. Episode discovery. Creator tools. Analytics for podcasters.
+30,Dating App,"app, dating",Vibrant & Block-based + Motion-Driven,"Aurora UI, Glassmorphism",Social Proof-Focused,User Behavior Analytics,Warm + Romantic (Pink/Red gradients),Profile cards. Swipe interactions. Match animations. Safety features. Video chat.
+31,Micro-Credentials/Badges Platform,"badges, credentials, micro, platform",Minimalism + Flat Design,"Accessible & Ethical, Swiss Modernism 2.0",Trust & Authority,Education Dashboard,Trust Blue + Gold (#FFD700),Credential verification. Badge display. Progress tracking. Issuer trust. LinkedIn integration.
+32,Knowledge Base/Documentation,"base, documentation, knowledge",Minimalism + Accessible & Ethical,"Swiss Modernism 2.0, Flat Design",FAQ/Documentation,N/A - Documentation focused,Clean hierarchy + minimal color,Search-first. Clear navigation. Code highlighting. Version switching. Feedback system.
+33,Hyperlocal Services,"appointment, booking, consultation, hyperlocal, service, services",Minimalism + Vibrant & Block-based,"Micro-interactions, Flat Design",Conversion-Optimized,Drill-Down Analytics + Map,Location markers + Trust colors,Map integration. Service categories. Provider profiles. Booking system. Reviews.
+34,Beauty/Spa/Wellness Service,"appointment, beauty, booking, consultation, service, spa, wellness",Soft UI Evolution + Neumorphism,"Glassmorphism, Minimalism",Hero-Centric Design + Social Proof,User Behavior Analytics,Soft pastels (Pink #FFB6C1 Sage #90EE90) + Cream + Gold accents,Calming aesthetic. Booking system. Service menu. Before/after gallery. Testimonials. Relaxing imagery.
+35,Luxury/Premium Brand,"brand, elegant, exclusive, high-end, luxury, premium",Liquid Glass + Glassmorphism,"Minimalism, 3D & Hyperrealism",Storytelling-Driven + Feature-Rich,Sales Intelligence Dashboard,Black + Gold (#FFD700) + White + Minimal accent,Elegance paramount. Premium imagery. Storytelling. High-quality visuals. Exclusive feel.
+36,Restaurant/Food Service,"appointment, booking, consultation, delivery, food, menu, order, restaurant, service",Vibrant & Block-based + Motion-Driven,"Claymorphism, Flat Design",Hero-Centric Design + Conversion,N/A - Booking focused,Warm colors (Orange Red Brown) + appetizing imagery,Menu display. Online ordering. Reservation system. Food photography. Location/hours prominent.
+37,Fitness/Gym App,"app, exercise, fitness, gym, health, workout",Vibrant & Block-based + Dark Mode (OLED),"Motion-Driven, Neumorphism",Feature-Rich Showcase,User Behavior Analytics,Energetic (Orange #FF6B35 Electric Blue) + Dark bg,Progress tracking. Workout plans. Community features. Achievements. Motivational design.
+38,Real Estate/Property,"buy, estate, housing, property, real, real-estate, rent",Glassmorphism + Minimalism,"Motion-Driven, 3D & Hyperrealism",Hero-Centric Design + Feature-Rich,Sales Intelligence Dashboard,Trust Blue (#0077B6) + Gold accents + White,Property listings. Virtual tours. Map integration. Agent profiles. Mortgage calculator. High-quality imagery.
+39,Travel/Tourism Agency,"agency, booking, creative, design, flight, hotel, marketing, studio, tourism, travel, vacation",Aurora UI + Motion-Driven,"Vibrant & Block-based, Glassmorphism",Storytelling-Driven + Hero-Centric,Booking Analytics,Vibrant destination colors + Sky Blue + Warm accents,Destination showcase. Booking system. Itinerary builder. Reviews. Inspiration galleries. Mobile-first.
+40,Hotel/Hospitality,"hospitality, hotel",Liquid Glass + Minimalism,"Glassmorphism, Soft UI Evolution",Hero-Centric Design + Social Proof,Revenue Management Dashboard,Warm neutrals + Gold (#D4AF37) + Brand accent,Room booking. Amenities showcase. Location maps. Guest reviews. Seasonal pricing. Luxury imagery.
+41,Wedding/Event Planning,"conference, event, meetup, planning, registration, ticket, wedding",Soft UI Evolution + Aurora UI,"Glassmorphism, Motion-Driven",Storytelling-Driven + Social Proof,N/A - Planning focused,Soft Pink (#FFD6E0) + Gold + Cream + Sage,Portfolio gallery. Vendor directory. Planning tools. Timeline. Budget tracker. Romantic aesthetic.
+42,Legal Services,"appointment, attorney, booking, compliance, consultation, contract, law, legal, service, services",Trust & Authority + Minimalism,"Accessible & Ethical, Swiss Modernism 2.0",Trust & Authority + Minimal,Case Management Dashboard,Navy Blue (#1E3A5F) + Gold + White,Credibility paramount. Practice areas. Attorney profiles. Case results. Contact forms. Professional imagery.
+43,Insurance Platform,"insurance, platform",Trust & Authority + Flat Design,"Accessible & Ethical, Minimalism",Conversion-Optimized + Trust,Claims Analytics Dashboard,Trust Blue (#0066CC) + Green (security) + Neutral,Quote calculator. Policy comparison. Claims process. Trust signals. Clear pricing. Security badges.
+44,Banking/Traditional Finance,"banking, finance, traditional",Minimalism + Accessible & Ethical,"Trust & Authority, Dark Mode (OLED)",Trust & Authority + Feature-Rich,Financial Dashboard,Navy (#0A1628) + Trust Blue + Gold accents,Security-first. Account overview. Transaction history. Mobile banking. Accessibility critical. Trust paramount.
+45,Online Course/E-learning,"course, e, learning, online",Claymorphism + Vibrant & Block-based,"Motion-Driven, Flat Design",Feature-Rich Showcase + Social Proof,Education Dashboard,Vibrant learning colors + Progress green,Course catalog. Progress tracking. Video player. Quizzes. Certificates. Community forums. Gamification.
+46,Non-profit/Charity,"charity, non, profit",Accessible & Ethical + Organic Biophilic,"Minimalism, Storytelling-Driven",Storytelling-Driven + Trust,Donation Analytics Dashboard,Cause-related colors + Trust + Warm,Impact stories. Donation flow. Transparency reports. Volunteer signup. Event calendar. Emotional connection.
+47,Music Streaming,"music, streaming",Dark Mode (OLED) + Vibrant & Block-based,"Motion-Driven, Aurora UI",Feature-Rich Showcase,Media/Entertainment Dashboard,Dark (#121212) + Vibrant accents + Album art colors,Audio player. Playlist management. Artist pages. Personalization. Social features. Waveform visualizations.
+48,Video Streaming/OTT,"ott, streaming, video",Dark Mode (OLED) + Motion-Driven,"Glassmorphism, Vibrant & Block-based",Hero-Centric Design + Feature-Rich,Media/Entertainment Dashboard,Dark bg + Content poster colors + Brand accent,Video player. Content discovery. Watchlist. Continue watching. Personalized recommendations. Thumbnail-heavy.
+49,Job Board/Recruitment,"board, job, recruitment",Flat Design + Minimalism,"Vibrant & Block-based, Accessible & Ethical",Conversion-Optimized + Feature-Rich,HR Analytics Dashboard,Professional Blue + Success Green + Neutral,Job listings. Search/filter. Company profiles. Application tracking. Resume upload. Salary insights.
+50,Marketplace (P2P),"buyers, listings, marketplace, p, platform, sellers",Vibrant & Block-based + Flat Design,"Micro-interactions, Trust & Authority",Feature-Rich Showcase + Social Proof,E-commerce Analytics,Trust colors + Category colors + Success green,Seller/buyer profiles. Listings. Reviews/ratings. Secure payment. Messaging. Search/filter. Trust badges.
+51,Logistics/Delivery,"delivery, logistics",Minimalism + Flat Design,"Dark Mode (OLED), Micro-interactions",Feature-Rich Showcase + Conversion,Real-Time Monitoring + Route Analytics,Blue (#2563EB) + Orange (tracking) + Green (delivered),Real-time tracking. Delivery scheduling. Route optimization. Driver management. Status updates. Map integration.
+52,Agriculture/Farm Tech,"agriculture, farm, tech",Organic Biophilic + Flat Design,"Minimalism, Accessible & Ethical",Feature-Rich Showcase + Trust,IoT Sensor Dashboard,Earth Green (#4A7C23) + Brown + Sky Blue,Crop monitoring. Weather data. IoT sensors. Yield tracking. Market prices. Sustainable imagery.
+53,Construction/Architecture,"architecture, construction",Minimalism + 3D & Hyperrealism,"Brutalism, Swiss Modernism 2.0",Hero-Centric Design + Feature-Rich,Project Management Dashboard,Grey (#4A4A4A) + Orange (safety) + Blueprint Blue,Project portfolio. 3D renders. Timeline. Material specs. Team collaboration. Blueprint aesthetic.
+54,Automotive/Car Dealership,"automotive, car, dealership",Motion-Driven + 3D & Hyperrealism,"Dark Mode (OLED), Glassmorphism",Hero-Centric Design + Feature-Rich,Sales Intelligence Dashboard,Brand colors + Metallic accents + Dark/Light,Vehicle showcase. 360° views. Comparison tools. Financing calculator. Test drive booking. High-quality imagery.
+55,Photography Studio,"photography, studio",Motion-Driven + Minimalism,"Aurora UI, Glassmorphism",Storytelling-Driven + Hero-Centric,N/A - Portfolio focused,Black + White + Minimal accent,Portfolio gallery. Before/after. Service packages. Booking system. Client galleries. Full-bleed imagery.
+56,Coworking Space,"coworking, space",Vibrant & Block-based + Glassmorphism,"Minimalism, Motion-Driven",Hero-Centric Design + Feature-Rich,Occupancy Dashboard,Energetic colors + Wood tones + Brand accent,Space tour. Membership plans. Booking system. Amenities. Community events. Virtual tour.
+57,Cleaning Service,"appointment, booking, cleaning, consultation, service",Soft UI Evolution + Flat Design,"Minimalism, Micro-interactions",Conversion-Optimized + Trust,Service Analytics,Fresh Blue (#00B4D8) + Clean White + Green,Service packages. Booking system. Price calculator. Before/after gallery. Reviews. Trust badges.
+58,Home Services (Plumber/Electrician),"appointment, booking, consultation, electrician, home, plumber, service, services",Flat Design + Trust & Authority,"Minimalism, Accessible & Ethical",Conversion-Optimized + Trust,Service Analytics,Trust Blue + Safety Orange + Professional grey,Service list. Emergency contact. Booking. Price transparency. Certifications. Local trust signals.
+59,Childcare/Daycare,"childcare, daycare",Claymorphism + Vibrant & Block-based,"Soft UI Evolution, Accessible & Ethical",Social Proof-Focused + Trust,Parent Dashboard,Playful pastels + Safe colors + Warm accents,Programs. Staff profiles. Safety certifications. Parent portal. Activity updates. Cheerful imagery.
+60,Senior Care/Elderly,"care, elderly, senior",Accessible & Ethical + Soft UI Evolution,"Minimalism, Neumorphism",Trust & Authority + Social Proof,Healthcare Analytics,Calm Blue + Warm neutrals + Large text,Care services. Staff qualifications. Facility tour. Family portal. Large touch targets. High contrast. Accessibility-first.
+61,Medical Clinic,"clinic, medical",Accessible & Ethical + Minimalism,"Neumorphism, Trust & Authority",Trust & Authority + Conversion,Healthcare Analytics,Medical Blue (#0077B6) + Trust White + Calm Green,Services. Doctor profiles. Online booking. Patient portal. Insurance info. HIPAA compliant. Trust signals.
+62,Pharmacy/Drug Store,"drug, pharmacy, store",Flat Design + Accessible & Ethical,"Minimalism, Trust & Authority",Conversion-Optimized + Trust,Inventory Dashboard,Pharmacy Green + Trust Blue + Clean White,Product catalog. Prescription upload. Refill reminders. Health info. Store locator. Safety certifications.
+63,Dental Practice,"dental, practice",Soft UI Evolution + Minimalism,"Accessible & Ethical, Trust & Authority",Social Proof-Focused + Conversion,Patient Analytics,Fresh Blue + White + Smile Yellow accent,Services. Dentist profiles. Before/after. Online booking. Insurance. Patient testimonials. Friendly imagery.
+64,Veterinary Clinic,"clinic, veterinary",Claymorphism + Accessible & Ethical,"Soft UI Evolution, Flat Design",Social Proof-Focused + Trust,Pet Health Dashboard,Caring Blue + Pet-friendly colors + Warm accents,Pet services. Vet profiles. Online booking. Pet portal. Emergency info. Friendly animal imagery.
+65,Florist/Plant Shop,"florist, plant, shop",Organic Biophilic + Vibrant & Block-based,"Aurora UI, Motion-Driven",Hero-Centric Design + Conversion,E-commerce Analytics,Natural Green + Floral pinks/purples + Earth tones,Product catalog. Occasion categories. Delivery scheduling. Care guides. Seasonal collections. Beautiful imagery.
+66,Bakery/Cafe,"bakery, cafe",Vibrant & Block-based + Soft UI Evolution,"Claymorphism, Motion-Driven",Hero-Centric Design + Conversion,N/A - Order focused,Warm Brown + Cream + Appetizing accents,Menu display. Online ordering. Location/hours. Catering. Seasonal specials. Appetizing photography.
+67,Coffee Shop,"coffee, shop",Minimalism + Organic Biophilic,"Soft UI Evolution, Flat Design",Hero-Centric Design + Conversion,N/A - Order focused,Coffee Brown (#6F4E37) + Cream + Warm accents,Menu. Online ordering. Loyalty program. Location. Story/origin. Cozy aesthetic.
+68,Brewery/Winery,"brewery, winery",Motion-Driven + Storytelling-Driven,"Dark Mode (OLED), Organic Biophilic",Storytelling-Driven + Hero-Centric,N/A - E-commerce focused,Deep amber/burgundy + Gold + Craft aesthetic,Product showcase. Story/heritage. Tasting notes. Events. Club membership. Artisanal imagery.
+69,Airline,"ai, airline, artificial-intelligence, automation, machine-learning, ml",Minimalism + Glassmorphism,"Motion-Driven, Accessible & Ethical",Conversion-Optimized + Feature-Rich,Operations Dashboard,Sky Blue + Brand colors + Trust accents,Flight search. Booking. Check-in. Boarding pass. Loyalty program. Route maps. Mobile-first.
+70,News/Media Platform,"content, entertainment, media, news, platform, streaming, video",Minimalism + Flat Design,"Dark Mode (OLED), Accessible & Ethical",Hero-Centric Design + Feature-Rich,Media Analytics Dashboard,Brand colors + High contrast + Category colors,Article layout. Breaking news. Categories. Search. Subscription. Mobile reading. Fast loading.
+71,Magazine/Blog,"articles, blog, content, magazine, posts, writing",Swiss Modernism 2.0 + Motion-Driven,"Minimalism, Aurora UI",Storytelling-Driven + Hero-Centric,Content Analytics,Editorial colors + Brand primary + Clean white,Article showcase. Category navigation. Author profiles. Newsletter signup. Related content. Typography-focused.
+72,Freelancer Platform,"freelancer, platform",Flat Design + Minimalism,"Vibrant & Block-based, Micro-interactions",Feature-Rich Showcase + Conversion,Marketplace Analytics,Professional Blue + Success Green + Neutral,Profile creation. Portfolio. Skill matching. Messaging. Payment. Reviews. Project management.
+73,Consulting Firm,"consulting, firm",Trust & Authority + Minimalism,"Swiss Modernism 2.0, Accessible & Ethical",Trust & Authority + Feature-Rich,N/A - Lead generation,Navy + Gold + Professional grey,Service areas. Case studies. Team profiles. Thought leadership. Contact. Professional credibility.
+74,Marketing Agency,"agency, creative, design, marketing, studio",Brutalism + Motion-Driven,"Vibrant & Block-based, Aurora UI",Storytelling-Driven + Feature-Rich,Campaign Analytics,Bold brand colors + Creative freedom,Portfolio. Case studies. Services. Team. Creative showcase. Results-focused. Bold aesthetic.
+75,Event Management,"conference, event, management, meetup, registration, ticket",Vibrant & Block-based + Motion-Driven,"Glassmorphism, Aurora UI",Hero-Centric Design + Feature-Rich,Event Analytics,Event theme colors + Excitement accents,Event showcase. Registration. Agenda. Speakers. Sponsors. Ticket sales. Countdown timer.
+76,Conference/Webinar Platform,"conference, platform, webinar",Glassmorphism + Minimalism,"Motion-Driven, Flat Design",Feature-Rich Showcase + Conversion,Attendee Analytics,Professional Blue + Video accent + Brand,Registration. Agenda. Speaker profiles. Live stream. Networking. Recording access. Virtual event features.
+77,Membership/Community,"community, membership",Vibrant & Block-based + Soft UI Evolution,"Bento Box Grid, Micro-interactions",Social Proof-Focused + Conversion,Community Analytics,Community brand colors + Engagement accents,Member benefits. Pricing tiers. Community showcase. Events. Member directory. Exclusive content.
+78,Newsletter Platform,"newsletter, platform",Minimalism + Flat Design,"Swiss Modernism 2.0, Accessible & Ethical",Minimal & Direct + Conversion,Email Analytics,Brand primary + Clean white + CTA accent,Subscribe form. Archive. About. Social proof. Sample content. Simple conversion.
+79,Digital Products/Downloads,"digital, downloads, products",Vibrant & Block-based + Motion-Driven,"Glassmorphism, Bento Box Grid",Feature-Rich Showcase + Conversion,E-commerce Analytics,Product category colors + Brand + Success green,Product showcase. Preview. Pricing. Instant delivery. License management. Customer reviews.
+80,Church/Religious Organization,"church, organization, religious",Accessible & Ethical + Soft UI Evolution,"Minimalism, Trust & Authority",Hero-Centric Design + Social Proof,N/A - Community focused,Warm Gold + Deep Purple/Blue + White,Service times. Events. Sermons. Community. Giving. Location. Welcoming imagery.
+81,Sports Team/Club,"club, sports, team",Vibrant & Block-based + Motion-Driven,"Dark Mode (OLED), 3D & Hyperrealism",Hero-Centric Design + Feature-Rich,Performance Analytics,Team colors + Energetic accents,Schedule. Roster. News. Tickets. Merchandise. Fan engagement. Action imagery.
+82,Museum/Gallery,"gallery, museum",Minimalism + Motion-Driven,"Swiss Modernism 2.0, 3D & Hyperrealism",Storytelling-Driven + Feature-Rich,Visitor Analytics,Art-appropriate neutrals + Exhibition accents,Exhibitions. Collections. Tickets. Events. Virtual tours. Educational content. Art-focused design.
+83,Theater/Cinema,"cinema, theater",Dark Mode (OLED) + Motion-Driven,"Vibrant & Block-based, Glassmorphism",Hero-Centric Design + Conversion,Booking Analytics,Dark + Spotlight accents + Gold,Showtimes. Seat selection. Trailers. Coming soon. Membership. Dramatic imagery.
+84,Language Learning App,"app, language, learning",Claymorphism + Vibrant & Block-based,"Micro-interactions, Flat Design",Feature-Rich Showcase + Social Proof,Learning Analytics,Playful colors + Progress indicators + Country flags,Lesson structure. Progress tracking. Gamification. Speaking practice. Community. Achievement badges.
+85,Coding Bootcamp,"bootcamp, coding",Dark Mode (OLED) + Minimalism,"Cyberpunk UI, Flat Design",Feature-Rich Showcase + Social Proof,Student Analytics,Code editor colors + Brand + Success green,Curriculum. Projects. Career outcomes. Alumni. Pricing. Application. Terminal aesthetic.
+86,Cybersecurity Platform,"cyber, security, platform",Cyberpunk UI + Dark Mode (OLED),"Neubrutalism, Minimal & Direct",Trust & Authority + Real-Time,Real-Time Monitoring + Heat Map,Matrix Green + Deep Black + Terminal feel,Data density. Threat visualization. Dark mode default.
+87,Developer Tool / IDE,"dev, developer, tool, ide",Dark Mode (OLED) + Minimalism,"Flat Design, Bento Box Grid",Minimal & Direct + Documentation,Real-Time Monitor + Terminal,Dark syntax theme colors + Blue focus,Keyboard shortcuts. Syntax highlighting. Fast performance.
+88,Biotech / Life Sciences,"biotech, biology, science",Glassmorphism + Clean Science,"Minimalism, Organic Biophilic",Storytelling-Driven + Research,Data-Dense + Predictive,Sterile White + DNA Blue + Life Green,Data accuracy. Cleanliness. Complex data viz.
+89,Space Tech / Aerospace,"aerospace, space, tech",Holographic / HUD + Dark Mode,"Glassmorphism, 3D & Hyperrealism",Immersive Experience + Hero,Real-Time Monitoring + 3D,Deep Space Black + Star White + Metallic,High-tech feel. Precision. Telemetry data.
+90,Architecture / Interior,"architecture, design, interior",Exaggerated Minimalism + High Imagery,"Swiss Modernism 2.0, Parallax",Portfolio Grid + Visuals,Project Management + Gallery,Monochrome + Gold Accent + High Imagery,High-res images. Typography. Space.
+91,Quantum Computing Interface,"quantum, computing, physics, qubit, future, science",Holographic / HUD + Dark Mode,"Glassmorphism, Spatial UI",Immersive/Interactive Experience,3D Spatial Data + Real-Time Monitor,Quantum Blue #00FFFF + Deep Black + Interference patterns,Visualize complexity. Qubit states. Probability clouds. High-tech trust.
+92,Biohacking / Longevity App,"biohacking, health, longevity, tracking, wellness, science",Biomimetic / Organic 2.0,"Minimalism, Dark Mode (OLED)",Data-Dense + Storytelling,Real-Time Monitor + Biological Data,Cellular Pink/Red + DNA Blue + Clean White,Personal data privacy. Scientific credibility. Biological visualizations.
+93,Autonomous Drone Fleet Manager,"drone, autonomous, fleet, aerial, logistics, robotics",HUD / Sci-Fi FUI,"Real-Time Monitor, Spatial UI",Real-Time Monitor,Geographic + Real-Time,Tactical Green #00FF00 + Alert Red + Map Dark,Real-time telemetry. 3D spatial awareness. Latency indicators. Safety alerts.
+94,Generative Art Platform,"art, generative, ai, creative, platform, gallery",Minimalism (Frame) + Gen Z Chaos,"Masonry Grid, Dark Mode",Bento Grid Showcase,Gallery / Portfolio,Neutral #F5F5F5 (Canvas) + User Content,Content is king. Fast loading. Creator attribution. Minting flow.
+95,Spatial Computing OS / App,"spatial, vr, ar, vision, os, immersive, mixed-reality",Spatial UI (VisionOS),"Glassmorphism, 3D & Hyperrealism",Immersive/Interactive Experience,Spatial Dashboard,Frosted Glass + System Colors + Depth,Gaze/Pinch interaction. Depth hierarchy. Environment awareness.
+96,Sustainable Energy / Climate Tech,"climate, energy, sustainable, green, tech, carbon",Organic Biophilic + E-Ink / Paper,"Data-Dense, Swiss Modernism",Interactive Demo + Data,Energy/Utilities Dashboard,Earth Green + Sky Blue + Solar Yellow,Data transparency. Impact visualization. Low-carbon web design.

.cursor/skills/ui-ux-pro-max/data/react-performance.csv

@@ -0,0 +1,45 @@
+No,Category,Issue,Keywords,Platform,Description,Do,Don't,Code Example Good,Code Example Bad,Severity
+1,Async Waterfall,Defer Await,async await defer branch,React/Next.js,Move await into branches where actually used to avoid blocking unused code paths,Move await operations into branches where they're needed,Await at top of function blocking all branches,"if (skip) return { skipped: true }; const data = await fetch()","const data = await fetch(); if (skip) return { skipped: true }",Critical
+2,Async Waterfall,Promise.all Parallel,promise all parallel concurrent,React/Next.js,Execute independent async operations concurrently using Promise.all(),Use Promise.all() for independent operations,Sequential await for independent operations,"const [user, posts] = await Promise.all([fetchUser(), fetchPosts()])","const user = await fetchUser(); const posts = await fetchPosts()",Critical
+3,Async Waterfall,Dependency Parallelization,better-all dependency parallel,React/Next.js,Use better-all for operations with partial dependencies to maximize parallelism,Use better-all to start each task at earliest possible moment,Wait for unrelated data before starting dependent fetch,"await all({ user() {}, config() {}, profile() { return fetch((await this.$.user).id) } })","const [user, config] = await Promise.all([...]); const profile = await fetchProfile(user.id)",Critical
+4,Async Waterfall,API Route Optimization,api route waterfall promise,React/Next.js,In API routes start independent operations immediately even if not awaited yet,Start promises early and await late,Sequential awaits in API handlers,"const sessionP = auth(); const configP = fetchConfig(); const session = await sessionP","const session = await auth(); const config = await fetchConfig()",Critical
+5,Async Waterfall,Suspense Boundaries,suspense streaming boundary,React/Next.js,Use Suspense to show wrapper UI faster while data loads,Wrap async components in Suspense boundaries,Await data blocking entire page render,"<Suspense fallback={<Skeleton />}><DataDisplay /></Suspense>","const data = await fetchData(); return <DataDisplay data={data} />",High
+6,Bundle Size,Barrel Imports,barrel import direct path,React/Next.js,Import directly from source files instead of barrel files to avoid loading unused modules,Import directly from source path,Import from barrel/index files,"import Check from 'lucide-react/dist/esm/icons/check'","import { Check } from 'lucide-react'",Critical
+7,Bundle Size,Dynamic Imports,dynamic import lazy next,React/Next.js,Use next/dynamic to lazy-load large components not needed on initial render,Use dynamic() for heavy components,Import heavy components at top level,"const Monaco = dynamic(() => import('./monaco'), { ssr: false })","import { MonacoEditor } from './monaco-editor'",Critical
+8,Bundle Size,Defer Third Party,analytics defer third-party,React/Next.js,Load analytics and logging after hydration since they don't block interaction,Load non-critical scripts after hydration,Include analytics in main bundle,"const Analytics = dynamic(() => import('@vercel/analytics'), { ssr: false })","import { Analytics } from '@vercel/analytics/react'",Medium
+9,Bundle Size,Conditional Loading,conditional module lazy,React/Next.js,Load large data or modules only when a feature is activated,Dynamic import when feature enabled,Import large modules unconditionally,"useEffect(() => { if (enabled) import('./heavy.js') }, [enabled])","import { heavyData } from './heavy.js'",High
+10,Bundle Size,Preload Intent,preload hover focus intent,React/Next.js,Preload heavy bundles on hover/focus before they're needed,Preload on user intent signals,Load only on click,"onMouseEnter={() => import('./editor')}","onClick={() => import('./editor')}",Medium
+11,Server,React.cache Dedup,react cache deduplicate request,React/Next.js,Use React.cache() for server-side request deduplication within single request,Wrap data fetchers with cache(),Fetch same data multiple times in tree,"export const getUser = cache(async () => await db.user.find())","export async function getUser() { return await db.user.find() }",Medium
+12,Server,LRU Cache Cross-Request,lru cache cross request,React/Next.js,Use LRU cache for data shared across sequential requests,Use LRU for cross-request caching,Refetch same data on every request,"const cache = new LRUCache({ max: 1000, ttl: 5*60*1000 })","Always fetch from database",High
+13,Server,Minimize Serialization,serialization rsc boundary,React/Next.js,Only pass fields that client actually uses across RSC boundaries,Pass only needed fields to client components,Pass entire objects to client,"<Profile name={user.name} />","<Profile user={user} /> // 50 fields serialized",High
+14,Server,Parallel Fetching,parallel fetch component composition,React/Next.js,Restructure components to parallelize data fetching in RSC,Use component composition for parallel fetches,Sequential fetches in parent component,"<Header /><Sidebar /> // both fetch in parallel","const header = await fetchHeader(); return <><div>{header}</div><Sidebar /></>",Critical
+15,Server,After Non-blocking,after non-blocking logging,React/Next.js,Use Next.js after() to schedule work after response is sent,Use after() for logging/analytics,Block response for non-critical operations,"after(async () => { await logAction() }); return Response.json(data)","await logAction(); return Response.json(data)",Medium
+16,Client,SWR Deduplication,swr dedup cache revalidate,React/Next.js,Use SWR for automatic request deduplication and caching,Use useSWR for client data fetching,Manual fetch in useEffect,"const { data } = useSWR('/api/users', fetcher)","useEffect(() => { fetch('/api/users').then(setUsers) }, [])",Medium-High
+17,Client,Event Listener Dedup,event listener deduplicate global,React/Next.js,Share global event listeners across component instances,Use useSWRSubscription for shared listeners,Register listener per component instance,"useSWRSubscription('global-keydown', () => { window.addEventListener... })","useEffect(() => { window.addEventListener('keydown', handler) }, [])",Low
+18,Rerender,Defer State Reads,state read callback subscription,React/Next.js,Don't subscribe to state only used in callbacks,Read state on-demand in callbacks,Subscribe to state used only in handlers,"const handleClick = () => { const params = new URLSearchParams(location.search) }","const params = useSearchParams(); const handleClick = () => { params.get('ref') }",Medium
+19,Rerender,Memoized Components,memo extract expensive,React/Next.js,Extract expensive work into memoized components for early returns,Extract to memo() components,Compute expensive values before early return,"const UserAvatar = memo(({ user }) => ...); if (loading) return <Skeleton />","const avatar = useMemo(() => compute(user)); if (loading) return <Skeleton />",Medium
+20,Rerender,Narrow Dependencies,effect dependency primitive,React/Next.js,Specify primitive dependencies instead of objects in effects,Use primitive values in dependency arrays,Use object references as dependencies,"useEffect(() => { console.log(user.id) }, [user.id])","useEffect(() => { console.log(user.id) }, [user])",Low
+21,Rerender,Derived State,derived boolean subscription,React/Next.js,Subscribe to derived booleans instead of continuous values,Use derived boolean state,Subscribe to continuous values,"const isMobile = useMediaQuery('(max-width: 767px)')","const width = useWindowWidth(); const isMobile = width < 768",Medium
+22,Rerender,Functional setState,functional setstate callback,React/Next.js,Use functional setState updates for stable callbacks and no stale closures,Use functional form: setState(curr => ...),Reference state directly in setState,"setItems(curr => [...curr, newItem])","setItems([...items, newItem]) // items in deps",Medium
+23,Rerender,Lazy State Init,usestate lazy initialization,React/Next.js,Pass function to useState for expensive initial values,Use function form for expensive init,Compute expensive value directly,"useState(() => buildSearchIndex(items))","useState(buildSearchIndex(items)) // runs every render",Medium
+24,Rerender,Transitions,starttransition non-urgent,React/Next.js,Mark frequent non-urgent state updates as transitions,Use startTransition for non-urgent updates,Block UI on every state change,"startTransition(() => setScrollY(window.scrollY))","setScrollY(window.scrollY) // blocks on every scroll",Medium
+25,Rendering,SVG Animation Wrapper,svg animation wrapper div,React/Next.js,Wrap SVG in div and animate wrapper for hardware acceleration,Animate div wrapper around SVG,Animate SVG element directly,"<div class='animate-spin'><svg>...</svg></div>","<svg class='animate-spin'>...</svg>",Low
+26,Rendering,Content Visibility,content-visibility auto,React/Next.js,Apply content-visibility: auto to defer off-screen rendering,Use content-visibility for long lists,Render all list items immediately,".item { content-visibility: auto; contain-intrinsic-size: 0 80px }","Render 1000 items without optimization",High
+27,Rendering,Hoist Static JSX,hoist static jsx element,React/Next.js,Extract static JSX outside components to avoid re-creation,Hoist static elements to module scope,Create static elements inside components,"const skeleton = <div class='animate-pulse' />; function C() { return skeleton }","function C() { return <div class='animate-pulse' /> }",Low
+28,Rendering,Hydration No Flicker,hydration mismatch flicker,React/Next.js,Use inline script to set client-only data before hydration,Inject sync script for client-only values,Use useEffect causing flash,"<script dangerouslySetInnerHTML={{ __html: 'el.className = localStorage.theme' }} />","useEffect(() => setTheme(localStorage.theme), []) // flickers",Medium
+29,Rendering,Conditional Render,conditional render ternary,React/Next.js,Use ternary instead of && when condition can be 0 or NaN,Use explicit ternary for conditionals,Use && with potentially falsy numbers,"{count > 0 ? <Badge>{count}</Badge> : null}","{count && <Badge>{count}</Badge>} // renders '0'",Low
+30,Rendering,Activity Component,activity show hide preserve,React/Next.js,Use Activity component to preserve state/DOM for toggled components,Use Activity for expensive toggle components,Unmount/remount on visibility toggle,"<Activity mode={isOpen ? 'visible' : 'hidden'}><Menu /></Activity>","{isOpen && <Menu />} // loses state",Medium
+31,JS Perf,Batch DOM CSS,batch dom css reflow,React/Next.js,Group CSS changes via classes or cssText to minimize reflows,Use class toggle or cssText,Change styles one property at a time,"element.classList.add('highlighted')","el.style.width='100px'; el.style.height='200px'",Medium
+32,JS Perf,Index Map Lookup,map index lookup find,React/Next.js,Build Map for repeated lookups instead of multiple .find() calls,Build index Map for O(1) lookups,Use .find() in loops,"const byId = new Map(users.map(u => [u.id, u])); byId.get(id)","users.find(u => u.id === order.userId) // O(n) each time",Low-Medium
+33,JS Perf,Cache Property Access,cache property loop,React/Next.js,Cache object property lookups in hot paths,Cache values before loops,Access nested properties in loops,"const val = obj.config.settings.value; for (...) process(val)","for (...) process(obj.config.settings.value)",Low-Medium
+34,JS Perf,Cache Function Results,memoize cache function,React/Next.js,Use module-level Map to cache repeated function results,Use Map cache for repeated calls,Recompute same values repeatedly,"const cache = new Map(); if (cache.has(x)) return cache.get(x)","slugify(name) // called 100 times same input",Medium
+35,JS Perf,Cache Storage API,localstorage cache read,React/Next.js,Cache localStorage/sessionStorage reads in memory,Cache storage reads in Map,Read storage on every call,"if (!cache.has(key)) cache.set(key, localStorage.getItem(key))","localStorage.getItem('theme') // every call",Low-Medium
+36,JS Perf,Combine Iterations,combine filter map loop,React/Next.js,Combine multiple filter/map into single loop,Single loop for multiple categorizations,Chain multiple filter() calls,"for (u of users) { if (u.isAdmin) admins.push(u); if (u.isTester) testers.push(u) }","users.filter(admin); users.filter(tester); users.filter(inactive)",Low-Medium
+37,JS Perf,Length Check First,length check array compare,React/Next.js,Check array lengths before expensive comparisons,Early return if lengths differ,Always run expensive comparison,"if (a.length !== b.length) return true; // then compare","a.sort().join() !== b.sort().join() // even when lengths differ",Medium-High
+38,JS Perf,Early Return,early return exit function,React/Next.js,Return early when result is determined to skip processing,Return immediately on first error,Process all items then check errors,"for (u of users) { if (!u.email) return { error: 'Email required' } }","let hasError; for (...) { if (!email) hasError=true }; if (hasError)...",Low-Medium
+39,JS Perf,Hoist RegExp,regexp hoist module,React/Next.js,Don't create RegExp inside render - hoist or memoize,Hoist RegExp to module scope,Create RegExp every render,"const EMAIL_RE = /^[^@]+@[^@]+$/; function validate() { EMAIL_RE.test(x) }","function C() { const re = new RegExp(pattern); re.test(x) }",Low-Medium
+40,JS Perf,Loop Min Max,loop min max sort,React/Next.js,Use loop for min/max instead of sort - O(n) vs O(n log n),Single pass loop for min/max,Sort array to find min/max,"let max = arr[0]; for (x of arr) if (x > max) max = x","arr.sort((a,b) => b-a)[0] // O(n log n)",Low
+41,JS Perf,Set Map Lookups,set map includes has,React/Next.js,Use Set/Map for O(1) lookups instead of array.includes(),Convert to Set for membership checks,Use .includes() for repeated checks,"const allowed = new Set(['a','b']); allowed.has(id)","const allowed = ['a','b']; allowed.includes(id)",Low-Medium
+42,JS Perf,toSorted Immutable,tosorted sort immutable,React/Next.js,Use toSorted() instead of sort() to avoid mutating arrays,Use toSorted() for immutability,Mutate arrays with sort(),"users.toSorted((a,b) => a.name.localeCompare(b.name))","users.sort((a,b) => a.name.localeCompare(b.name)) // mutates",Medium-High
+43,Advanced,Event Handler Refs,useeffectevent ref handler,React/Next.js,Store callbacks in refs for stable effect subscriptions,Use useEffectEvent for stable handlers,Re-subscribe on every callback change,"const onEvent = useEffectEvent(handler); useEffect(() => { listen(onEvent) }, [])","useEffect(() => { listen(handler) }, [handler]) // re-subscribes",Low
+44,Advanced,useLatest Hook,uselatest ref callback,React/Next.js,Access latest values in callbacks without adding to dependency arrays,Use useLatest for fresh values in stable callbacks,Add callback to effect dependencies,"const cbRef = useLatest(cb); useEffect(() => { setTimeout(() => cbRef.current()) }, [])","useEffect(() => { setTimeout(() => cb()) }, [cb]) // re-runs",Low

.cursor/skills/ui-ux-pro-max/data/stacks/astro.csv

@@ -0,0 +1,54 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Architecture,Use Islands Architecture,Astro's partial hydration only loads JS for interactive components,Interactive components with client directives,Hydrate entire page like traditional SPA,<Counter client:load />,Everything as client component,High,https://docs.astro.build/en/concepts/islands/
+2,Architecture,Default to zero JS,Astro ships zero JS by default - add only when needed,Static components without client directive,Add client:load to everything,<Header /> (static),<Header client:load /> (unnecessary),High,https://docs.astro.build/en/basics/astro-components/
+3,Architecture,Choose right client directive,Different directives for different hydration timing,client:visible for below-fold client:idle for non-critical,client:load for everything,<Comments client:visible />,<Comments client:load />,Medium,https://docs.astro.build/en/reference/directives-reference/#client-directives
+4,Architecture,Use content collections,Type-safe content management for blogs docs,Content collections for structured content,Loose markdown files without schema,const posts = await getCollection('blog'),import.meta.glob('./posts/*.md'),High,https://docs.astro.build/en/guides/content-collections/
+5,Architecture,Define collection schemas,Zod schemas for content validation,Schema with required fields and types,No schema validation,"defineCollection({ schema: z.object({...}) })",defineCollection({}),High,https://docs.astro.build/en/guides/content-collections/#defining-a-collection-schema
+6,Routing,Use file-based routing,Create routes by adding .astro files in pages/,pages/ directory for routes,Manual route configuration,src/pages/about.astro,Custom router setup,Medium,https://docs.astro.build/en/basics/astro-pages/
+7,Routing,Dynamic routes with brackets,Use [param] for dynamic routes,Bracket notation for params,Query strings for dynamic content,pages/blog/[slug].astro,pages/blog.astro?slug=x,Medium,https://docs.astro.build/en/guides/routing/#dynamic-routes
+8,Routing,Use getStaticPaths for SSG,Generate static pages at build time,getStaticPaths for known dynamic routes,Fetch at runtime for static content,"export async function getStaticPaths() { return [...] }",No getStaticPaths with dynamic route,High,https://docs.astro.build/en/reference/api-reference/#getstaticpaths
+9,Routing,Enable SSR when needed,Server-side rendering for dynamic content,output: 'server' or 'hybrid' for dynamic,SSR for purely static sites,"export const prerender = false;",SSR for static blog,Medium,https://docs.astro.build/en/guides/server-side-rendering/
+10,Components,Keep .astro for static,Use .astro components for static content,Astro components for layout structure,React/Vue for static markup,<Layout><slot /></Layout>,<ReactLayout>{children}</ReactLayout>,High,
+11,Components,Use framework components for interactivity,React Vue Svelte for complex interactivity,Framework component with client directive,Astro component with inline scripts,<ReactCounter client:load />,<script> in .astro for complex state,Medium,https://docs.astro.build/en/guides/framework-components/
+12,Components,Pass data via props,Astro components receive props in frontmatter,Astro.props for component data,Global state for simple data,"const { title } = Astro.props;",Import global store,Low,https://docs.astro.build/en/basics/astro-components/#component-props
+13,Components,Use slots for composition,Named and default slots for flexible layouts,<slot /> for child content,Props for HTML content,<slot name="header" />,<Component header={<div>...</div>} />,Medium,https://docs.astro.build/en/basics/astro-components/#slots
+14,Components,Colocate component styles,Scoped styles in component file,<style> in same .astro file,Separate CSS files for component styles,<style> .card { } </style>,import './Card.css',Low,
+15,Styling,Use scoped styles by default,Astro scopes styles to component automatically,<style> for component-specific styles,Global styles for everything,<style> h1 { } </style> (scoped),<style is:global> for everything,Medium,https://docs.astro.build/en/guides/styling/#scoped-styles
+16,Styling,Use is:global sparingly,Global styles only when truly needed,is:global for base styles or overrides,is:global for component styles,<style is:global> body { } </style>,<style is:global> .card { } </style>,Medium,
+17,Styling,Integrate Tailwind properly,Use @astrojs/tailwind integration,Official Tailwind integration,Manual Tailwind setup,npx astro add tailwind,Manual PostCSS config,Low,https://docs.astro.build/en/guides/integrations-guide/tailwind/
+18,Styling,Use CSS variables for theming,Define tokens in :root,CSS custom properties for themes,Hardcoded colors everywhere,:root { --primary: #3b82f6; },color: #3b82f6; everywhere,Medium,
+19,Data,Fetch in frontmatter,Data fetching in component frontmatter,Top-level await in frontmatter,useEffect for initial data,const data = await fetch(url),client-side fetch on mount,High,https://docs.astro.build/en/guides/data-fetching/
+20,Data,Use Astro.glob for local files,Import multiple local files,Astro.glob for markdown/data files,Manual imports for each file,const posts = await Astro.glob('./posts/*.md'),"import post1; import post2;",Medium,
+21,Data,Prefer content collections over glob,Type-safe collections for structured content,getCollection() for blog/docs,Astro.glob for structured content,await getCollection('blog'),await Astro.glob('./blog/*.md'),High,
+22,Data,Use environment variables correctly,Import.meta.env for env vars,PUBLIC_ prefix for client vars,Expose secrets to client,import.meta.env.PUBLIC_API_URL,import.meta.env.SECRET in client,High,https://docs.astro.build/en/guides/environment-variables/
+23,Performance,Preload critical assets,Use link preload for important resources,Preload fonts above-fold images,No preload hints,"<link rel=""preload"" href=""font.woff2"" as=""font"">",No preload for critical assets,Medium,
+24,Performance,Optimize images with astro:assets,Built-in image optimization,<Image /> component for optimization,<img> for local images,"import { Image } from 'astro:assets';","<img src=""./image.jpg"">",High,https://docs.astro.build/en/guides/images/
+25,Performance,Use picture for responsive images,Multiple formats and sizes,<Picture /> for art direction,Single image size for all screens,<Picture /> with multiple sources,<Image /> with single size,Medium,
+26,Performance,Lazy load below-fold content,Defer loading non-critical content,loading=lazy for images client:visible for components,Load everything immediately,"<img loading=""lazy"">",No lazy loading,Medium,
+27,Performance,Minimize client directives,Each directive adds JS bundle,Audit client: usage regularly,Sprinkle client:load everywhere,Only interactive components hydrated,Every component with client:load,High,
+28,ViewTransitions,Enable View Transitions,Smooth page transitions,<ViewTransitions /> in head,Full page reloads,"import { ViewTransitions } from 'astro:transitions';",No transition API,Medium,https://docs.astro.build/en/guides/view-transitions/
+29,ViewTransitions,Use transition:name,Named elements for morphing,transition:name for persistent elements,Unnamed transitions,"<header transition:name=""header"">",<header> without name,Low,
+30,ViewTransitions,Handle transition:persist,Keep state across navigations,transition:persist for media players,Re-initialize on every navigation,"<video transition:persist id=""player"">",Video restarts on navigation,Medium,
+31,ViewTransitions,Add fallback for no-JS,Graceful degradation,Content works without JS,Require JS for basic navigation,Static content accessible,Broken without ViewTransitions JS,High,
+32,SEO,Use built-in SEO component,Head management for meta tags,Astro SEO integration or manual head,No meta tags,"<title>{title}</title><meta name=""description"">",No SEO tags,High,
+33,SEO,Generate sitemap,Automatic sitemap generation,@astrojs/sitemap integration,Manual sitemap maintenance,npx astro add sitemap,Hand-written sitemap.xml,Medium,https://docs.astro.build/en/guides/integrations-guide/sitemap/
+34,SEO,Add RSS feed for content,RSS for blogs and content sites,@astrojs/rss for feed generation,No RSS feed,rss() helper in pages/rss.xml.js,No feed for blog,Low,https://docs.astro.build/en/guides/rss/
+35,SEO,Use canonical URLs,Prevent duplicate content issues,Astro.url for canonical generation,"<link rel=""canonical"" href={Astro.url}>",No canonical tags,Medium,
+36,Integrations,Use official integrations,Astro's integration system,npx astro add for integrations,Manual configuration,npx astro add react,Manual React setup,Medium,https://docs.astro.build/en/guides/integrations-guide/
+37,Integrations,Configure integrations in astro.config,Centralized configuration,integrations array in config,Scattered configuration,"integrations: [react(), tailwind()]",Multiple config files,Low,
+38,Integrations,Use adapter for deployment,Platform-specific adapters,Correct adapter for host,Wrong or no adapter,@astrojs/vercel for Vercel,No adapter for SSR,High,https://docs.astro.build/en/guides/deploy/
+39,TypeScript,Enable TypeScript,Type safety for Astro projects,tsconfig.json with astro types,No TypeScript,Astro TypeScript template,JavaScript only,Medium,https://docs.astro.build/en/guides/typescript/
+40,TypeScript,Type component props,Define prop interfaces,Props interface in frontmatter,Untyped props,"interface Props { title: string }",No props typing,Medium,
+41,TypeScript,Use strict mode,Catch errors early,strict: true in tsconfig,Loose TypeScript config,strictest template,base template,Low,
+42,Markdown,Use MDX for components,Components in markdown content,@astrojs/mdx for interactive docs,Plain markdown with workarounds,<Component /> in .mdx,HTML in .md files,Medium,https://docs.astro.build/en/guides/integrations-guide/mdx/
+43,Markdown,Configure markdown plugins,Extend markdown capabilities,remarkPlugins rehypePlugins in config,Manual HTML for features,remarkPlugins: [remarkToc],Manual TOC in every post,Low,
+44,Markdown,Use frontmatter for metadata,Structured post metadata,Frontmatter with typed schema,Inline metadata,title date in frontmatter,# Title as first line,Medium,
+45,API,Use API routes for endpoints,Server endpoints in pages/api,pages/api/[endpoint].ts for APIs,External API for simple endpoints,pages/api/posts.json.ts,Separate Express server,Medium,https://docs.astro.build/en/guides/endpoints/
+46,API,Return proper responses,Use Response object,new Response() with headers,Plain objects,return new Response(JSON.stringify(data)),return data,Medium,
+47,API,Handle methods correctly,Export named method handlers,export GET POST handlers,Single default export,export const GET = async () => {},export default async () => {},Low,
+48,Security,Sanitize user content,Prevent XSS in dynamic content,set:html only for trusted content,set:html with user input,"<Fragment set:html={sanitized} />","<div set:html={userInput} />",High,
+49,Security,Use HTTPS in production,Secure connections,HTTPS for all production sites,HTTP in production,https://example.com,http://example.com,High,
+50,Security,Validate API input,Check and sanitize all input,Zod validation for API routes,Trust all input,const body = schema.parse(data),const body = await request.json(),High,
+51,Build,Use hybrid rendering,Mix static and dynamic pages,output: 'hybrid' for flexibility,All SSR or all static,prerender per-page basis,Single rendering mode,Medium,https://docs.astro.build/en/guides/server-side-rendering/#hybrid-rendering
+52,Build,Analyze bundle size,Monitor JS bundle impact,Build output shows bundle sizes,Ignore bundle growth,Check astro build output,No size monitoring,Medium,
+53,Build,Use prefetch,Preload linked pages,prefetch integration,No prefetch for navigation,npx astro add prefetch,Manual prefetch,Low,https://docs.astro.build/en/guides/prefetch/

.cursor/skills/ui-ux-pro-max/data/stacks/flutter.csv

@@ -0,0 +1,53 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Widgets,Use StatelessWidget when possible,Immutable widgets are simpler,StatelessWidget for static UI,StatefulWidget for everything,class MyWidget extends StatelessWidget,class MyWidget extends StatefulWidget (static),Medium,https://api.flutter.dev/flutter/widgets/StatelessWidget-class.html
+2,Widgets,Keep widgets small,Single responsibility principle,Extract widgets into smaller pieces,Large build methods,Column(children: [Header() Content()]),500+ line build method,Medium,
+3,Widgets,Use const constructors,Compile-time constants for performance,const MyWidget() when possible,Non-const for static widgets,const Text('Hello'),Text('Hello') for literals,High,https://dart.dev/guides/language/language-tour#constant-constructors
+4,Widgets,Prefer composition over inheritance,Combine widgets using children,Compose widgets,Extend widget classes,Container(child: MyContent()),class MyContainer extends Container,Medium,
+5,State,Use setState correctly,Minimal state in StatefulWidget,setState for UI state changes,setState for business logic,setState(() { _counter++; }),Complex logic in setState,Medium,https://api.flutter.dev/flutter/widgets/State/setState.html
+6,State,Avoid setState in build,Never call setState during build,setState in callbacks only,setState in build method,onPressed: () => setState(() {}),build() { setState(); },High,
+7,State,Use state management for complex apps,Provider Riverpod BLoC,State management for shared state,setState for global state,Provider.of<MyState>(context),Global setState calls,Medium,
+8,State,Prefer Riverpod or Provider,Recommended state solutions,Riverpod for new projects,InheritedWidget manually,ref.watch(myProvider),Custom InheritedWidget,Medium,https://riverpod.dev/
+9,State,Dispose resources,Clean up controllers and subscriptions,dispose() for cleanup,Memory leaks from subscriptions,@override void dispose() { controller.dispose(); },No dispose implementation,High,
+10,Layout,Use Column and Row,Basic layout widgets,Column Row for linear layouts,Stack for simple layouts,"Column(children: [Text(), Button()])",Stack for vertical list,Medium,https://api.flutter.dev/flutter/widgets/Column-class.html
+11,Layout,Use Expanded and Flexible,Control flex behavior,Expanded to fill space,Fixed sizes in flex containers,Expanded(child: Container()),Container(width: 200) in Row,Medium,
+12,Layout,Use SizedBox for spacing,Consistent spacing,SizedBox for gaps,Container for spacing only,SizedBox(height: 16),Container(height: 16),Low,
+13,Layout,Use LayoutBuilder for responsive,Respond to constraints,LayoutBuilder for adaptive layouts,Fixed sizes for responsive,LayoutBuilder(builder: (context constraints) {}),Container(width: 375),Medium,https://api.flutter.dev/flutter/widgets/LayoutBuilder-class.html
+14,Layout,Avoid deep nesting,Keep widget tree shallow,Extract deeply nested widgets,10+ levels of nesting,Extract widget to method or class,Column(Row(Column(Row(...)))),Medium,
+15,Lists,Use ListView.builder,Lazy list building,ListView.builder for long lists,ListView with children for large lists,"ListView.builder(itemCount: 100, itemBuilder: ...)",ListView(children: items.map(...).toList()),High,https://api.flutter.dev/flutter/widgets/ListView-class.html
+16,Lists,Provide itemExtent when known,Skip measurement,itemExtent for fixed height items,No itemExtent for uniform lists,ListView.builder(itemExtent: 50),ListView.builder without itemExtent,Medium,
+17,Lists,Use keys for stateful items,Preserve widget state,Key for stateful list items,No key for dynamic lists,ListTile(key: ValueKey(item.id)),ListTile without key,High,
+18,Lists,Use SliverList for custom scroll,Custom scroll effects,CustomScrollView with Slivers,Nested ListViews,CustomScrollView(slivers: [SliverList()]),ListView inside ListView,Medium,https://api.flutter.dev/flutter/widgets/SliverList-class.html
+19,Navigation,Use Navigator 2.0 or GoRouter,Declarative routing,go_router for navigation,Navigator.push for complex apps,GoRouter(routes: [...]),Navigator.push everywhere,Medium,https://pub.dev/packages/go_router
+20,Navigation,Use named routes,Organized navigation,Named routes for clarity,Anonymous routes,Navigator.pushNamed(context '/home'),Navigator.push(context MaterialPageRoute()),Low,
+21,Navigation,Handle back button (PopScope),Android back behavior and predictive back (Android 14+),Use PopScope widget (WillPopScope is deprecated),Use WillPopScope,"PopScope(canPop: false, onPopInvoked: (didPop) => ...)",WillPopScope(onWillPop: ...),High,https://api.flutter.dev/flutter/widgets/PopScope-class.html
+22,Navigation,Pass typed arguments,Type-safe route arguments,Typed route arguments,Dynamic arguments,MyRoute(id: '123'),arguments: {'id': '123'},Medium,
+23,Async,Use FutureBuilder,Async UI building,FutureBuilder for async data,setState for async,FutureBuilder(future: fetchData()),fetchData().then((d) => setState()),Medium,https://api.flutter.dev/flutter/widgets/FutureBuilder-class.html
+24,Async,Use StreamBuilder,Stream UI building,StreamBuilder for streams,Manual stream subscription,StreamBuilder(stream: myStream),stream.listen in initState,Medium,https://api.flutter.dev/flutter/widgets/StreamBuilder-class.html
+25,Async,Handle loading and error states,Complete async UI states,ConnectionState checks,Only success state,if (snapshot.connectionState == ConnectionState.waiting),No loading indicator,High,
+26,Async,Cancel subscriptions,Clean up stream subscriptions,Cancel in dispose,Memory leaks,subscription.cancel() in dispose,No subscription cleanup,High,
+27,Theming,Use ThemeData,Consistent theming,ThemeData for app theme,Hardcoded colors,Theme.of(context).primaryColor,Color(0xFF123456) everywhere,Medium,https://api.flutter.dev/flutter/material/ThemeData-class.html
+28,Theming,Use ColorScheme,Material 3 color system,ColorScheme for colors,Individual color properties,colorScheme: ColorScheme.fromSeed(),primaryColor: Colors.blue,Medium,
+29,Theming,Access theme via context,Dynamic theme access,Theme.of(context),Static theme reference,Theme.of(context).textTheme.bodyLarge,TextStyle(fontSize: 16),Medium,
+30,Theming,Support dark mode,Respect system theme,darkTheme in MaterialApp,Light theme only,"MaterialApp(theme: light, darkTheme: dark)",MaterialApp(theme: light),Medium,
+31,Animation,Use implicit animations,Simple animations,AnimatedContainer AnimatedOpacity,Explicit for simple transitions,AnimatedContainer(duration: Duration()),AnimationController for fade,Low,https://api.flutter.dev/flutter/widgets/AnimatedContainer-class.html
+32,Animation,Use AnimationController for complex,Fine-grained control,AnimationController with Ticker,Implicit for complex sequences,AnimationController(vsync: this),AnimatedContainer for staggered,Medium,
+33,Animation,Dispose AnimationControllers,Clean up animation resources,dispose() for controllers,Memory leaks,controller.dispose() in dispose,No controller disposal,High,
+34,Animation,Use Hero for transitions,Shared element transitions,Hero for navigation animations,Manual shared element,Hero(tag: 'image' child: Image()),Custom shared element animation,Low,https://api.flutter.dev/flutter/widgets/Hero-class.html
+35,Forms,Use Form widget,Form validation,Form with GlobalKey,Individual validation,Form(key: _formKey child: ...),TextField without Form,Medium,https://api.flutter.dev/flutter/widgets/Form-class.html
+36,Forms,Use TextEditingController,Control text input,Controller for text fields,onChanged for all text,final controller = TextEditingController(),onChanged: (v) => setState(),Medium,
+37,Forms,Validate on submit,Form validation flow,_formKey.currentState!.validate(),Skip validation,if (_formKey.currentState!.validate()),Submit without validation,High,
+38,Forms,Dispose controllers,Clean up text controllers,dispose() for controllers,Memory leaks,controller.dispose() in dispose,No controller disposal,High,
+39,Performance,Use const widgets,Reduce rebuilds,const for static widgets,No const for literals,const Icon(Icons.add),Icon(Icons.add),High,
+40,Performance,Avoid rebuilding entire tree,Minimal rebuild scope,Isolate changing widgets,setState on parent,Consumer only around changing widget,setState on root widget,High,
+41,Performance,Use RepaintBoundary,Isolate repaints,RepaintBoundary for animations,Full screen repaints,RepaintBoundary(child: AnimatedWidget()),Animation without boundary,Medium,https://api.flutter.dev/flutter/widgets/RepaintBoundary-class.html
+42,Performance,Profile with DevTools,Measure before optimizing,Flutter DevTools profiling,Guess at performance,DevTools performance tab,Optimize without measuring,Medium,https://docs.flutter.dev/tools/devtools
+43,Accessibility,Use Semantics widget,Screen reader support,Semantics for accessibility,Missing accessibility info,Semantics(label: 'Submit button'),GestureDetector without semantics,High,https://api.flutter.dev/flutter/widgets/Semantics-class.html
+44,Accessibility,Support large fonts,MediaQuery text scaling,MediaQuery.textScaleFactor,Fixed font sizes,style: Theme.of(context).textTheme,TextStyle(fontSize: 14),High,
+45,Accessibility,Test with screen readers,TalkBack and VoiceOver,Test accessibility regularly,Skip accessibility testing,Regular TalkBack testing,No screen reader testing,High,
+46,Testing,Use widget tests,Test widget behavior,WidgetTester for UI tests,Unit tests only,testWidgets('...' (tester) async {}),Only test() for UI,Medium,https://docs.flutter.dev/testing
+47,Testing,Use integration tests,Full app testing,integration_test package,Manual testing only,IntegrationTestWidgetsFlutterBinding,Manual E2E testing,Medium,
+48,Testing,Mock dependencies,Isolate tests,Mockito or mocktail,Real dependencies in tests,when(mock.method()).thenReturn(),Real API calls in tests,Medium,
+49,Platform,Use Platform checks,Platform-specific code,Platform.isIOS Platform.isAndroid,Same code for all platforms,if (Platform.isIOS) {},Hardcoded iOS behavior,Medium,
+50,Platform,Use kIsWeb for web,Web platform detection,kIsWeb for web checks,Platform for web,if (kIsWeb) {},Platform.isWeb (doesn't exist),Medium,
+51,Packages,Use pub.dev packages,Community packages,Popular maintained packages,Custom implementations,cached_network_image,Custom image cache,Medium,https://pub.dev/
+52,Packages,Check package quality,Quality before adding,Pub points and popularity,Any package without review,100+ pub points,Unmaintained packages,Medium,

.cursor/skills/ui-ux-pro-max/data/stacks/html-tailwind.csv

@@ -0,0 +1,56 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Animation,Use Tailwind animate utilities,Built-in animations are optimized and respect reduced-motion,Use animate-pulse animate-spin animate-ping,Custom @keyframes for simple effects,animate-pulse,@keyframes pulse {...},Medium,https://tailwindcss.com/docs/animation
+2,Animation,Limit bounce animations,Continuous bounce is distracting and causes motion sickness,Use animate-bounce sparingly on CTAs only,Multiple bounce animations on page,Single CTA with animate-bounce,5+ elements with animate-bounce,High,
+3,Animation,Transition duration,Use appropriate transition speeds for UI feedback,duration-150 to duration-300 for UI,duration-1000 or longer for UI elements,transition-all duration-200,transition-all duration-1000,Medium,https://tailwindcss.com/docs/transition-duration
+4,Animation,Hover transitions,Add smooth transitions on hover state changes,Add transition class with hover states,Instant hover changes without transition,hover:bg-gray-100 transition-colors,hover:bg-gray-100 (no transition),Low,
+5,Z-Index,Use Tailwind z-* scale,Consistent stacking context with predefined scale,z-0 z-10 z-20 z-30 z-40 z-50,Arbitrary z-index values,z-50 for modals,z-[9999],Medium,https://tailwindcss.com/docs/z-index
+6,Z-Index,Fixed elements z-index,Fixed navigation and modals need explicit z-index,z-50 for nav z-40 for dropdowns,Relying on DOM order for stacking,fixed top-0 z-50,fixed top-0 (no z-index),High,
+7,Z-Index,Negative z-index for backgrounds,Use negative z-index for decorative backgrounds,z-[-1] for background elements,Positive z-index for backgrounds,-z-10 for decorative,z-10 for background,Low,
+8,Layout,Container max-width,Limit content width for readability,max-w-7xl mx-auto for main content,Full-width content on large screens,max-w-7xl mx-auto px-4,w-full (no max-width),Medium,https://tailwindcss.com/docs/container
+9,Layout,Responsive padding,Adjust padding for different screen sizes,px-4 md:px-6 lg:px-8,Same padding all sizes,px-4 sm:px-6 lg:px-8,px-8 (same all sizes),Medium,
+10,Layout,Grid gaps,Use consistent gap utilities for spacing,gap-4 gap-6 gap-8,Margins on individual items,grid gap-6,grid with mb-4 on each item,Medium,https://tailwindcss.com/docs/gap
+11,Layout,Flexbox alignment,Use flex utilities for alignment,items-center justify-between,Multiple nested wrappers,flex items-center justify-between,Nested divs for alignment,Low,
+12,Images,Aspect ratio,Maintain consistent image aspect ratios,aspect-video aspect-square,No aspect ratio on containers,aspect-video rounded-lg,No aspect control,Medium,https://tailwindcss.com/docs/aspect-ratio
+13,Images,Object fit,Control image scaling within containers,object-cover object-contain,Stretched distorted images,object-cover w-full h-full,No object-fit,Medium,https://tailwindcss.com/docs/object-fit
+14,Images,Lazy loading,Defer loading of off-screen images,loading='lazy' on images,All images eager load,<img loading='lazy'>,<img> without lazy,High,
+15,Images,Responsive images,Serve appropriate image sizes,srcset and sizes attributes,Same large image all devices,srcset with multiple sizes,4000px image everywhere,High,
+16,Typography,Prose plugin,Use @tailwindcss/typography for rich text,prose prose-lg for article content,Custom styles for markdown,prose prose-lg max-w-none,Custom text styling,Medium,https://tailwindcss.com/docs/typography-plugin
+17,Typography,Line height,Use appropriate line height for readability,leading-relaxed for body text,Default tight line height,leading-relaxed (1.625),leading-none or leading-tight,Medium,https://tailwindcss.com/docs/line-height
+18,Typography,Font size scale,Use consistent text size scale,text-sm text-base text-lg text-xl,Arbitrary font sizes,text-lg,text-[17px],Low,https://tailwindcss.com/docs/font-size
+19,Typography,Text truncation,Handle long text gracefully,truncate or line-clamp-*,Overflow breaking layout,line-clamp-2,No overflow handling,Medium,https://tailwindcss.com/docs/text-overflow
+20,Colors,Opacity utilities,Use color opacity utilities,bg-black/50 text-white/80,Separate opacity class,bg-black/50,bg-black opacity-50,Low,https://tailwindcss.com/docs/background-color
+21,Colors,Dark mode,Support dark mode with dark: prefix,dark:bg-gray-900 dark:text-white,No dark mode support,dark:bg-gray-900,Only light theme,Medium,https://tailwindcss.com/docs/dark-mode
+22,Colors,Semantic colors,Use semantic color naming in config,primary secondary danger success,Generic color names in components,bg-primary,bg-blue-500 everywhere,Medium,
+23,Spacing,Consistent spacing scale,Use Tailwind spacing scale consistently,p-4 m-6 gap-8,Arbitrary pixel values,p-4 (1rem),p-[15px],Low,https://tailwindcss.com/docs/customizing-spacing
+24,Spacing,Negative margins,Use sparingly for overlapping effects,-mt-4 for overlapping elements,Negative margins for layout fixing,-mt-8 for card overlap,-m-2 to fix spacing issues,Medium,
+25,Spacing,Space between,Use space-y-* for vertical lists,space-y-4 on flex/grid column,Margin on each child,space-y-4,Each child has mb-4,Low,https://tailwindcss.com/docs/space
+26,Forms,Focus states,Always show focus indicators,focus:ring-2 focus:ring-blue-500,Remove focus outline,focus:ring-2 focus:ring-offset-2,focus:outline-none (no replacement),High,
+27,Forms,Input sizing,Consistent input dimensions,h-10 px-3 for inputs,Inconsistent input heights,h-10 w-full px-3,Various heights per input,Medium,
+28,Forms,Disabled states,Clear disabled styling,disabled:opacity-50 disabled:cursor-not-allowed,No disabled indication,disabled:opacity-50,Same style as enabled,Medium,
+29,Forms,Placeholder styling,Style placeholder text appropriately,placeholder:text-gray-400,Dark placeholder text,placeholder:text-gray-400,Default dark placeholder,Low,
+30,Responsive,Mobile-first approach,Start with mobile styles and add breakpoints,Default mobile + md: lg: xl:,Desktop-first approach,text-sm md:text-base,text-base max-md:text-sm,Medium,https://tailwindcss.com/docs/responsive-design
+31,Responsive,Breakpoint testing,Test at standard breakpoints,320 375 768 1024 1280 1536,Only test on development device,Test all breakpoints,Single device testing,High,
+32,Responsive,Hidden/shown utilities,Control visibility per breakpoint,hidden md:block,Different content per breakpoint,hidden md:flex,Separate mobile/desktop components,Low,https://tailwindcss.com/docs/display
+33,Buttons,Button sizing,Consistent button dimensions,px-4 py-2 or px-6 py-3,Inconsistent button sizes,px-4 py-2 text-sm,Various padding per button,Medium,
+34,Buttons,Touch targets,Minimum 44px touch target on mobile,min-h-[44px] on mobile,Small buttons on mobile,min-h-[44px] min-w-[44px],h-8 w-8 on mobile,High,
+35,Buttons,Loading states,Show loading feedback,disabled + spinner icon,Clickable during loading,<Button disabled><Spinner/></Button>,Button without loading state,High,
+36,Buttons,Icon buttons,Accessible icon-only buttons,aria-label on icon buttons,Icon button without label,<button aria-label='Close'><XIcon/></button>,<button><XIcon/></button>,High,
+37,Cards,Card structure,Consistent card styling,rounded-lg shadow-md p-6,Inconsistent card styles,rounded-2xl shadow-lg p-6,Mixed card styling,Low,
+38,Cards,Card hover states,Interactive cards should have hover feedback,hover:shadow-lg transition-shadow,No hover on clickable cards,hover:shadow-xl transition-shadow,Static cards that are clickable,Medium,
+39,Cards,Card spacing,Consistent internal card spacing,space-y-4 for card content,Inconsistent internal spacing,space-y-4 or p-6,Mixed mb-2 mb-4 mb-6,Low,
+40,Accessibility,Screen reader text,Provide context for screen readers,sr-only for hidden labels,Missing context for icons,<span class='sr-only'>Close menu</span>,No label for icon button,High,https://tailwindcss.com/docs/screen-readers
+41,Accessibility,Focus visible,Show focus only for keyboard users,focus-visible:ring-2,Focus on all interactions,focus-visible:ring-2,focus:ring-2 (shows on click too),Medium,
+42,Accessibility,Reduced motion,Respect user motion preferences,motion-reduce:animate-none,Ignore motion preferences,motion-reduce:transition-none,No reduced motion support,High,https://tailwindcss.com/docs/hover-focus-and-other-states#prefers-reduced-motion
+43,Performance,Configure content paths,Tailwind needs to know where classes are used,Use 'content' array in config,Use deprecated 'purge' option (v2),"content: ['./src/**/*.{js,ts,jsx,tsx}']",purge: [...],High,https://tailwindcss.com/docs/content-configuration
+44,Performance,JIT mode,Use JIT for faster builds and smaller bundles,JIT enabled (default in v3),Full CSS in development,Tailwind v3 defaults,Tailwind v2 without JIT,Medium,
+45,Performance,Avoid @apply bloat,Use @apply sparingly,Direct utilities in HTML,Heavy @apply usage,class='px-4 py-2 rounded',@apply px-4 py-2 rounded;,Low,https://tailwindcss.com/docs/reusing-styles
+46,Plugins,Official plugins,Use official Tailwind plugins,@tailwindcss/forms typography aspect-ratio,Custom implementations,@tailwindcss/forms,Custom form reset CSS,Medium,https://tailwindcss.com/docs/plugins
+47,Plugins,Custom utilities,Create utilities for repeated patterns,Custom utility in config,Repeated arbitrary values,Custom shadow utility,"shadow-[0_4px_20px_rgba(0,0,0,0.1)] everywhere",Medium,
+48,Layout,Container Queries,Use @container for component-based responsiveness,Use @container and @lg: etc.,Media queries for component internals,@container @lg:grid-cols-2,@media (min-width: ...) inside component,Medium,https://github.com/tailwindlabs/tailwindcss-container-queries
+49,Interactivity,Group and Peer,Style based on parent/sibling state,group-hover peer-checked,JS for simple state interactions,group-hover:text-blue-500,onMouseEnter={() => setHover(true)},Low,https://tailwindcss.com/docs/hover-focus-and-other-states#styling-based-on-parent-state
+50,Customization,Arbitrary Values,Use [] for one-off values,w-[350px] for specific needs,Creating config for single use,top-[117px] (if strictly needed),style={{ top: '117px' }},Low,https://tailwindcss.com/docs/adding-custom-styles#using-arbitrary-values
+51,Colors,Theme color variables,Define colors in Tailwind theme and use directly,bg-primary text-success border-cta,bg-[var(--color-primary)] text-[var(--color-success)],bg-primary,bg-[var(--color-primary)],Medium,https://tailwindcss.com/docs/customizing-colors
+52,Colors,Use bg-linear-to-* for gradients,Tailwind v4 uses bg-linear-to-* syntax for gradients,bg-linear-to-r bg-linear-to-b,bg-gradient-to-* (deprecated in v4),bg-linear-to-r from-blue-500 to-purple-500,bg-gradient-to-r from-blue-500 to-purple-500,Medium,https://tailwindcss.com/docs/background-image
+53,Layout,Use shrink-0 shorthand,Shorter class name for flex-shrink-0,shrink-0 shrink,flex-shrink-0 flex-shrink,shrink-0,flex-shrink-0,Low,https://tailwindcss.com/docs/flex-shrink
+54,Layout,Use size-* for square dimensions,Single utility for equal width and height,size-4 size-8 size-12,Separate h-* w-* for squares,size-6,h-6 w-6,Low,https://tailwindcss.com/docs/size
+55,Images,SVG explicit dimensions,Add width/height attributes to SVGs to prevent layout shift before CSS loads,<svg class='size-6' width='24' height='24'>,SVG without explicit dimensions,<svg class='size-6' width='24' height='24'>,<svg class='size-6'>,High,

.cursor/skills/ui-ux-pro-max/data/stacks/jetpack-compose.csv

@@ -0,0 +1,53 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Composable,Pure UI composables,Composable functions should only render UI,Accept state and callbacks,Calling usecase/repo,Pure UI composable,Business logic in UI,High,https://developer.android.com/jetpack/compose/mental-model
+2,Composable,Small composables,Each composable has single responsibility,Split into components,Huge composable,Reusable UI,Monolithic UI,Medium,
+3,Composable,Stateless by default,Prefer stateless composables,Hoist state,Local mutable state,Stateless UI,Hidden state,High,https://developer.android.com/jetpack/compose/state#state-hoisting
+4,State,Single source of truth,UI state comes from one source,StateFlow from VM,Multiple states,Unified UiState,Scattered state,High,https://developer.android.com/topic/architecture/ui-layer
+5,State,Model UI State,Use sealed interface/data class,UiState.Loading,Boolean flags,Explicit state,Flag hell,High,
+6,State,remember only UI state,remember for UI-only state,"Scroll, animation",Business state,Correct remember,Misuse remember,High,https://developer.android.com/jetpack/compose/state
+7,State,rememberSaveable,Persist state across config,rememberSaveable,remember,State survives,State lost,High,https://developer.android.com/jetpack/compose/state#restore-ui-state
+8,State,derivedStateOf,Optimize recomposition,derivedStateOf,Recompute always,Optimized,Jank,Medium,https://developer.android.com/jetpack/compose/performance
+9,SideEffect,LaunchedEffect keys,Use correct keys,LaunchedEffect(id),LaunchedEffect(Unit),Scoped effect,Infinite loop,High,https://developer.android.com/jetpack/compose/side-effects
+10,SideEffect,rememberUpdatedState,Avoid stale lambdas,rememberUpdatedState,Capture directly,Safe callback,Stale state,Medium,https://developer.android.com/jetpack/compose/side-effects
+11,SideEffect,DisposableEffect,Clean up resources,onDispose,No cleanup,No leak,Memory leak,High,
+12,Architecture,Unidirectional data flow,UI → VM → State,onEvent,Two-way binding,Predictable flow,Hard debug,High,https://developer.android.com/topic/architecture
+13,Architecture,No business logic in UI,Logic belongs to VM,Collect state,Call repo,Clean UI,Fat UI,High,
+14,Architecture,Expose immutable state,Expose StateFlow,asStateFlow,Mutable exposed,Safe API,State mutation,High,
+15,Lifecycle,Lifecycle-aware collect,Use collectAsStateWithLifecycle,Lifecycle aware,collectAsState,No leak,Leak,High,https://developer.android.com/jetpack/compose/lifecycle
+16,Navigation,Event-based navigation,VM emits navigation event,"VM: Channel + receiveAsFlow(), V: Collect with Dispatchers.Main.immediate",Nav in UI,Decoupled nav,Using State / SharedFlow for navigation -> event is replayed and navigation fires again (StateFlow),High,https://developer.android.com/jetpack/compose/navigation
+17,Navigation,Typed routes,Use sealed routes,sealed class Route,String routes,Type-safe,Runtime crash,Medium,
+18,Performance,Stable parameters,Prefer immutable/stable params,@Immutable,Mutable params,Stable recomposition,Extra recomposition,High,https://developer.android.com/jetpack/compose/performance
+19,Performance,Use key in Lazy,Provide stable keys,key=id,No key,Stable list,Item jump,High,
+20,Performance,Avoid heavy work,No heavy computation in UI,Precompute in VM,Compute in UI,Smooth UI,Jank,High,
+21,Performance,Remember expensive objects,remember heavy objects,remember,Recreate each recomposition,Efficient,Wasteful,Medium,
+22,Theming,Design system,Centralized theme,Material3 tokens,Hardcoded values,Consistent UI,Inconsistent,High,https://developer.android.com/jetpack/compose/themes
+23,Theming,Dark mode support,Theme-based colors,colorScheme,Fixed color,Adaptive UI,Broken dark,Medium,
+24,Layout,Prefer Modifier over extra layouts,Use Modifier to adjust layout instead of adding wrapper composables,Use Modifier.padding(),Wrap content with extra Box,Padding via modifier,Box just for padding,High,https://developer.android.com/jetpack/compose/modifiers
+25,Layout,Avoid deep layout nesting,Deep layout trees increase measure & layout cost,Keep layout flat,Box ? Column ? Box ? Row,Flat hierarchy,Deep nested tree,High,
+26,Layout,Use Row/Column for linear layout,Linear layouts are simpler and more performant,Use Row / Column,Custom layout for simple cases,Row/Column usage,Over-engineered layout,High,
+27,Layout,Use Box only for overlapping content,Box should be used only when children overlap,Stack elements,Use Box as Column,Proper overlay,Misused Box,Medium,
+28,Layout,Prefer LazyColumn over Column scroll,Lazy layouts are virtualized and efficient,LazyColumn,Column.verticalScroll(),Lazy list,Scrollable Column,High,https://developer.android.com/jetpack/compose/lists
+29,Layout,Avoid nested scroll containers,Nested scrolling causes UX & performance issues,Single scroll container,Scroll inside scroll,One scroll per screen,Nested scroll,High,
+30,Layout,Avoid fillMaxSize by default,fillMaxSize may break parent constraints,Use exact size,Fill max everywhere,Constraint-aware size,Overfilled layout,Medium,
+31,Layout,Avoid intrinsic size unless necessary,Intrinsic measurement is expensive,Explicit sizing,IntrinsicSize.Min,Predictable layout,Expensive measure,High,https://developer.android.com/jetpack/compose/layout/intrinsics
+32,Layout,Use Arrangement and Alignment APIs,Declare layout intent explicitly,Use Arrangement / Alignment,Manual spacing hacks,Declarative spacing,Magic spacing,High,
+33,Layout,Extract reusable layout patterns,Repeated layouts should be shared,Create layout composable,Copy-paste layouts,Reusable scaffold,Duplicated layout,High,
+34,Theming,No hardcoded text style,Use typography,MaterialTheme.typography,Hardcode sp,Scalable,Inconsistent,Medium,
+35,Testing,Stateless UI testing,Composable easy to test,Pass state,Hidden state,Testable,Hard test,High,https://developer.android.com/jetpack/compose/testing
+36,Testing,Use testTag,Stable UI selectors,Modifier.testTag,Find by text,Stable tests,Flaky tests,Medium,
+37,Preview,Multiple previews,Preview multiple states,@Preview,Single preview,Better dev UX,Misleading,Low,https://developer.android.com/jetpack/compose/tooling/preview
+38,DI,Inject VM via Hilt,Use hiltViewModel,@HiltViewModel,Manual VM,Clean DI,Coupling,High,https://developer.android.com/training/dependency-injection/hilt-jetpack
+39,DI,No DI in UI,Inject in VM,Constructor inject,Inject composable,Proper scope,Wrong scope,High,
+40,Accessibility,Content description,Accessible UI,contentDescription,Ignore a11y,Inclusive,A11y fail,Medium,https://developer.android.com/jetpack/compose/accessibility
+41,Accessibility,Semantics,Use semantics API,Modifier.semantics,None,Testable a11y,Invisible,Medium,
+42,Animation,Compose animation APIs,Use animate*AsState,AnimatedVisibility,Manual anim,Smooth,Jank,Medium,https://developer.android.com/jetpack/compose/animation
+43,Animation,Avoid animation logic in VM,Animation is UI concern,Animate in UI,Animate in VM,Correct layering,Mixed concern,Low,
+44,Modularization,Feature-based UI modules,UI per feature,:feature:ui,God module,Scalable,Tight coupling,High,https://developer.android.com/topic/modularization
+45,Modularization,Public UI contracts,Expose minimal UI API,Interface/Route,Expose impl,Encapsulated,Leaky module,Medium,
+46,State,Snapshot state only,Use Compose state,mutableStateOf,Custom observable,Compose aware,Buggy UI,Medium,
+47,State,Avoid mutable collections,Immutable list/map,PersistentList,MutableList,Stable UI,Silent bug,High,
+48,Lifecycle,RememberCoroutineScope usage,Only for UI jobs,UI coroutine,Long jobs,Scoped job,Leak,Medium,https://developer.android.com/jetpack/compose/side-effects#remembercoroutinescope
+49,Interop,Interop View carefully,Use AndroidView,Isolated usage,Mix everywhere,Safe interop,Messy UI,Low,https://developer.android.com/jetpack/compose/interop
+50,Interop,Avoid legacy patterns,No LiveData in UI,StateFlow,LiveData,Modern stack,Legacy debt,Medium,
+51,Debug,Use layout inspector,Inspect recomposition,Tools,Blind debug,Fast debug,Guessing,Low,https://developer.android.com/studio/debug/layout-inspector
+52,Debug,Enable recomposition counts,Track recomposition,Debug flags,Ignore,Performance aware,Hidden jank,Low,

.cursor/skills/ui-ux-pro-max/data/stacks/nextjs.csv

@@ -0,0 +1,53 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Routing,Use App Router for new projects,App Router is the recommended approach in Next.js 14+,app/ directory with page.tsx,pages/ for new projects,app/dashboard/page.tsx,pages/dashboard.tsx,Medium,https://nextjs.org/docs/app
+2,Routing,Use file-based routing,Create routes by adding files in app directory,page.tsx for routes layout.tsx for layouts,Manual route configuration,app/blog/[slug]/page.tsx,Custom router setup,Medium,https://nextjs.org/docs/app/building-your-application/routing
+3,Routing,Colocate related files,Keep components styles tests with their routes,Component files alongside page.tsx,Separate components folder,app/dashboard/_components/,components/dashboard/,Low,
+4,Routing,Use route groups for organization,Group routes without affecting URL,Parentheses for route groups,Nested folders affecting URL,(marketing)/about/page.tsx,marketing/about/page.tsx,Low,https://nextjs.org/docs/app/building-your-application/routing/route-groups
+5,Routing,Handle loading states,Use loading.tsx for route loading UI,loading.tsx alongside page.tsx,Manual loading state management,app/dashboard/loading.tsx,useState for loading in page,Medium,https://nextjs.org/docs/app/building-your-application/routing/loading-ui-and-streaming
+6,Routing,Handle errors with error.tsx,Catch errors at route level,error.tsx with reset function,try/catch in every component,app/dashboard/error.tsx,try/catch in page component,High,https://nextjs.org/docs/app/building-your-application/routing/error-handling
+7,Rendering,Use Server Components by default,Server Components reduce client JS bundle,Keep components server by default,Add 'use client' unnecessarily,export default function Page(),('use client') for static content,High,https://nextjs.org/docs/app/building-your-application/rendering/server-components
+8,Rendering,Mark Client Components explicitly,'use client' for interactive components,Add 'use client' only when needed,Server Component with hooks/events,('use client') for onClick useState,No directive with useState,High,https://nextjs.org/docs/app/building-your-application/rendering/client-components
+9,Rendering,Push Client Components down,Keep Client Components as leaf nodes,Client wrapper for interactive parts only,Mark page as Client Component,<InteractiveButton/> in Server Page,('use client') on page.tsx,High,
+10,Rendering,Use streaming for better UX,Stream content with Suspense boundaries,Suspense for slow data fetches,Wait for all data before render,<Suspense><SlowComponent/></Suspense>,await allData then render,Medium,https://nextjs.org/docs/app/building-your-application/routing/loading-ui-and-streaming
+11,Rendering,Choose correct rendering strategy,SSG for static SSR for dynamic ISR for semi-static,generateStaticParams for known paths,SSR for static content,export const revalidate = 3600,fetch without cache config,Medium,
+12,DataFetching,Fetch data in Server Components,Fetch directly in async Server Components,async function Page() { const data = await fetch() },useEffect for initial data,const data = await fetch(url),useEffect(() => fetch(url)),High,https://nextjs.org/docs/app/building-your-application/data-fetching
+13,DataFetching,Configure caching explicitly (Next.js 15+),Next.js 15 changed defaults to uncached for fetch,Explicitly set cache: 'force-cache' for static data,Assume default is cached (it's not in Next.js 15),fetch(url { cache: 'force-cache' }),fetch(url) // Uncached in v15,High,https://nextjs.org/docs/app/building-your-application/upgrading/version-15
+14,DataFetching,Deduplicate fetch requests,React and Next.js dedupe same requests,Same fetch call in multiple components,Manual request deduplication,Multiple components fetch same URL,Custom cache layer,Low,
+15,DataFetching,Use Server Actions for mutations,Server Actions for form submissions,action={serverAction} in forms,API route for every mutation,<form action={createPost}>,<form onSubmit={callApiRoute}>,Medium,https://nextjs.org/docs/app/building-your-application/data-fetching/server-actions-and-mutations
+16,DataFetching,Revalidate data appropriately,Use revalidatePath/revalidateTag after mutations,Revalidate after Server Action,'use client' with manual refetch,revalidatePath('/posts'),router.refresh() everywhere,Medium,https://nextjs.org/docs/app/building-your-application/caching#revalidating
+17,Images,Use next/image for optimization,Automatic image optimization and lazy loading,<Image> component for all images,<img> tags directly,<Image src={} alt={} width={} height={}>,<img src={}/>,High,https://nextjs.org/docs/app/building-your-application/optimizing/images
+18,Images,Provide width and height,Prevent layout shift with dimensions,width and height props or fill,Missing dimensions,<Image width={400} height={300}/>,<Image src={url}/>,High,
+19,Images,Use fill for responsive images,Fill container with object-fit,fill prop with relative parent,Fixed dimensions for responsive,"<Image fill className=""object-cover""/>",<Image width={window.width}/>,Medium,
+20,Images,Configure remote image domains,Whitelist external image sources,remotePatterns in next.config.js,Allow all domains,remotePatterns: [{ hostname: 'cdn.example.com' }],domains: ['*'],High,https://nextjs.org/docs/app/api-reference/components/image#remotepatterns
+21,Images,Use priority for LCP images,Mark above-fold images as priority,priority prop on hero images,All images with priority,<Image priority src={hero}/>,<Image priority/> on every image,Medium,
+22,Fonts,Use next/font for fonts,Self-hosted fonts with zero layout shift,next/font/google or next/font/local,External font links,import { Inter } from 'next/font/google',"<link href=""fonts.googleapis.com""/>",Medium,https://nextjs.org/docs/app/building-your-application/optimizing/fonts
+23,Fonts,Apply font to layout,Set font in root layout for consistency,className on body in layout.tsx,Font in individual pages,<body className={inter.className}>,Each page imports font,Low,
+24,Fonts,Use variable fonts,Variable fonts reduce bundle size,Single variable font file,Multiple font weights as files,Inter({ subsets: ['latin'] }),Inter_400 Inter_500 Inter_700,Low,
+25,Metadata,Use generateMetadata for dynamic,Generate metadata based on params,export async function generateMetadata(),Hardcoded metadata everywhere,generateMetadata({ params }),export const metadata = {},Medium,https://nextjs.org/docs/app/building-your-application/optimizing/metadata
+26,Metadata,Include OpenGraph images,Add OG images for social sharing,opengraph-image.tsx or og property,Missing social preview images,opengraph: { images: ['/og.png'] },No OG configuration,Medium,
+27,Metadata,Use metadata API,Export metadata object for static metadata,export const metadata = {},Manual head tags,export const metadata = { title: 'Page' },<head><title>Page</title></head>,Medium,
+28,API,Use Route Handlers for APIs,app/api routes for API endpoints,app/api/users/route.ts,pages/api for new projects,export async function GET(request),export default function handler,Medium,https://nextjs.org/docs/app/building-your-application/routing/route-handlers
+29,API,Return proper Response objects,Use NextResponse for API responses,NextResponse.json() for JSON,Plain objects or res.json(),return NextResponse.json({ data }),return { data },Medium,
+30,API,Handle HTTP methods explicitly,Export named functions for methods,Export GET POST PUT DELETE,Single handler for all methods,export async function POST(),switch(req.method),Low,
+31,API,Validate request body,Validate input before processing,Zod or similar for validation,Trust client input,const body = schema.parse(await req.json()),const body = await req.json(),High,
+32,Middleware,Use middleware for auth,Protect routes with middleware.ts,middleware.ts at root,Auth check in every page,export function middleware(request),if (!session) redirect in page,Medium,https://nextjs.org/docs/app/building-your-application/routing/middleware
+33,Middleware,Match specific paths,Configure middleware matcher,config.matcher for specific routes,Run middleware on all routes,matcher: ['/dashboard/:path*'],No matcher config,Medium,
+34,Middleware,Keep middleware edge-compatible,Middleware runs on Edge runtime,Edge-compatible code only,Node.js APIs in middleware,Edge-compatible auth check,fs.readFile in middleware,High,
+35,Environment,Use NEXT_PUBLIC prefix,Client-accessible env vars need prefix,NEXT_PUBLIC_ for client vars,Server vars exposed to client,NEXT_PUBLIC_API_URL,API_SECRET in client code,High,https://nextjs.org/docs/app/building-your-application/configuring/environment-variables
+36,Environment,Validate env vars,Check required env vars exist,Validate on startup,Undefined env at runtime,if (!process.env.DATABASE_URL) throw,process.env.DATABASE_URL (might be undefined),High,
+37,Environment,Use .env.local for secrets,Local env file for development secrets,.env.local gitignored,Secrets in .env committed,.env.local with secrets,.env with DATABASE_PASSWORD,High,
+38,Performance,Analyze bundle size,Use @next/bundle-analyzer,Bundle analyzer in dev,Ship large bundles blindly,ANALYZE=true npm run build,No bundle analysis,Medium,https://nextjs.org/docs/app/building-your-application/optimizing/bundle-analyzer
+39,Performance,Use dynamic imports,Code split with next/dynamic,dynamic() for heavy components,Import everything statically,const Chart = dynamic(() => import('./Chart')),import Chart from './Chart',Medium,https://nextjs.org/docs/app/building-your-application/optimizing/lazy-loading
+40,Performance,Avoid layout shifts,Reserve space for dynamic content,Skeleton loaders aspect ratios,Content popping in,"<Skeleton className=""h-48""/>",No placeholder for async content,High,
+41,Performance,Use Partial Prerendering,Combine static and dynamic in one route,Static shell with Suspense holes,Full dynamic or static pages,Static header + dynamic content,Entire page SSR,Low,https://nextjs.org/docs/app/building-your-application/rendering/partial-prerendering
+42,Link,Use next/link for navigation,Client-side navigation with prefetching,"<Link href=""""> for internal links",<a> for internal navigation,"<Link href=""/about"">About</Link>","<a href=""/about"">About</a>",High,https://nextjs.org/docs/app/api-reference/components/link
+43,Link,Prefetch strategically,Control prefetching behavior,prefetch={false} for low-priority,Prefetch all links,<Link prefetch={false}>,Default prefetch on every link,Low,
+44,Link,Use scroll option appropriately,Control scroll behavior on navigation,scroll={false} for tabs pagination,Always scroll to top,<Link scroll={false}>,Manual scroll management,Low,
+45,Config,Use next.config.js correctly,Configure Next.js behavior,Proper config options,Deprecated or wrong options,images: { remotePatterns: [] },images: { domains: [] },Medium,https://nextjs.org/docs/app/api-reference/next-config-js
+46,Config,Enable strict mode,Catch potential issues early,reactStrictMode: true,Strict mode disabled,reactStrictMode: true,reactStrictMode: false,Medium,
+47,Config,Configure redirects and rewrites,Use config for URL management,redirects() rewrites() in config,Manual redirect handling,redirects: async () => [...],res.redirect in pages,Medium,https://nextjs.org/docs/app/api-reference/next-config-js/redirects
+48,Deployment,Use Vercel for easiest deploy,Vercel optimized for Next.js,Deploy to Vercel,Self-host without knowledge,vercel deploy,Complex Docker setup for simple app,Low,https://nextjs.org/docs/app/building-your-application/deploying
+49,Deployment,Configure output for self-hosting,Set output option for deployment target,output: 'standalone' for Docker,Default output for containers,output: 'standalone',No output config for Docker,Medium,https://nextjs.org/docs/app/building-your-application/deploying#self-hosting
+50,Security,Sanitize user input,Never trust user input,Escape sanitize validate all input,Direct interpolation of user data,DOMPurify.sanitize(userInput),dangerouslySetInnerHTML={{ __html: userInput }},High,
+51,Security,Use CSP headers,Content Security Policy for XSS protection,Configure CSP in next.config.js,No security headers,headers() with CSP,No CSP configuration,High,https://nextjs.org/docs/app/building-your-application/configuring/content-security-policy
+52,Security,Validate Server Action input,Server Actions are public endpoints,Validate and authorize in Server Action,Trust Server Action input,Auth check + validation in action,Direct database call without check,High,

.cursor/skills/ui-ux-pro-max/data/stacks/nuxt-ui.csv

@@ -0,0 +1,51 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Installation,Add Nuxt UI module,Install and configure Nuxt UI in your Nuxt project,pnpm add @nuxt/ui and add to modules,Manual component imports,"modules: ['@nuxt/ui']","import { UButton } from '@nuxt/ui'",High,https://ui.nuxt.com/docs/getting-started/installation/nuxt
+2,Installation,Import Tailwind and Nuxt UI CSS,Required CSS imports in main.css file,@import tailwindcss and @import @nuxt/ui,Skip CSS imports,"@import ""tailwindcss""; @import ""@nuxt/ui"";",No CSS imports,High,https://ui.nuxt.com/docs/getting-started/installation/nuxt
+3,Installation,Wrap app with UApp component,UApp provides global configs for Toast Tooltip and overlays,<UApp> wrapper in app.vue,Skip UApp wrapper,<UApp><NuxtPage/></UApp>,<NuxtPage/> without wrapper,High,https://ui.nuxt.com/docs/components/app
+4,Components,Use U prefix for components,All Nuxt UI components use U prefix by default,UButton UInput UModal,Button Input Modal,<UButton>Click</UButton>,<Button>Click</Button>,Medium,https://ui.nuxt.com/docs/getting-started/installation/nuxt
+5,Components,Use semantic color props,Use semantic colors like primary secondary error,color="primary" color="error",Hardcoded colors,"<UButton color=""primary"">","<UButton class=""bg-green-500"">",Medium,https://ui.nuxt.com/docs/getting-started/theme/design-system
+6,Components,Use variant prop for styling,Nuxt UI provides solid outline soft subtle ghost link variants,variant="soft" variant="outline",Custom button classes,"<UButton variant=""soft"">","<UButton class=""border bg-transparent"">",Medium,https://ui.nuxt.com/docs/components/button
+7,Components,Use size prop consistently,Components support xs sm md lg xl sizes,size="sm" size="lg",Arbitrary sizing classes,"<UButton size=""lg"">","<UButton class=""text-xl px-6"">",Low,https://ui.nuxt.com/docs/components/button
+8,Icons,Use icon prop with Iconify format,Nuxt UI supports Iconify icons via icon prop,icon="lucide:home" icon="heroicons:user",i-lucide-home format,"<UButton icon=""lucide:home"">","<UButton icon=""i-lucide-home"">",Medium,https://ui.nuxt.com/docs/getting-started/integrations/icons/nuxt
+9,Icons,Use leadingIcon and trailingIcon,Position icons with dedicated props for clarity,leadingIcon="lucide:plus" trailingIcon="lucide:arrow-right",Manual icon positioning,"<UButton leadingIcon=""lucide:plus"">","<UButton><Icon name=""lucide:plus""/>Add</UButton>",Low,https://ui.nuxt.com/docs/components/button
+10,Theming,Configure colors in app.config.ts,Runtime color configuration without restart,ui.colors.primary in app.config.ts,Hardcoded colors in components,"defineAppConfig({ ui: { colors: { primary: 'blue' } } })","<UButton class=""bg-blue-500"">",High,https://ui.nuxt.com/docs/getting-started/theme/design-system
+11,Theming,Use @theme directive for custom colors,Define design tokens in CSS with Tailwind @theme,@theme { --color-brand-500: #xxx },Inline color definitions,@theme { --color-brand-500: #ef4444; },:style="{ color: '#ef4444' }",Medium,https://ui.nuxt.com/docs/getting-started/theme/design-system
+12,Theming,Extend semantic colors in nuxt.config,Register new colors like tertiary in theme.colors,theme.colors array in ui config,Use undefined colors,"ui: { theme: { colors: ['primary', 'tertiary'] } }","<UButton color=""tertiary""> without config",Medium,https://ui.nuxt.com/docs/getting-started/theme/design-system
+13,Forms,Use UForm with schema validation,UForm supports Zod Yup Joi Valibot schemas,:schema prop with validation schema,Manual form validation,"<UForm :schema=""schema"" :state=""state"">",Manual @blur validation,High,https://ui.nuxt.com/docs/components/form
+14,Forms,Use UFormField for field wrapper,Provides label error message and validation display,UFormField with name prop,Manual error handling,"<UFormField name=""email"" label=""Email"">",<div><label>Email</label><UInput/><span>error</span></div>,Medium,https://ui.nuxt.com/docs/components/form-field
+15,Forms,Handle form submit with @submit,UForm emits submit event with validated data,@submit handler on UForm,@click on submit button,"<UForm @submit=""onSubmit"">","<UButton @click=""onSubmit"">",Medium,https://ui.nuxt.com/docs/components/form
+16,Forms,Use validateOn prop for validation timing,Control when validation triggers (blur change input),validateOn="['blur']" for performance,Always validate on input,"<UForm :validateOn=""['blur', 'change']"">","<UForm> (validates on every keystroke)",Low,https://ui.nuxt.com/docs/components/form
+17,Overlays,Use v-model:open for overlay control,Modal Slideover Drawer use v-model:open,v-model:open for controlled state,Manual show/hide logic,"<UModal v-model:open=""isOpen"">",<UModal v-if="isOpen">,Medium,https://ui.nuxt.com/docs/components/modal
+18,Overlays,Use useOverlay composable for programmatic overlays,Open overlays programmatically without template refs,useOverlay().open(MyModal),Template ref and manual control,"const overlay = useOverlay(); overlay.open(MyModal, { props })","const modal = ref(); modal.value.open()",Medium,https://ui.nuxt.com/docs/components/modal
+19,Overlays,Use title and description props,Built-in header support for overlays,title="Confirm" description="Are you sure?",Manual header content,"<UModal title=""Confirm"" description=""Are you sure?"">","<UModal><template #header><h2>Confirm</h2></template>",Low,https://ui.nuxt.com/docs/components/modal
+20,Dashboard,Use UDashboardSidebar for navigation,Provides collapsible resizable sidebar with mobile support,UDashboardSidebar with header default footer slots,Custom sidebar implementation,<UDashboardSidebar><template #header>...</template></UDashboardSidebar>,<aside class="w-64 border-r">,Medium,https://ui.nuxt.com/docs/components/dashboard-sidebar
+21,Dashboard,Use UDashboardGroup for layout,Wraps dashboard components with sidebar state management,UDashboardGroup > UDashboardSidebar + UDashboardPanel,Manual layout flex containers,<UDashboardGroup><UDashboardSidebar/><UDashboardPanel/></UDashboardGroup>,"<div class=""flex""><aside/><main/></div>",Medium,https://ui.nuxt.com/docs/components/dashboard-group
+22,Dashboard,Use UDashboardNavbar for top navigation,Responsive navbar with mobile menu support,UDashboardNavbar in dashboard layout,Custom navbar implementation,<UDashboardNavbar :links="navLinks"/>,<nav class="border-b">,Low,https://ui.nuxt.com/docs/components/dashboard-navbar
+23,Tables,Use UTable with data and columns props,Powered by TanStack Table with built-in features,:data and :columns props,Manual table markup,"<UTable :data=""users"" :columns=""columns""/>","<table><tr v-for=""user in users"">",High,https://ui.nuxt.com/docs/components/table
+24,Tables,Define columns with accessorKey,Column definitions use accessorKey for data binding,accessorKey: 'email' in column def,String column names only,"{ accessorKey: 'email', header: 'Email' }","['name', 'email']",Medium,https://ui.nuxt.com/docs/components/table
+25,Tables,Use cell slot for custom rendering,Customize cell content with scoped slots,#cell-columnName slot,Override entire table,<template #cell-status="{ row }">,Manual column render function,Medium,https://ui.nuxt.com/docs/components/table
+26,Tables,Enable sorting with sortable column option,Add sortable: true to column definition,sortable: true in column,Manual sort implementation,"{ accessorKey: 'name', sortable: true }",@click="sortBy('name')",Low,https://ui.nuxt.com/docs/components/table
+27,Navigation,Use UNavigationMenu for nav links,Horizontal or vertical navigation with dropdown support,UNavigationMenu with items array,Manual nav with v-for,"<UNavigationMenu :items=""navItems""/>","<nav><a v-for=""item in items"">",Medium,https://ui.nuxt.com/docs/components/navigation-menu
+28,Navigation,Use UBreadcrumb for page hierarchy,Automatic breadcrumb with NuxtLink support,:items array with label and to,Manual breadcrumb links,"<UBreadcrumb :items=""breadcrumbs""/>","<nav><span v-for=""crumb in crumbs"">",Low,https://ui.nuxt.com/docs/components/breadcrumb
+29,Navigation,Use UTabs for tabbed content,Tab navigation with content panels,UTabs with items containing slot content,Manual tab state,"<UTabs :items=""tabs""/>","<div><button @click=""tab=1"">",Medium,https://ui.nuxt.com/docs/components/tabs
+30,Feedback,Use useToast for notifications,Composable for toast notifications,useToast().add({ title description }),Alert components for toasts,"const toast = useToast(); toast.add({ title: 'Saved' })",<UAlert v-if="showSuccess">,High,https://ui.nuxt.com/docs/components/toast
+31,Feedback,Use UAlert for inline messages,Static alert messages with icon and actions,UAlert with title description color,Toast for static messages,"<UAlert title=""Warning"" color=""warning""/>",useToast for inline alerts,Medium,https://ui.nuxt.com/docs/components/alert
+32,Feedback,Use USkeleton for loading states,Placeholder content during data loading,USkeleton with appropriate size,Spinner for content loading,<USkeleton class="h-4 w-32"/>,<UIcon name="lucide:loader" class="animate-spin"/>,Low,https://ui.nuxt.com/docs/components/skeleton
+33,Color Mode,Use UColorModeButton for theme toggle,Built-in light/dark mode toggle button,UColorModeButton component,Manual color mode logic,<UColorModeButton/>,"<button @click=""toggleColorMode"">",Low,https://ui.nuxt.com/docs/components/color-mode-button
+34,Color Mode,Use UColorModeSelect for theme picker,Dropdown to select system light or dark mode,UColorModeSelect component,Custom select for theme,<UColorModeSelect/>,"<USelect v-model=""colorMode"" :items=""modes""/>",Low,https://ui.nuxt.com/docs/components/color-mode-select
+35,Customization,Use ui prop for component styling,Override component styles via ui prop,ui prop with slot class overrides,Global CSS overrides,"<UButton :ui=""{ base: 'rounded-full' }""/>",<UButton class="!rounded-full"/>,Medium,https://ui.nuxt.com/docs/getting-started/theme/components
+36,Customization,Configure default variants in nuxt.config,Set default color and size for all components,theme.defaultVariants in ui config,Repeat props on every component,"ui: { theme: { defaultVariants: { color: 'neutral' } } }","<UButton color=""neutral""> everywhere",Medium,https://ui.nuxt.com/docs/getting-started/installation/nuxt
+37,Customization,Use app.config.ts for theme overrides,Runtime theme customization,defineAppConfig with ui key,nuxt.config for runtime values,"defineAppConfig({ ui: { button: { defaultVariants: { size: 'sm' } } } })","nuxt.config ui.button.size: 'sm'",Medium,https://ui.nuxt.com/docs/getting-started/theme/components
+38,Performance,Enable component detection,Tree-shake unused component CSS,experimental.componentDetection: true,Include all component CSS,"ui: { experimental: { componentDetection: true } }","ui: {} (includes all CSS)",Low,https://ui.nuxt.com/docs/getting-started/installation/nuxt
+39,Performance,Use UTable virtualize for large data,Enable virtualization for 1000+ rows,:virtualize prop on UTable,Render all rows,"<UTable :data=""largeData"" virtualize/>","<UTable :data=""largeData""/>",Medium,https://ui.nuxt.com/docs/components/table
+40,Accessibility,Use semantic component props,Components have built-in ARIA support,Use title description label props,Skip accessibility props,"<UModal title=""Settings"">","<UModal><h2>Settings</h2>",Medium,https://ui.nuxt.com/docs/components/modal
+41,Accessibility,Use UFormField for form accessibility,Automatic label-input association,UFormField wraps inputs,Manual id and for attributes,"<UFormField label=""Email""><UInput/></UFormField>","<label for=""email"">Email</label><UInput id=""email""/>",High,https://ui.nuxt.com/docs/components/form-field
+42,Content,Use UContentToc for table of contents,Automatic TOC with active heading highlight,UContentToc with :links,Manual TOC implementation,"<UContentToc :links=""toc""/>","<nav><a v-for=""heading in headings"">",Low,https://ui.nuxt.com/docs/components/content-toc
+43,Content,Use UContentSearch for docs search,Command palette for documentation search,UContentSearch with Nuxt Content,Custom search implementation,<UContentSearch/>,<UCommandPalette :groups="searchResults"/>,Low,https://ui.nuxt.com/docs/components/content-search
+44,AI/Chat,Use UChatMessages for chat UI,Designed for Vercel AI SDK integration,UChatMessages with messages array,Custom chat message list,"<UChatMessages :messages=""messages""/>","<div v-for=""msg in messages"">",Medium,https://ui.nuxt.com/docs/components/chat-messages
+45,AI/Chat,Use UChatPrompt for input,Enhanced textarea for AI prompts,UChatPrompt with v-model,Basic textarea,<UChatPrompt v-model="prompt"/>,<UTextarea v-model="prompt"/>,Medium,https://ui.nuxt.com/docs/components/chat-prompt
+46,Editor,Use UEditor for rich text,TipTap-based editor with toolbar support,UEditor with v-model:content,Custom TipTap setup,"<UEditor v-model:content=""content""/>",Manual TipTap initialization,Medium,https://ui.nuxt.com/docs/components/editor
+47,Links,Use to prop for navigation,UButton and ULink support NuxtLink to prop,to="/dashboard" for internal links,href for internal navigation,"<UButton to=""/dashboard"">","<UButton href=""/dashboard"">",Medium,https://ui.nuxt.com/docs/components/button
+48,Links,Use external prop for outside links,Explicitly mark external links,target="_blank" with external URLs,Forget rel="noopener","<UButton to=""https://example.com"" target=""_blank"">","<UButton href=""https://..."">",Low,https://ui.nuxt.com/docs/components/link
+49,Loading,Use loadingAuto on buttons,Automatic loading state from @click promise,loadingAuto prop on UButton,Manual loading state,"<UButton loadingAuto @click=""async () => await save()"">","<UButton :loading=""isLoading"" @click=""save"">",Low,https://ui.nuxt.com/docs/components/button
+50,Loading,Use UForm loadingAuto,Auto-disable form during submit,loadingAuto on UForm (default true),Manual form disabled state,"<UForm @submit=""handleSubmit"">","<UForm :disabled=""isSubmitting"">",Low,https://ui.nuxt.com/docs/components/form

.cursor/skills/ui-ux-pro-max/data/stacks/nuxtjs.csv

@@ -0,0 +1,59 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Routing,Use file-based routing,Create routes by adding files in pages directory,pages/ directory with index.vue,Manual route configuration,pages/dashboard/index.vue,Custom router setup,Medium,https://nuxt.com/docs/getting-started/routing
+2,Routing,Use dynamic route parameters,Create dynamic routes with bracket syntax,[id].vue for dynamic params,Hardcoded routes for dynamic content,pages/posts/[id].vue,pages/posts/post1.vue,Medium,https://nuxt.com/docs/getting-started/routing
+3,Routing,Use catch-all routes,Handle multiple path segments with [...slug],[...slug].vue for catch-all,Multiple nested dynamic routes,pages/[...slug].vue,pages/[a]/[b]/[c].vue,Low,https://nuxt.com/docs/getting-started/routing
+4,Routing,Define page metadata with definePageMeta,Set page-level configuration and middleware,definePageMeta for layout middleware title,Manual route meta configuration,"definePageMeta({ layout: 'admin', middleware: 'auth' })",router.beforeEach for page config,High,https://nuxt.com/docs/api/utils/define-page-meta
+5,Routing,Use validate for route params,Validate dynamic route parameters before rendering,validate function in definePageMeta,Manual validation in setup,"definePageMeta({ validate: (route) => /^\d+$/.test(route.params.id) })",if (!valid) navigateTo('/404'),Medium,https://nuxt.com/docs/api/utils/define-page-meta
+6,Rendering,Use SSR by default,Server-side rendering is enabled by default,Keep ssr: true (default),Disable SSR unnecessarily,ssr: true (default),ssr: false for all pages,High,https://nuxt.com/docs/guide/concepts/rendering
+7,Rendering,Use .client suffix for client-only components,Mark components to render only on client,ComponentName.client.vue suffix,v-if with process.client check,Comments.client.vue,<div v-if="process.client"><Comments/></div>,Medium,https://nuxt.com/docs/guide/directory-structure/components
+8,Rendering,Use .server suffix for server-only components,Mark components to render only on server,ComponentName.server.vue suffix,Manual server check,HeavyMarkdown.server.vue,v-if="process.server",Low,https://nuxt.com/docs/guide/directory-structure/components
+9,DataFetching,Use useFetch for simple data fetching,Wrapper around useAsyncData for URL fetching,useFetch for API calls,$fetch in onMounted,"const { data } = await useFetch('/api/posts')","onMounted(async () => { data.value = await $fetch('/api/posts') })",High,https://nuxt.com/docs/api/composables/use-fetch
+10,DataFetching,Use useAsyncData for complex fetching,Fine-grained control over async data,useAsyncData for CMS or custom fetching,useFetch for non-URL data sources,"const { data } = await useAsyncData('posts', () => cms.getPosts())","const { data } = await useFetch(() => cms.getPosts())",Medium,https://nuxt.com/docs/api/composables/use-async-data
+11,DataFetching,Use $fetch for non-reactive requests,$fetch for event handlers and non-component code,$fetch in event handlers or server routes,useFetch in click handlers,"async function submit() { await $fetch('/api/submit', { method: 'POST' }) }","async function submit() { await useFetch('/api/submit') }",High,https://nuxt.com/docs/api/utils/dollarfetch
+12,DataFetching,Use lazy option for non-blocking fetch,Defer data fetching for better initial load,lazy: true for below-fold content,Blocking fetch for non-critical data,"useFetch('/api/comments', { lazy: true })",await useFetch('/api/comments') for footer,Medium,https://nuxt.com/docs/api/composables/use-fetch
+13,DataFetching,Use server option to control fetch location,Choose where data is fetched,server: false for client-only data,Server fetch for user-specific client data,"useFetch('/api/user-preferences', { server: false })",useFetch for localStorage-dependent data,Medium,https://nuxt.com/docs/api/composables/use-fetch
+14,DataFetching,Use pick to reduce payload size,Select only needed fields from response,pick option for large responses,Fetching entire objects when few fields needed,"useFetch('/api/user', { pick: ['id', 'name'] })",useFetch('/api/user') then destructure,Low,https://nuxt.com/docs/api/composables/use-fetch
+15,DataFetching,Use transform for data manipulation,Transform data before storing in state,transform option for data shaping,Manual transformation after fetch,"useFetch('/api/posts', { transform: (posts) => posts.map(p => p.title) })",const titles = data.value.map(p => p.title),Low,https://nuxt.com/docs/api/composables/use-fetch
+16,DataFetching,Handle loading and error states,Always handle pending and error states,Check status pending error refs,Ignoring loading states,"<div v-if=""status === 'pending'"">Loading...</div>",No loading indicator,High,https://nuxt.com/docs/getting-started/data-fetching
+17,Lifecycle,Avoid side effects in script setup root,Move side effects to lifecycle hooks,Side effects in onMounted,setInterval in root script setup,"onMounted(() => { interval = setInterval(...) })","<script setup>setInterval(...)</script>",High,https://nuxt.com/docs/guide/concepts/nuxt-lifecycle
+18,Lifecycle,Use onMounted for DOM access,Access DOM only after component is mounted,onMounted for DOM manipulation,Direct DOM access in setup,"onMounted(() => { document.getElementById('el') })","<script setup>document.getElementById('el')</script>",High,https://nuxt.com/docs/api/composables/on-mounted
+19,Lifecycle,Use nextTick for post-render access,Wait for DOM updates before accessing elements,await nextTick() after state changes,Immediate DOM access after state change,"count.value++; await nextTick(); el.value.focus()","count.value++; el.value.focus()",Medium,https://nuxt.com/docs/api/utils/next-tick
+20,Lifecycle,Use onPrehydrate for pre-hydration logic,Run code before Nuxt hydrates the page,onPrehydrate for client setup,onMounted for hydration-critical code,"onPrehydrate(() => { console.log(window) })",onMounted for pre-hydration needs,Low,https://nuxt.com/docs/api/composables/on-prehydrate
+21,Server,Use server/api for API routes,Create API endpoints in server/api directory,server/api/users.ts for /api/users,Manual Express setup,server/api/hello.ts -> /api/hello,app.get('/api/hello'),High,https://nuxt.com/docs/guide/directory-structure/server
+22,Server,Use defineEventHandler for handlers,Define server route handlers,defineEventHandler for all handlers,export default function,"export default defineEventHandler((event) => { return { hello: 'world' } })","export default function(req, res) {}",High,https://nuxt.com/docs/guide/directory-structure/server
+23,Server,Use server/routes for non-api routes,Routes without /api prefix,server/routes for custom paths,server/api for non-api routes,server/routes/sitemap.xml.ts,server/api/sitemap.xml.ts,Medium,https://nuxt.com/docs/guide/directory-structure/server
+24,Server,Use getQuery and readBody for input,Access query params and request body,getQuery(event) readBody(event),Direct event access,"const { id } = getQuery(event)",event.node.req.query,Medium,https://nuxt.com/docs/guide/directory-structure/server
+25,Server,Validate server input,Always validate input in server handlers,Zod or similar for validation,Trust client input,"const body = await readBody(event); schema.parse(body)",const body = await readBody(event),High,https://nuxt.com/docs/guide/directory-structure/server
+26,State,Use useState for shared reactive state,SSR-friendly shared state across components,useState for cross-component state,ref for shared state,"const count = useState('count', () => 0)",const count = ref(0) in composable,High,https://nuxt.com/docs/api/composables/use-state
+27,State,Use unique keys for useState,Prevent state conflicts with unique keys,Descriptive unique keys for each state,Generic or duplicate keys,"useState('user-preferences', () => ({}))",useState('data') in multiple places,Medium,https://nuxt.com/docs/api/composables/use-state
+28,State,Use Pinia for complex state,Pinia for advanced state management,@pinia/nuxt for complex apps,Custom state management,useMainStore() with Pinia,Custom reactive store implementation,Medium,https://nuxt.com/docs/getting-started/state-management
+29,State,Use callOnce for one-time async operations,Ensure async operations run only once,callOnce for store initialization,Direct await in component,"await callOnce(store.fetch)",await store.fetch() on every render,Medium,https://nuxt.com/docs/api/utils/call-once
+30,SEO,Use useSeoMeta for SEO tags,Type-safe SEO meta tag management,useSeoMeta for meta tags,useHead for simple meta,"useSeoMeta({ title: 'Home', ogTitle: 'Home', description: '...' })","useHead({ meta: [{ name: 'description', content: '...' }] })",High,https://nuxt.com/docs/api/composables/use-seo-meta
+31,SEO,Use reactive values in useSeoMeta,Dynamic SEO tags with refs or getters,Computed getters for dynamic values,Static values for dynamic content,"useSeoMeta({ title: () => post.value.title })","useSeoMeta({ title: post.value.title })",Medium,https://nuxt.com/docs/api/composables/use-seo-meta
+32,SEO,Use useHead for non-meta head elements,Scripts styles links in head,useHead for scripts and links,useSeoMeta for scripts,"useHead({ script: [{ src: '/analytics.js' }] })","useSeoMeta({ script: '...' })",Medium,https://nuxt.com/docs/api/composables/use-head
+33,SEO,Include OpenGraph tags,Add OG tags for social sharing,ogTitle ogDescription ogImage,Missing social preview,"useSeoMeta({ ogImage: '/og.png', twitterCard: 'summary_large_image' })",No OG configuration,Medium,https://nuxt.com/docs/api/composables/use-seo-meta
+34,Middleware,Use defineNuxtRouteMiddleware,Define route middleware properly,defineNuxtRouteMiddleware wrapper,export default function,"export default defineNuxtRouteMiddleware((to, from) => {})","export default function(to, from) {}",High,https://nuxt.com/docs/guide/directory-structure/middleware
+35,Middleware,Use navigateTo for redirects,Redirect in middleware with navigateTo,return navigateTo('/login'),router.push in middleware,"if (!auth) return navigateTo('/login')","if (!auth) router.push('/login')",High,https://nuxt.com/docs/api/utils/navigate-to
+36,Middleware,Reference middleware in definePageMeta,Apply middleware to specific pages,middleware array in definePageMeta,Global middleware for page-specific,definePageMeta({ middleware: ['auth'] }),Global auth check for one page,Medium,https://nuxt.com/docs/guide/directory-structure/middleware
+37,Middleware,Use .global suffix for global middleware,Apply middleware to all routes,auth.global.ts for app-wide auth,Manual middleware on every page,middleware/auth.global.ts,middleware: ['auth'] on every page,Medium,https://nuxt.com/docs/guide/directory-structure/middleware
+38,ErrorHandling,Use createError for errors,Create errors with proper status codes,createError with statusCode,throw new Error,"throw createError({ statusCode: 404, statusMessage: 'Not Found' })",throw new Error('Not Found'),High,https://nuxt.com/docs/api/utils/create-error
+39,ErrorHandling,Use NuxtErrorBoundary for local errors,Handle errors within component subtree,NuxtErrorBoundary for component errors,Global error page for local errors,"<NuxtErrorBoundary @error=""log""><template #error=""{ error }"">",error.vue for component errors,Medium,https://nuxt.com/docs/getting-started/error-handling
+40,ErrorHandling,Use clearError to recover from errors,Clear error state and optionally redirect,clearError({ redirect: '/' }),Manual error state reset,clearError({ redirect: '/home' }),error.value = null,Medium,https://nuxt.com/docs/api/utils/clear-error
+41,ErrorHandling,Use short statusMessage,Keep statusMessage brief for security,Short generic messages,Detailed error info in statusMessage,"createError({ statusCode: 400, statusMessage: 'Bad Request' })","createError({ statusMessage: 'Invalid user ID: 123' })",High,https://nuxt.com/docs/getting-started/error-handling
+42,Link,Use NuxtLink for internal navigation,Client-side navigation with prefetching,<NuxtLink to> for internal links,<a href> for internal links,<NuxtLink to="/about">About</NuxtLink>,<a href="/about">About</a>,High,https://nuxt.com/docs/api/components/nuxt-link
+43,Link,Configure prefetch behavior,Control when prefetching occurs,prefetchOn for interaction-based,Default prefetch for low-priority,"<NuxtLink prefetch-on=""interaction"">",Always default prefetch,Low,https://nuxt.com/docs/api/components/nuxt-link
+44,Link,Use useRouter for programmatic navigation,Navigate programmatically,useRouter().push() for navigation,Direct window.location,"const router = useRouter(); router.push('/dashboard')",window.location.href = '/dashboard',Medium,https://nuxt.com/docs/api/composables/use-router
+45,Link,Use navigateTo in composables,Navigate outside components,navigateTo() in middleware or plugins,useRouter in non-component code,return navigateTo('/login'),router.push in middleware,Medium,https://nuxt.com/docs/api/utils/navigate-to
+46,AutoImports,Leverage auto-imports,Use auto-imported composables directly,Direct use of ref computed useFetch,Manual imports for Nuxt composables,"const count = ref(0)","import { ref } from 'vue'; const count = ref(0)",Medium,https://nuxt.com/docs/guide/concepts/auto-imports
+47,AutoImports,Use #imports for explicit imports,Explicit imports when needed,#imports for clarity or disabled auto-imports,"import from 'vue' when auto-import enabled","import { ref } from '#imports'","import { ref } from 'vue'",Low,https://nuxt.com/docs/guide/concepts/auto-imports
+48,AutoImports,Configure third-party auto-imports,Add external package auto-imports,imports.presets in nuxt.config,Manual imports everywhere,"imports: { presets: [{ from: 'vue-i18n', imports: ['useI18n'] }] }",import { useI18n } everywhere,Low,https://nuxt.com/docs/guide/concepts/auto-imports
+49,Plugins,Use defineNuxtPlugin,Define plugins properly,defineNuxtPlugin wrapper,export default function,"export default defineNuxtPlugin((nuxtApp) => {})","export default function(ctx) {}",High,https://nuxt.com/docs/guide/directory-structure/plugins
+50,Plugins,Use provide for injection,Provide helpers across app,return { provide: {} } for type safety,nuxtApp.provide without types,"return { provide: { hello: (name) => `Hello ${name}!` } }","nuxtApp.provide('hello', fn)",Medium,https://nuxt.com/docs/guide/directory-structure/plugins
+51,Plugins,Use .client or .server suffix,Control plugin execution environment,plugin.client.ts for client-only,if (process.client) checks,analytics.client.ts,"if (process.client) { // analytics }",Medium,https://nuxt.com/docs/guide/directory-structure/plugins
+52,Environment,Use runtimeConfig for env vars,Access environment variables safely,runtimeConfig in nuxt.config,process.env directly,"runtimeConfig: { apiSecret: '', public: { apiBase: '' } }",process.env.API_SECRET in components,High,https://nuxt.com/docs/guide/going-further/runtime-config
+53,Environment,Use NUXT_ prefix for env override,Override config with environment variables,NUXT_API_SECRET NUXT_PUBLIC_API_BASE,Custom env var names,NUXT_PUBLIC_API_BASE=https://api.example.com,API_BASE=https://api.example.com,High,https://nuxt.com/docs/guide/going-further/runtime-config
+54,Environment,Access public config with useRuntimeConfig,Get public config in components,useRuntimeConfig().public,Direct process.env access,const config = useRuntimeConfig(); config.public.apiBase,process.env.NUXT_PUBLIC_API_BASE,High,https://nuxt.com/docs/api/composables/use-runtime-config
+55,Environment,Keep secrets in private config,Server-only secrets in runtimeConfig root,runtimeConfig.apiSecret (server only),Secrets in public config,runtimeConfig: { dbPassword: '' },runtimeConfig: { public: { dbPassword: '' } },High,https://nuxt.com/docs/guide/going-further/runtime-config
+56,Performance,Use Lazy prefix for code splitting,Lazy load components with Lazy prefix,<LazyComponent> for below-fold,Eager load all components,<LazyMountainsList v-if="show"/>,<MountainsList/> for hidden content,Medium,https://nuxt.com/docs/guide/directory-structure/components
+57,Performance,Use useLazyFetch for non-blocking data,Alias for useFetch with lazy: true,useLazyFetch for secondary data,useFetch for all requests,"const { data } = useLazyFetch('/api/comments')",await useFetch for comments section,Medium,https://nuxt.com/docs/api/composables/use-lazy-fetch
+58,Performance,Use lazy hydration for interactivity,Delay component hydration until needed,LazyComponent with hydration strategy,Immediate hydration for all,<LazyModal hydrate-on-visible/>,<Modal/> in footer,Low,https://nuxt.com/docs/guide/going-further/experimental-features

.cursor/skills/ui-ux-pro-max/data/stacks/react-native.csv

@@ -0,0 +1,52 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Components,Use functional components,Hooks-based components are standard,Functional components with hooks,Class components,const App = () => { },class App extends Component,Medium,https://reactnative.dev/docs/intro-react
+2,Components,Keep components small,Single responsibility principle,Split into smaller components,Large monolithic components,<Header /><Content /><Footer />,500+ line component,Medium,
+3,Components,Use TypeScript,Type safety for props and state,TypeScript for new projects,JavaScript without types,const Button: FC<Props> = () => { },const Button = (props) => { },Medium,
+4,Components,Colocate component files,Keep related files together,Component folder with styles,Flat structure,components/Button/index.tsx styles.ts,components/Button.tsx styles/button.ts,Low,
+5,Styling,Use StyleSheet.create,Optimized style objects,StyleSheet for all styles,Inline style objects,StyleSheet.create({ container: {} }),style={{ margin: 10 }},High,https://reactnative.dev/docs/stylesheet
+6,Styling,Avoid inline styles,Prevent object recreation,Styles in StyleSheet,Inline style objects in render,style={styles.container},"style={{ margin: 10, padding: 5 }}",Medium,
+7,Styling,Use flexbox for layout,React Native uses flexbox,flexDirection alignItems justifyContent,Absolute positioning everywhere,flexDirection: 'row',position: 'absolute' everywhere,Medium,https://reactnative.dev/docs/flexbox
+8,Styling,Handle platform differences,Platform-specific styles,Platform.select or .ios/.android files,Same styles for both platforms,"Platform.select({ ios: {}, android: {} })",Hardcoded iOS values,Medium,https://reactnative.dev/docs/platform-specific-code
+9,Styling,Use responsive dimensions,Scale for different screens,Dimensions or useWindowDimensions,Fixed pixel values,useWindowDimensions(),width: 375,Medium,
+10,Navigation,Use React Navigation,Standard navigation library,React Navigation for routing,Manual navigation management,createStackNavigator(),Custom navigation state,Medium,https://reactnavigation.org/
+11,Navigation,Type navigation params,Type-safe navigation,Typed navigation props,Untyped navigation,"navigation.navigate<RootStackParamList>('Home', { id })","navigation.navigate('Home', { id })",Medium,
+12,Navigation,Use deep linking,Support URL-based navigation,Configure linking prop,No deep link support,linking: { prefixes: [] },No linking configuration,Medium,https://reactnavigation.org/docs/deep-linking/
+13,Navigation,Handle back button,Android back button handling,useFocusEffect with BackHandler,Ignore back button,BackHandler.addEventListener,No back handler,High,
+14,State,Use useState for local state,Simple component state,useState for UI state,Class component state,"const [count, setCount] = useState(0)",this.state = { count: 0 },Medium,
+15,State,Use useReducer for complex state,Complex state logic,useReducer for related state,Multiple useState for related values,useReducer(reducer initialState),5+ useState calls,Medium,
+16,State,Use context sparingly,Context for global state,Context for theme auth locale,Context for frequently changing data,ThemeContext for app theme,Context for list item data,Medium,
+17,State,Consider Zustand or Redux,External state management,Zustand for simple Redux for complex,useState for global state,create((set) => ({ })),Prop drilling global state,Medium,
+18,Lists,Use FlatList for long lists,Virtualized list rendering,FlatList for 50+ items,ScrollView with map,<FlatList data={items} />,<ScrollView>{items.map()}</ScrollView>,High,https://reactnative.dev/docs/flatlist
+19,Lists,Provide keyExtractor,Unique keys for list items,keyExtractor with stable ID,Index as key,keyExtractor={(item) => item.id},"keyExtractor={(_, index) => index}",High,
+20,Lists,Optimize renderItem,Memoize list item components,React.memo for list items,Inline render function,renderItem={({ item }) => <MemoizedItem item={item} />},renderItem={({ item }) => <View>...</View>},High,
+21,Lists,Use getItemLayout for fixed height,Skip measurement for performance,getItemLayout when height known,Dynamic measurement for fixed items,"getItemLayout={(_, index) => ({ length: 50, offset: 50 * index, index })}",No getItemLayout for fixed height,Medium,
+22,Lists,Implement windowSize,Control render window,Smaller windowSize for memory,Default windowSize for large lists,windowSize={5},windowSize={21} for huge lists,Medium,
+23,Performance,Use React.memo,Prevent unnecessary re-renders,memo for pure components,No memoization,export default memo(MyComponent),export default MyComponent,Medium,
+24,Performance,Use useCallback for handlers,Stable function references,useCallback for props,New function on every render,"useCallback(() => {}, [deps])",() => handlePress(),Medium,
+25,Performance,Use useMemo for expensive ops,Cache expensive calculations,useMemo for heavy computations,Recalculate every render,"useMemo(() => expensive(), [deps])",const result = expensive(),Medium,
+26,Performance,Avoid anonymous functions in JSX,Prevent re-renders,Named handlers or useCallback,Inline arrow functions,onPress={handlePress},onPress={() => doSomething()},Medium,
+27,Performance,Use Hermes engine,Improved startup and memory,Enable Hermes in build,JavaScriptCore for new projects,hermes_enabled: true,hermes_enabled: false,Medium,https://reactnative.dev/docs/hermes
+28,Images,Use expo-image,Modern performant image component for React Native,"Use expo-image for caching, blurring, and performance",Use default Image for heavy lists or unmaintained libraries,<Image source={url} cachePolicy='memory-disk' /> (expo-image),<FastImage source={url} />,Medium,https://docs.expo.dev/versions/latest/sdk/image/
+29,Images,Specify image dimensions,Prevent layout shifts,width and height for remote images,No dimensions for network images,<Image style={{ width: 100 height: 100 }} />,<Image source={{ uri }} /> no size,High,
+30,Images,Use resizeMode,Control image scaling,resizeMode cover contain,Stretch images,"resizeMode=""cover""",No resizeMode,Low,
+31,Forms,Use controlled inputs,State-controlled form fields,value + onChangeText,Uncontrolled inputs,<TextInput value={text} onChangeText={setText} />,<TextInput defaultValue={text} />,Medium,
+32,Forms,Handle keyboard,Manage keyboard visibility,KeyboardAvoidingView,Content hidden by keyboard,"<KeyboardAvoidingView behavior=""padding"">",No keyboard handling,High,https://reactnative.dev/docs/keyboardavoidingview
+33,Forms,Use proper keyboard types,Appropriate keyboard for input,keyboardType for input type,Default keyboard for all,"keyboardType=""email-address""","keyboardType=""default"" for email",Low,
+34,Touch,Use Pressable,Modern touch handling,Pressable for touch interactions,TouchableOpacity for new code,<Pressable onPress={} />,<TouchableOpacity onPress={} />,Low,https://reactnative.dev/docs/pressable
+35,Touch,Provide touch feedback,Visual feedback on press,Ripple or opacity change,No feedback on press,android_ripple={{ color: 'gray' }},No press feedback,Medium,
+36,Touch,Set hitSlop for small targets,Increase touch area,hitSlop for icons and small buttons,Tiny touch targets,hitSlop={{ top: 10 bottom: 10 }},44x44 with no hitSlop,Medium,
+37,Animation,Use Reanimated,High-performance animations,react-native-reanimated,Animated API for complex,useSharedValue useAnimatedStyle,Animated.timing for gesture,Medium,https://docs.swmansion.com/react-native-reanimated/
+38,Animation,Run on UI thread,worklets for smooth animation,Run animations on UI thread,JS thread animations,runOnUI(() => {}),Animated on JS thread,High,
+39,Animation,Use gesture handler,Native gesture recognition,react-native-gesture-handler,JS-based gesture handling,<GestureDetector>,<View onTouchMove={} />,Medium,https://docs.swmansion.com/react-native-gesture-handler/
+40,Async,Handle loading states,Show loading indicators,ActivityIndicator during load,Empty screen during load,{isLoading ? <ActivityIndicator /> : <Content />},No loading state,Medium,
+41,Async,Handle errors gracefully,Error boundaries and fallbacks,Error UI for failed requests,Crash on error,{error ? <ErrorView /> : <Content />},No error handling,High,
+42,Async,Cancel async operations,Cleanup on unmount,AbortController or cleanup,Memory leaks from async,useEffect cleanup,No cleanup for subscriptions,High,
+43,Accessibility,Add accessibility labels,Describe UI elements,accessibilityLabel for all interactive,Missing labels,"accessibilityLabel=""Submit form""",<Pressable> without label,High,https://reactnative.dev/docs/accessibility
+44,Accessibility,Use accessibility roles,Semantic meaning,accessibilityRole for elements,Wrong roles,"accessibilityRole=""button""",No role for button,Medium,
+45,Accessibility,Support screen readers,Test with TalkBack/VoiceOver,Test with screen readers,Skip accessibility testing,Regular TalkBack testing,No screen reader testing,High,
+46,Testing,Use React Native Testing Library,Component testing,render and fireEvent,Enzyme or manual testing,render(<Component />),shallow(<Component />),Medium,https://callstack.github.io/react-native-testing-library/
+47,Testing,Test on real devices,Real device behavior,Test on iOS and Android devices,Simulator only,Device testing in CI,Simulator only testing,High,
+48,Testing,Use Detox for E2E,End-to-end testing,Detox for critical flows,Manual E2E testing,detox test,Manual testing only,Medium,https://wix.github.io/Detox/
+49,Native,Use native modules carefully,Bridge has overhead,Batch native calls,Frequent bridge crossing,Batch updates,Call native on every keystroke,High,
+50,Native,Use Expo when possible,Simplified development,Expo for standard features,Bare RN for simple apps,expo install package,react-native link package,Low,https://docs.expo.dev/
+51,Native,Handle permissions,Request permissions properly,Check and request permissions,Assume permissions granted,PermissionsAndroid.request(),Access without permission check,High,https://reactnative.dev/docs/permissionsandroid

.cursor/skills/ui-ux-pro-max/data/stacks/react.csv

@@ -0,0 +1,54 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,State,Use useState for local state,Simple component state should use useState hook,useState for form inputs toggles counters,Class components this.state,"const [count, setCount] = useState(0)",this.state = { count: 0 },Medium,https://react.dev/reference/react/useState
+2,State,Lift state up when needed,Share state between siblings by lifting to parent,Lift shared state to common ancestor,Prop drilling through many levels,Parent holds state passes down,Deep prop chains,Medium,https://react.dev/learn/sharing-state-between-components
+3,State,Use useReducer for complex state,Complex state logic benefits from reducer pattern,useReducer for state with multiple sub-values,Multiple useState for related values,useReducer with action types,5+ useState calls that update together,Medium,https://react.dev/reference/react/useReducer
+4,State,Avoid unnecessary state,Derive values from existing state when possible,Compute derived values in render,Store derivable values in state,const total = items.reduce(...),"const [total, setTotal] = useState(0)",High,https://react.dev/learn/choosing-the-state-structure
+5,State,Initialize state lazily,Use function form for expensive initial state,useState(() => computeExpensive()),useState(computeExpensive()),useState(() => JSON.parse(data)),useState(JSON.parse(data)),Medium,https://react.dev/reference/react/useState#avoiding-recreating-the-initial-state
+6,Effects,Clean up effects,Return cleanup function for subscriptions timers,Return cleanup function in useEffect,No cleanup for subscriptions,useEffect(() => { sub(); return unsub; }),useEffect(() => { subscribe(); }),High,https://react.dev/reference/react/useEffect#connecting-to-an-external-system
+7,Effects,Specify dependencies correctly,Include all values used inside effect in deps array,All referenced values in dependency array,Empty deps with external references,[value] when using value in effect,[] when using props/state in effect,High,https://react.dev/reference/react/useEffect#specifying-reactive-dependencies
+8,Effects,Avoid unnecessary effects,Don't use effects for transforming data or events,Transform data during render handle events directly,useEffect for derived state or event handling,const filtered = items.filter(...),useEffect(() => setFiltered(items.filter(...))),High,https://react.dev/learn/you-might-not-need-an-effect
+9,Effects,Use refs for non-reactive values,Store values that don't trigger re-renders in refs,useRef for interval IDs DOM elements,useState for values that don't need render,const intervalRef = useRef(null),"const [intervalId, setIntervalId] = useState()",Medium,https://react.dev/reference/react/useRef
+10,Rendering,Use keys properly,Stable unique keys for list items,Use stable IDs as keys,Array index as key for dynamic lists,key={item.id},key={index},High,https://react.dev/learn/rendering-lists#keeping-list-items-in-order-with-key
+11,Rendering,Memoize expensive calculations,Use useMemo for costly computations,useMemo for expensive filtering/sorting,Recalculate every render,"useMemo(() => expensive(), [deps])",const result = expensiveCalc(),Medium,https://react.dev/reference/react/useMemo
+12,Rendering,Memoize callbacks passed to children,Use useCallback for functions passed as props,useCallback for handlers passed to memoized children,New function reference every render,"useCallback(() => {}, [deps])",const handler = () => {},Medium,https://react.dev/reference/react/useCallback
+13,Rendering,Use React.memo wisely,Wrap components that render often with same props,memo for pure components with stable props,memo everything or nothing,memo(ExpensiveList),memo(SimpleButton),Low,https://react.dev/reference/react/memo
+14,Rendering,Avoid inline object/array creation in JSX,Create objects outside render or memoize,Define style objects outside component,Inline objects in props,<div style={styles.container}>,<div style={{ margin: 10 }}>,Medium,
+15,Components,Keep components small and focused,Single responsibility for each component,One concern per component,Large multi-purpose components,<UserAvatar /><UserName />,<UserCard /> with 500 lines,Medium,
+16,Components,Use composition over inheritance,Compose components using children and props,Use children prop for flexibility,Inheritance hierarchies,<Card>{content}</Card>,class SpecialCard extends Card,Medium,https://react.dev/learn/thinking-in-react
+17,Components,Colocate related code,Keep related components and hooks together,Related files in same directory,Flat structure with many files,components/User/UserCard.tsx,components/UserCard.tsx + hooks/useUser.ts,Low,
+18,Components,Use fragments to avoid extra DOM,Fragment or <> for multiple elements without wrapper,<> for grouping without DOM node,Extra div wrappers,<>{items.map(...)}</>,<div>{items.map(...)}</div>,Low,https://react.dev/reference/react/Fragment
+19,Props,Destructure props,Destructure props for cleaner component code,Destructure in function signature,props.name props.value throughout,"function User({ name, age })",function User(props),Low,
+20,Props,Provide default props values,Use default parameters or defaultProps,Default values in destructuring,Undefined checks throughout,function Button({ size = 'md' }),if (size === undefined) size = 'md',Low,
+21,Props,Avoid prop drilling,Use context or composition for deeply nested data,Context for global data composition for UI,Passing props through 5+ levels,<UserContext.Provider>,<A user={u}><B user={u}><C user={u}>,Medium,https://react.dev/learn/passing-data-deeply-with-context
+22,Props,Validate props with TypeScript,Use TypeScript interfaces for prop types,interface Props { name: string },PropTypes or no validation,interface ButtonProps { onClick: () => void },Button.propTypes = {},Medium,
+23,Events,Use synthetic events correctly,React normalizes events across browsers,e.preventDefault() e.stopPropagation(),Access native event unnecessarily,onClick={(e) => e.preventDefault()},onClick={(e) => e.nativeEvent.preventDefault()},Low,https://react.dev/reference/react-dom/components/common#react-event-object
+24,Events,Avoid binding in render,Use arrow functions in class or hooks,Arrow functions in functional components,bind in render or constructor,const handleClick = () => {},this.handleClick.bind(this),Medium,
+25,Events,Pass event handlers not call results,Pass function reference not invocation,onClick={handleClick},onClick={handleClick()} causing immediate call,onClick={handleClick},onClick={handleClick()},High,
+26,Forms,Controlled components for forms,Use state to control form inputs,value + onChange for inputs,Uncontrolled inputs with refs,<input value={val} onChange={setVal}>,<input ref={inputRef}>,Medium,https://react.dev/reference/react-dom/components/input#controlling-an-input-with-a-state-variable
+27,Forms,Handle form submission properly,Prevent default and handle in submit handler,onSubmit with preventDefault,onClick on submit button only,<form onSubmit={handleSubmit}>,<button onClick={handleSubmit}>,Medium,
+28,Forms,Debounce rapid input changes,Debounce search/filter inputs,useDeferredValue or debounce for search,Filter on every keystroke,useDeferredValue(searchTerm),useEffect filtering on every change,Medium,https://react.dev/reference/react/useDeferredValue
+29,Hooks,Follow rules of hooks,Only call hooks at top level and in React functions,Hooks at component top level,Hooks in conditions loops or callbacks,"const [x, setX] = useState()","if (cond) { const [x, setX] = useState() }",High,https://react.dev/reference/rules/rules-of-hooks
+30,Hooks,Custom hooks for reusable logic,Extract shared stateful logic to custom hooks,useCustomHook for reusable patterns,Duplicate hook logic across components,const { data } = useFetch(url),Duplicate useEffect/useState in components,Medium,https://react.dev/learn/reusing-logic-with-custom-hooks
+31,Hooks,Name custom hooks with use prefix,Custom hooks must start with use,useFetch useForm useAuth,fetchData or getData for hook,function useFetch(url),function fetchData(url),High,
+32,Context,Use context for global data,Context for theme auth locale,Context for app-wide state,Context for frequently changing data,<ThemeContext.Provider>,Context for form field values,Medium,https://react.dev/learn/passing-data-deeply-with-context
+33,Context,Split contexts by concern,Separate contexts for different domains,ThemeContext + AuthContext,One giant AppContext,<ThemeProvider><AuthProvider>,<AppProvider value={{theme user...}}>,Medium,
+34,Context,Memoize context values,Prevent unnecessary re-renders with useMemo,useMemo for context value object,New object reference every render,"value={useMemo(() => ({...}), [])}","value={{ user, theme }}",High,
+35,Performance,Use React DevTools Profiler,Profile to identify performance bottlenecks,Profile before optimizing,Optimize without measuring,React DevTools Profiler,Guessing at bottlenecks,Medium,https://react.dev/learn/react-developer-tools
+36,Performance,Lazy load components,Use React.lazy for code splitting,lazy() for routes and heavy components,Import everything upfront,const Page = lazy(() => import('./Page')),import Page from './Page',Medium,https://react.dev/reference/react/lazy
+37,Performance,Virtualize long lists,Use windowing for lists over 100 items,react-window or react-virtual,Render thousands of DOM nodes,<VirtualizedList items={items}/>,{items.map(i => <Item />)},High,
+38,Performance,Batch state updates,React 18 auto-batches but be aware,Let React batch related updates,Manual batching with flushSync,setA(1); setB(2); // batched,flushSync(() => setA(1)),Low,https://react.dev/learn/queueing-a-series-of-state-updates
+39,ErrorHandling,Use error boundaries,Catch JavaScript errors in component tree,ErrorBoundary wrapping sections,Let errors crash entire app,<ErrorBoundary><App/></ErrorBoundary>,No error handling,High,https://react.dev/reference/react/Component#catching-rendering-errors-with-an-error-boundary
+40,ErrorHandling,Handle async errors,Catch errors in async operations,try/catch in async handlers,Unhandled promise rejections,try { await fetch() } catch(e) {},await fetch() // no catch,High,
+41,Testing,Test behavior not implementation,Test what user sees and does,Test renders and interactions,Test internal state or methods,expect(screen.getByText('Hello')),expect(component.state.name),Medium,https://testing-library.com/docs/react-testing-library/intro/
+42,Testing,Use testing-library queries,Use accessible queries,getByRole getByLabelText,getByTestId for everything,getByRole('button'),getByTestId('submit-btn'),Medium,https://testing-library.com/docs/queries/about#priority
+43,Accessibility,Use semantic HTML,Proper HTML elements for their purpose,button for clicks nav for navigation,div with onClick for buttons,<button onClick={...}>,<div onClick={...}>,High,https://react.dev/reference/react-dom/components#all-html-components
+44,Accessibility,Manage focus properly,Handle focus for modals dialogs,Focus trap in modals return focus on close,No focus management,useEffect to focus input,Modal without focus trap,High,
+45,Accessibility,Announce dynamic content,Use ARIA live regions for updates,aria-live for dynamic updates,Silent updates to screen readers,"<div aria-live=""polite"">{msg}</div>",<div>{msg}</div>,Medium,
+46,Accessibility,Label form controls,Associate labels with inputs,htmlFor matching input id,Placeholder as only label,"<label htmlFor=""email"">Email</label>","<input placeholder=""Email""/>",High,
+47,TypeScript,Type component props,Define interfaces for all props,interface Props with all prop types,any or missing types,interface Props { name: string },function Component(props: any),High,
+48,TypeScript,Type state properly,Provide types for useState,useState<Type>() for complex state,Inferred any types,useState<User | null>(null),useState(null),Medium,
+49,TypeScript,Type event handlers,Use React event types,React.ChangeEvent<HTMLInputElement>,Generic Event type,onChange: React.ChangeEvent<HTMLInputElement>,onChange: Event,Medium,
+50,TypeScript,Use generics for reusable components,Generic components for flexible typing,Generic props for list components,Union types for flexibility,<List<T> items={T[]}>,<List items={any[]}>,Medium,
+51,Patterns,Container/Presentational split,Separate data logic from UI,Container fetches presentational renders,Mixed data and UI in one,<UserContainer><UserView/></UserContainer>,<User /> with fetch and render,Low,
+52,Patterns,Render props for flexibility,Share code via render prop pattern,Render prop for customizable rendering,Duplicate logic across components,<DataFetcher render={data => ...}/>,Copy paste fetch logic,Low,https://react.dev/reference/react/cloneElement#passing-data-with-a-render-prop
+53,Patterns,Compound components,Related components sharing state,Tab + TabPanel sharing context,Prop drilling between related,<Tabs><Tab/><TabPanel/></Tabs>,<Tabs tabs={[]} panels={[...]}/>,Low,

.cursor/skills/ui-ux-pro-max/data/stacks/shadcn.csv

@@ -0,0 +1,61 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Setup,Use CLI for installation,Install components via shadcn CLI for proper setup,npx shadcn@latest add component-name,Manual copy-paste from docs,npx shadcn@latest add button,Copy component code manually,High,https://ui.shadcn.com/docs/cli
+2,Setup,Initialize project properly,Run init command to set up components.json and globals.css,npx shadcn@latest init before adding components,Skip init and add components directly,npx shadcn@latest init,npx shadcn@latest add button (without init),High,https://ui.shadcn.com/docs/installation
+3,Setup,Configure path aliases,Set up proper import aliases in tsconfig and components.json,Use @/components/ui path aliases,Relative imports like ../../components,import { Button } from "@/components/ui/button",import { Button } from "../../components/ui/button",Medium,https://ui.shadcn.com/docs/installation
+4,Theming,Use CSS variables for colors,Define colors as CSS variables in globals.css for theming,CSS variables in :root and .dark,Hardcoded color values in components,bg-primary text-primary-foreground,bg-blue-500 text-white,High,https://ui.shadcn.com/docs/theming
+5,Theming,Follow naming convention,Use semantic color names with foreground pattern,primary/primary-foreground secondary/secondary-foreground,Generic color names,--primary --primary-foreground,--blue --light-blue,Medium,https://ui.shadcn.com/docs/theming
+6,Theming,Support dark mode,Include .dark class styles for all custom CSS,Define both :root and .dark color schemes,Only light mode colors,.dark { --background: 240 10% 3.9%; },No .dark class styles,High,https://ui.shadcn.com/docs/dark-mode
+7,Components,Use component variants,Leverage cva variants for consistent styling,Use variant prop for different styles,Inline conditional classes,<Button variant="destructive">,<Button className={isError ? "bg-red-500" : "bg-blue-500"}>,Medium,https://ui.shadcn.com/docs/components/button
+8,Components,Compose with className,Add custom classes via className prop for overrides,Extend with className for one-off customizations,Modify component source directly,<Button className="w-full">,Edit button.tsx to add w-full,Medium,https://ui.shadcn.com/docs/components/button
+9,Components,Use size variants consistently,Apply size prop for consistent sizing across components,size="sm" size="lg" for sizing,Mix size classes inconsistently,<Button size="lg">,<Button className="text-lg px-8 py-4">,Medium,https://ui.shadcn.com/docs/components/button
+10,Components,Prefer compound components,Use provided sub-components for complex UI,Card + CardHeader + CardContent pattern,Single component with many props,<Card><CardHeader><CardTitle>,<Card title="x" content="y" footer="z">,Medium,https://ui.shadcn.com/docs/components/card
+11,Dialog,Use Dialog for modal content,Dialog component for overlay modal windows,Dialog for confirmations forms details,Alert for modal content,<Dialog><DialogContent>,<Alert> styled as modal,High,https://ui.shadcn.com/docs/components/dialog
+12,Dialog,Handle dialog state properly,Use open and onOpenChange for controlled dialogs,Controlled state with useState,Uncontrolled with default open only,"<Dialog open={open} onOpenChange={setOpen}>","<Dialog defaultOpen={true}>",Medium,https://ui.shadcn.com/docs/components/dialog
+13,Dialog,Include proper dialog structure,Use DialogHeader DialogTitle DialogDescription,Complete semantic structure,Missing title or description,<DialogHeader><DialogTitle><DialogDescription>,<DialogContent><p>Content</p></DialogContent>,High,https://ui.shadcn.com/docs/components/dialog
+14,Sheet,Use Sheet for side panels,Sheet component for slide-out panels and drawers,Sheet for navigation filters settings,Dialog for side content,<Sheet side="right">,<Dialog> with slide animation,Medium,https://ui.shadcn.com/docs/components/sheet
+15,Sheet,Specify sheet side,Set side prop for sheet slide direction,Explicit side="left" or side="right",Default side without consideration,<Sheet><SheetContent side="left">,<Sheet><SheetContent>,Low,https://ui.shadcn.com/docs/components/sheet
+16,Form,Use Form with react-hook-form,Integrate Form component with react-hook-form for validation,useForm + Form + FormField pattern,Custom form handling without Form,<Form {...form}><FormField control={form.control}>,<form onSubmit={handleSubmit}>,High,https://ui.shadcn.com/docs/components/form
+17,Form,Use FormField for inputs,Wrap inputs in FormField for proper labeling and errors,FormField + FormItem + FormLabel + FormControl,Input without FormField wrapper,<FormField><FormItem><FormLabel><FormControl><Input>,<Input onChange={...}>,High,https://ui.shadcn.com/docs/components/form
+18,Form,Display form messages,Use FormMessage for validation error display,FormMessage after FormControl,Custom error text without FormMessage,<FormControl><Input/></FormControl><FormMessage/>,<Input/>{error && <span>{error}</span>},Medium,https://ui.shadcn.com/docs/components/form
+19,Form,Use Zod for validation,Define form schema with Zod for type-safe validation,zodResolver with form schema,Manual validation logic,zodResolver(formSchema),validate: (values) => { if (!values.email) },Medium,https://ui.shadcn.com/docs/components/form
+20,Select,Use Select for dropdowns,Select component for option selection,Select for choosing from list,Native select element,<Select><SelectTrigger><SelectContent>,<select><option>,Medium,https://ui.shadcn.com/docs/components/select
+21,Select,Structure Select properly,Include Trigger Value Content and Items,Complete Select structure,Missing SelectValue or SelectContent,<SelectTrigger><SelectValue/></SelectTrigger><SelectContent><SelectItem>,<Select><option>,High,https://ui.shadcn.com/docs/components/select
+22,Command,Use Command for search,Command component for searchable lists and palettes,Command for command palette search,Input with custom dropdown,<Command><CommandInput><CommandList>,<Input><div className="dropdown">,Medium,https://ui.shadcn.com/docs/components/command
+23,Command,Group command items,Use CommandGroup for categorized items,CommandGroup with heading for sections,Flat list without grouping,<CommandGroup heading="Suggestions"><CommandItem>,<CommandItem> without groups,Low,https://ui.shadcn.com/docs/components/command
+24,Table,Use Table for data display,Table component for structured data,Table for tabular data display,Div grid for table-like layouts,<Table><TableHeader><TableBody><TableRow>,<div className="grid">,Medium,https://ui.shadcn.com/docs/components/table
+25,Table,Include proper table structure,Use TableHeader TableBody TableRow TableCell,Semantic table structure,Missing thead or tbody,<TableHeader><TableRow><TableHead>,<Table><TableRow> without header,High,https://ui.shadcn.com/docs/components/table
+26,DataTable,Use DataTable for complex tables,Combine Table with TanStack Table for features,DataTable pattern for sorting filtering pagination,Custom table implementation,useReactTable + Table components,Custom sort filter pagination logic,Medium,https://ui.shadcn.com/docs/components/data-table
+27,Tabs,Use Tabs for content switching,Tabs component for tabbed interfaces,Tabs for related content sections,Custom tab implementation,<Tabs><TabsList><TabsTrigger><TabsContent>,<div onClick={() => setTab(...)},Medium,https://ui.shadcn.com/docs/components/tabs
+28,Tabs,Set default tab value,Specify defaultValue for initial tab,defaultValue on Tabs component,No default leaving first tab,<Tabs defaultValue="account">,<Tabs> without defaultValue,Low,https://ui.shadcn.com/docs/components/tabs
+29,Accordion,Use Accordion for collapsible,Accordion for expandable content sections,Accordion for FAQ settings panels,Custom collapse implementation,<Accordion><AccordionItem><AccordionTrigger>,<div onClick={() => setOpen(!open)}>,Medium,https://ui.shadcn.com/docs/components/accordion
+30,Accordion,Choose accordion type,Use type="single" or type="multiple" appropriately,type="single" for one open type="multiple" for many,Default type without consideration,<Accordion type="single" collapsible>,<Accordion> without type,Low,https://ui.shadcn.com/docs/components/accordion
+31,Toast,Use Sonner for toasts,Sonner integration for toast notifications,toast() from sonner for notifications,Custom toast implementation,toast("Event created"),setShowToast(true),Medium,https://ui.shadcn.com/docs/components/sonner
+32,Toast,Add Toaster to layout,Include Toaster component in root layout,<Toaster /> in app layout,Toaster in individual pages,app/layout.tsx: <Toaster />,page.tsx: <Toaster />,High,https://ui.shadcn.com/docs/components/sonner
+33,Toast,Use toast variants,Apply toast.success toast.error for context,Semantic toast methods,Generic toast for all messages,toast.success("Saved!") toast.error("Failed"),toast("Saved!") toast("Failed"),Medium,https://ui.shadcn.com/docs/components/sonner
+34,Popover,Use Popover for floating content,Popover for dropdown menus and floating panels,Popover for contextual actions,Absolute positioned divs,<Popover><PopoverTrigger><PopoverContent>,<div className="relative"><div className="absolute">,Medium,https://ui.shadcn.com/docs/components/popover
+35,Popover,Handle popover alignment,Use align and side props for positioning,Explicit alignment configuration,Default alignment for all,<PopoverContent align="start" side="bottom">,<PopoverContent>,Low,https://ui.shadcn.com/docs/components/popover
+36,DropdownMenu,Use DropdownMenu for actions,DropdownMenu for action lists and context menus,DropdownMenu for user menu actions,Popover for action lists,<DropdownMenu><DropdownMenuTrigger><DropdownMenuContent>,<Popover> for menu actions,Medium,https://ui.shadcn.com/docs/components/dropdown-menu
+37,DropdownMenu,Group menu items,Use DropdownMenuGroup and DropdownMenuSeparator,Organized menu with separators,Flat list of items,<DropdownMenuGroup><DropdownMenuItem><DropdownMenuSeparator>,<DropdownMenuItem> without organization,Low,https://ui.shadcn.com/docs/components/dropdown-menu
+38,Tooltip,Use Tooltip for hints,Tooltip for icon buttons and truncated text,Tooltip for additional context,Title attribute for tooltips,<Tooltip><TooltipTrigger><TooltipContent>,<button title="Delete">,Medium,https://ui.shadcn.com/docs/components/tooltip
+39,Tooltip,Add TooltipProvider,Wrap app or section in TooltipProvider,TooltipProvider at app level,TooltipProvider per tooltip,<TooltipProvider><App/></TooltipProvider>,<Tooltip><TooltipProvider>,High,https://ui.shadcn.com/docs/components/tooltip
+40,Skeleton,Use Skeleton for loading,Skeleton component for loading placeholders,Skeleton matching content layout,Spinner for content loading,<Skeleton className="h-4 w-[200px]"/>,<Spinner/> for card loading,Medium,https://ui.shadcn.com/docs/components/skeleton
+41,Skeleton,Match skeleton dimensions,Size skeleton to match loaded content,Skeleton same size as expected content,Generic skeleton size,<Skeleton className="h-12 w-12 rounded-full"/>,<Skeleton/> without sizing,Medium,https://ui.shadcn.com/docs/components/skeleton
+42,AlertDialog,Use AlertDialog for confirms,AlertDialog for destructive action confirmation,AlertDialog for delete confirmations,Dialog for confirmations,<AlertDialog><AlertDialogTrigger><AlertDialogContent>,<Dialog> for delete confirmation,High,https://ui.shadcn.com/docs/components/alert-dialog
+43,AlertDialog,Include action buttons,Use AlertDialogAction and AlertDialogCancel,Standard confirm/cancel pattern,Custom buttons in AlertDialog,<AlertDialogCancel>Cancel</AlertDialogCancel><AlertDialogAction>,<Button>Cancel</Button><Button>Confirm</Button>,Medium,https://ui.shadcn.com/docs/components/alert-dialog
+44,Sidebar,Use Sidebar for navigation,Sidebar component for app navigation,Sidebar for main app navigation,Custom sidebar implementation,<SidebarProvider><Sidebar><SidebarContent>,<div className="w-64 fixed">,Medium,https://ui.shadcn.com/docs/components/sidebar
+45,Sidebar,Wrap in SidebarProvider,Use SidebarProvider for sidebar state management,SidebarProvider at layout level,Sidebar without provider,<SidebarProvider><Sidebar></SidebarProvider>,<Sidebar> without provider,High,https://ui.shadcn.com/docs/components/sidebar
+46,Sidebar,Use SidebarTrigger,Include SidebarTrigger for mobile toggle,SidebarTrigger for responsive toggle,Custom toggle button,<SidebarTrigger/>,<Button onClick={() => toggleSidebar()}>,Medium,https://ui.shadcn.com/docs/components/sidebar
+47,Chart,Use Chart for data viz,Chart component with Recharts integration,Chart component for dashboards,Direct Recharts without wrapper,<ChartContainer config={chartConfig}>,<ResponsiveContainer><BarChart>,Medium,https://ui.shadcn.com/docs/components/chart
+48,Chart,Define chart config,Create chartConfig for consistent theming,chartConfig with color definitions,Inline colors in charts,"{ desktop: { label: ""Desktop"", color: ""#2563eb"" } }",<Bar fill="#2563eb"/>,Medium,https://ui.shadcn.com/docs/components/chart
+49,Chart,Use ChartTooltip,Apply ChartTooltip for interactive charts,ChartTooltip with ChartTooltipContent,Recharts Tooltip directly,<ChartTooltip content={<ChartTooltipContent/>}/>,<Tooltip/> from recharts,Low,https://ui.shadcn.com/docs/components/chart
+50,Blocks,Use blocks for scaffolding,Start from shadcn blocks for common layouts,npx shadcn@latest add dashboard-01,Build dashboard from scratch,npx shadcn@latest add login-01,Custom login page from scratch,Medium,https://ui.shadcn.com/blocks
+51,Blocks,Customize block components,Modify copied block code to fit needs,Edit block files after installation,Use blocks without modification,Customize dashboard-01 layout,Use dashboard-01 as-is,Low,https://ui.shadcn.com/blocks
+52,A11y,Use semantic components,Shadcn components have built-in ARIA,Rely on component accessibility,Override ARIA attributes,<Button> has button role,<div role="button">,High,https://ui.shadcn.com/docs/components/button
+53,A11y,Maintain focus management,Dialog Sheet handle focus automatically,Let components manage focus,Custom focus handling,<Dialog> traps focus,document.querySelector().focus(),High,https://ui.shadcn.com/docs/components/dialog
+54,A11y,Provide labels,Use FormLabel and aria-label appropriately,FormLabel for form inputs,Placeholder as only label,<FormLabel>Email</FormLabel><Input/>,<Input placeholder="Email"/>,High,https://ui.shadcn.com/docs/components/form
+55,Performance,Import components individually,Import only needed components,Named imports from component files,Import all from index,import { Button } from "@/components/ui/button",import { Button Card Dialog } from "@/components/ui",Medium,
+56,Performance,Lazy load dialogs,Dynamic import for heavy dialog content,React.lazy for dialog content,Import all dialogs upfront,const HeavyContent = lazy(() => import('./Heavy')),import HeavyContent from './Heavy',Medium,
+57,Customization,Extend variants with cva,Add new variants using class-variance-authority,Extend buttonVariants for new styles,Inline classes for variants,"variants: { size: { xl: ""h-14 px-8"" } }",className="h-14 px-8",Medium,https://ui.shadcn.com/docs/components/button
+58,Customization,Create custom components,Build new components following shadcn patterns,Use cn() and cva for custom components,Different patterns for custom,const Custom = ({ className }) => <div className={cn("base" className)}>,const Custom = ({ style }) => <div style={style}>,Medium,
+59,Patterns,Use asChild for composition,asChild prop for component composition,Slot pattern with asChild,Wrapper divs for composition,<Button asChild><Link href="/">,<Button><Link href="/"></Link></Button>,Medium,https://ui.shadcn.com/docs/components/button
+60,Patterns,Combine with React Hook Form,Form + useForm for complete forms,RHF Controller with shadcn inputs,Custom form state management,<FormField control={form.control} name="email">,<Input value={email} onChange={(e) => setEmail(e.target.value)},High,https://ui.shadcn.com/docs/components/form

.cursor/skills/ui-ux-pro-max/data/stacks/svelte.csv

@@ -0,0 +1,54 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Reactivity,Use $: for reactive statements,Automatic dependency tracking,$: for derived values,Manual recalculation,$: doubled = count * 2,let doubled; count && (doubled = count * 2),Medium,https://svelte.dev/docs/svelte-components#script-3-$-marks-a-statement-as-reactive
+2,Reactivity,Trigger reactivity with assignment,Svelte tracks assignments not mutations,Reassign arrays/objects to trigger update,Mutate without reassignment,"items = [...items, newItem]",items.push(newItem),High,https://svelte.dev/docs/svelte-components#script-2-assignments-are-reactive
+3,Reactivity,Use $state in Svelte 5,Runes for explicit reactivity,let count = $state(0),Implicit reactivity in Svelte 5,let count = $state(0),let count = 0 (Svelte 5),Medium,https://svelte.dev/blog/runes
+4,Reactivity,Use $derived for computed values,$derived replaces $: in Svelte 5,let doubled = $derived(count * 2),$: in Svelte 5,let doubled = $derived(count * 2),$: doubled = count * 2 (Svelte 5),Medium,
+5,Reactivity,Use $effect for side effects,$effect replaces $: side effects,Use $effect for subscriptions,$: for side effects in Svelte 5,$effect(() => console.log(count)),$: console.log(count) (Svelte 5),Medium,
+6,Props,Export let for props,Declare props with export let,export let propName,Props without export,export let count = 0,let count = 0,High,https://svelte.dev/docs/svelte-components#script-1-export-creates-a-component-prop
+7,Props,Use $props in Svelte 5,$props rune for prop access,let { name } = $props(),export let in Svelte 5,"let { name, age = 0 } = $props()",export let name; export let age = 0,Medium,
+8,Props,Provide default values,Default props with assignment,export let count = 0,Required props without defaults,export let count = 0,export let count,Low,
+9,Props,Use spread props,Pass through unknown props,{...$$restProps} on elements,Manual prop forwarding,<button {...$$restProps}>,<button class={$$props.class}>,Low,https://svelte.dev/docs/basic-markup#attributes-and-props
+10,Bindings,Use bind: for two-way binding,Simplified input handling,bind:value for inputs,on:input with manual update,<input bind:value={name}>,<input value={name} on:input={e => name = e.target.value}>,Low,https://svelte.dev/docs/element-directives#bind-property
+11,Bindings,Bind to DOM elements,Reference DOM nodes,bind:this for element reference,querySelector in onMount,<div bind:this={el}>,onMount(() => el = document.querySelector()),Medium,
+12,Bindings,Use bind:group for radios/checkboxes,Simplified group handling,bind:group for radio/checkbox groups,Manual checked handling,"<input type=""radio"" bind:group={selected}>","<input type=""radio"" checked={selected === value}>",Low,
+13,Events,Use on: for event handlers,Event directive syntax,on:click={handler},addEventListener in onMount,<button on:click={handleClick}>,onMount(() => btn.addEventListener()),Medium,https://svelte.dev/docs/element-directives#on-eventname
+14,Events,Forward events with on:event,Pass events to parent,on:click without handler,createEventDispatcher for DOM events,<button on:click>,"dispatch('click', event)",Low,
+15,Events,Use createEventDispatcher,Custom component events,dispatch for custom events,on:event for custom events,"dispatch('save', { data })",on:save without dispatch,Medium,https://svelte.dev/docs/svelte#createeventdispatcher
+16,Lifecycle,Use onMount for initialization,Run code after component mounts,onMount for setup and data fetching,Code in script body for side effects,onMount(() => fetchData()),fetchData() in script body,High,https://svelte.dev/docs/svelte#onmount
+17,Lifecycle,Return cleanup from onMount,Automatic cleanup on destroy,Return function from onMount,Separate onDestroy for paired cleanup,onMount(() => { sub(); return unsub }),onMount(sub); onDestroy(unsub),Medium,
+18,Lifecycle,Use onDestroy sparingly,Only when onMount cleanup not possible,onDestroy for non-mount cleanup,onDestroy for mount-related cleanup,onDestroy for store unsubscribe,onDestroy(() => clearInterval(id)),Low,
+19,Lifecycle,Avoid beforeUpdate/afterUpdate,Usually not needed,Reactive statements instead,beforeUpdate for derived state,$: if (x) doSomething(),beforeUpdate(() => doSomething()),Low,
+20,Stores,Use writable for mutable state,Basic reactive store,writable for shared mutable state,Local variables for shared state,const count = writable(0),let count = 0 in module,Medium,https://svelte.dev/docs/svelte-store#writable
+21,Stores,Use readable for read-only state,External data sources,readable for derived/external data,writable for read-only data,"readable(0, set => interval(set))",writable(0) for timer,Low,https://svelte.dev/docs/svelte-store#readable
+22,Stores,Use derived for computed stores,Combine or transform stores,derived for computed values,Manual subscription for derived,"derived(count, $c => $c * 2)",count.subscribe(c => doubled = c * 2),Medium,https://svelte.dev/docs/svelte-store#derived
+23,Stores,Use $ prefix for auto-subscription,Automatic subscribe/unsubscribe,$storeName in components,Manual subscription,{$count},count.subscribe(c => value = c),High,
+24,Stores,Clean up custom subscriptions,Unsubscribe when component destroys,Return unsubscribe from onMount,Leave subscriptions open,onMount(() => store.subscribe(fn)),store.subscribe(fn) in script,High,
+25,Slots,Use slots for composition,Content projection,<slot> for flexible content,Props for all content,<slot>Default</slot>,"<Component content=""text""/>",Medium,https://svelte.dev/docs/special-elements#slot
+26,Slots,Name slots for multiple areas,Multiple content areas,"<slot name=""header"">",Single slot for complex layouts,"<slot name=""header""><slot name=""footer"">",<slot> with complex conditionals,Low,
+27,Slots,Check slot content with $$slots,Conditional slot rendering,$$slots.name for conditional rendering,Always render slot wrapper,"{#if $$slots.footer}<slot name=""footer""/>{/if}","<div><slot name=""footer""/></div>",Low,
+28,Styling,Use scoped styles by default,Styles scoped to component,<style> for component styles,Global styles for component,:global() only when needed,<style> all global,Medium,https://svelte.dev/docs/svelte-components#style
+29,Styling,Use :global() sparingly,Escape scoping when needed,:global for third-party styling,Global for all styles,:global(.external-lib),<style> without scoping,Medium,
+30,Styling,Use CSS variables for theming,Dynamic styling,CSS custom properties,Inline styles for themes,"style=""--color: {color}""","style=""color: {color}""",Low,
+31,Transitions,Use built-in transitions,Svelte transition directives,transition:fade for simple effects,Manual CSS transitions,<div transition:fade>,<div class:fade={visible}>,Low,https://svelte.dev/docs/element-directives#transition-fn
+32,Transitions,Use in: and out: separately,Different enter/exit animations,in:fly out:fade for asymmetric,Same transition for both,<div in:fly out:fade>,<div transition:fly>,Low,
+33,Transitions,Add local modifier,Prevent ancestor trigger,transition:fade|local,Global transitions for lists,<div transition:slide|local>,<div transition:slide>,Medium,
+34,Actions,Use actions for DOM behavior,Reusable DOM logic,use:action for DOM enhancements,onMount for each usage,<div use:clickOutside>,onMount(() => setupClickOutside(el)),Medium,https://svelte.dev/docs/element-directives#use-action
+35,Actions,Return update and destroy,Lifecycle methods for actions,"Return { update, destroy }",Only initial setup,"return { update(params) {}, destroy() {} }",return destroy only,Medium,
+36,Actions,Pass parameters to actions,Configure action behavior,use:action={params},Hardcoded action behavior,<div use:tooltip={options}>,<div use:tooltip>,Low,
+37,Logic,Use {#if} for conditionals,Template conditionals,{#if} {:else if} {:else},Ternary in expressions,{#if cond}...{:else}...{/if},{cond ? a : b} for complex,Low,https://svelte.dev/docs/logic-blocks#if
+38,Logic,Use {#each} for lists,List rendering,{#each} with key,Map in expression,{#each items as item (item.id)},{items.map(i => `<div>${i}</div>`)},Medium,
+39,Logic,Always use keys in {#each},Proper list reconciliation,(item.id) for unique key,Index as key or no key,{#each items as item (item.id)},"{#each items as item, i (i)}",High,
+40,Logic,Use {#await} for promises,Handle async states,{#await} for loading/error states,Manual promise handling,{#await promise}...{:then}...{:catch},{#if loading}...{#if error},Medium,https://svelte.dev/docs/logic-blocks#await
+41,SvelteKit,Use +page.svelte for routes,File-based routing,+page.svelte for route components,Custom routing setup,routes/about/+page.svelte,routes/About.svelte,Medium,https://kit.svelte.dev/docs/routing
+42,SvelteKit,Use +page.js for data loading,Load data before render,load function in +page.js,onMount for data fetching,export function load() {},onMount(() => fetchData()),High,https://kit.svelte.dev/docs/load
+43,SvelteKit,Use +page.server.js for server-only,Server-side data loading,+page.server.js for sensitive data,+page.js for API keys,+page.server.js with DB access,+page.js with DB access,High,
+44,SvelteKit,Use form actions,Server-side form handling,+page.server.js actions,API routes for forms,export const actions = { default },fetch('/api/submit'),Medium,https://kit.svelte.dev/docs/form-actions
+45,SvelteKit,Use $app/stores for app state,$page $navigating $updated,$page for current page data,Manual URL parsing,import { page } from '$app/stores',window.location.pathname,Medium,https://kit.svelte.dev/docs/modules#$app-stores
+46,Performance,Use {#key} for forced re-render,Reset component state,{#key id} for fresh instance,Manual destroy/create,{#key item.id}<Component/>{/key},on:change={() => component = null},Low,https://svelte.dev/docs/logic-blocks#key
+47,Performance,Avoid unnecessary reactivity,Not everything needs $:,$: only for side effects,$: for simple assignments,$: if (x) console.log(x),$: y = x (when y = x works),Low,
+48,Performance,Use immutable compiler option,Skip equality checks,immutable: true for large lists,Default for all components,<svelte:options immutable/>,Default without immutable,Low,
+49,TypeScript,"Use lang=""ts"" in script",TypeScript support,"<script lang=""ts"">",JavaScript for typed projects,"<script lang=""ts"">",<script> with JSDoc,Medium,https://svelte.dev/docs/typescript
+50,TypeScript,Type props with interface,Explicit prop types,interface $$Props for types,Untyped props,interface $$Props { name: string },export let name,Medium,
+51,TypeScript,Type events with createEventDispatcher,Type-safe events,createEventDispatcher<Events>(),Untyped dispatch,createEventDispatcher<{ save: Data }>(),createEventDispatcher(),Medium,
+52,Accessibility,Use semantic elements,Proper HTML in templates,button nav main appropriately,div for everything,<button on:click>,<div on:click>,High,
+53,Accessibility,Add aria to dynamic content,Accessible state changes,aria-live for updates,Silent dynamic updates,"<div aria-live=""polite"">{message}</div>",<div>{message}</div>,Medium,

.cursor/skills/ui-ux-pro-max/data/stacks/swiftui.csv

@@ -0,0 +1,51 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Views,Use struct for views,SwiftUI views are value types,struct MyView: View,class MyView: View,struct ContentView: View { var body: some View },class ContentView: View,High,https://developer.apple.com/documentation/swiftui/view
+2,Views,Keep views small and focused,Single responsibility for each view,Extract subviews for complex layouts,Large monolithic views,Extract HeaderView FooterView,500+ line View struct,Medium,
+3,Views,Use body computed property,body returns the view hierarchy,var body: some View { },func body() -> some View,"var body: some View { Text(""Hello"") }",func body() -> Text,High,
+4,Views,Prefer composition over inheritance,Compose views using ViewBuilder,Combine smaller views,Inheritance hierarchies,VStack { Header() Content() },class SpecialView extends BaseView,Medium,
+5,State,Use @State for local state,Simple value types owned by view,@State for view-local primitives,@State for shared data,@State private var count = 0,@State var sharedData: Model,High,https://developer.apple.com/documentation/swiftui/state
+6,State,Use @Binding for two-way data,Pass mutable state to child views,@Binding for child input,@State in child for parent data,@Binding var isOn: Bool,$isOn to pass binding,Medium,https://developer.apple.com/documentation/swiftui/binding
+7,State,Use @StateObject for reference types,ObservableObject owned by view,@StateObject for view-created objects,@ObservedObject for owned objects,@StateObject private var vm = ViewModel(),@ObservedObject var vm = ViewModel(),High,https://developer.apple.com/documentation/swiftui/stateobject
+8,State,Use @ObservedObject for injected objects,Reference types passed from parent,@ObservedObject for injected dependencies,@StateObject for injected objects,@ObservedObject var vm: ViewModel,@StateObject var vm: ViewModel (injected),High,https://developer.apple.com/documentation/swiftui/observedobject
+9,State,Use @EnvironmentObject for shared state,App-wide state injection,@EnvironmentObject for global state,Prop drilling through views,@EnvironmentObject var settings: Settings,Pass settings through 5 views,Medium,https://developer.apple.com/documentation/swiftui/environmentobject
+10,State,Use @Published in ObservableObject,Automatically publish property changes,@Published for observed properties,Manual objectWillChange calls,@Published var items: [Item] = [],var items: [Item] { didSet { objectWillChange.send() } },Medium,
+11,Observable,Use @Observable macro (iOS 17+),Modern observation without Combine,@Observable class for view models,ObservableObject for new projects,@Observable class ViewModel { },class ViewModel: ObservableObject,Medium,https://developer.apple.com/documentation/observation
+12,Observable,Use @Bindable for @Observable,Create bindings from @Observable,@Bindable var vm for bindings,@Binding with @Observable,@Bindable var viewModel,$viewModel.name with @Observable,Medium,
+13,Layout,Use VStack HStack ZStack,Standard stack-based layouts,Stacks for linear arrangements,GeometryReader for simple layouts,VStack { Text() Image() },GeometryReader for vertical list,Medium,https://developer.apple.com/documentation/swiftui/vstack
+14,Layout,Use LazyVStack LazyHStack for lists,Lazy loading for performance,Lazy stacks for long lists,Regular stacks for 100+ items,LazyVStack { ForEach(items) },VStack { ForEach(largeArray) },High,https://developer.apple.com/documentation/swiftui/lazyvstack
+15,Layout,Use GeometryReader sparingly,Only when needed for sizing,GeometryReader for responsive layouts,GeometryReader everywhere,GeometryReader for aspect ratio,GeometryReader wrapping everything,Medium,
+16,Layout,Use spacing and padding consistently,Consistent spacing throughout app,Design system spacing values,Magic numbers for spacing,.padding(16) or .padding(),".padding(13), .padding(17)",Low,
+17,Layout,Use frame modifiers correctly,Set explicit sizes when needed,.frame(maxWidth: .infinity),Fixed sizes for responsive content,.frame(maxWidth: .infinity),.frame(width: 375),Medium,
+18,Modifiers,Order modifiers correctly,Modifier order affects rendering,Background before padding for full coverage,Wrong modifier order,.padding().background(Color.red),.background(Color.red).padding(),High,
+19,Modifiers,Create custom ViewModifiers,Reusable modifier combinations,ViewModifier for repeated styling,Duplicate modifier chains,struct CardStyle: ViewModifier,.shadow().cornerRadius() everywhere,Medium,https://developer.apple.com/documentation/swiftui/viewmodifier
+20,Modifiers,Use conditional modifiers carefully,Avoid changing view identity,if-else with same view type,Conditional that changes view identity,Text(title).foregroundColor(isActive ? .blue : .gray),if isActive { Text().bold() } else { Text() },Medium,
+21,Navigation,Use NavigationStack (iOS 16+),Modern navigation with type-safe paths,NavigationStack with navigationDestination,NavigationView for new projects,NavigationStack { },NavigationView { } (deprecated),Medium,https://developer.apple.com/documentation/swiftui/navigationstack
+22,Navigation,Use navigationDestination,Type-safe navigation destinations,.navigationDestination(for:),NavigationLink(destination:),.navigationDestination(for: Item.self),NavigationLink(destination: DetailView()),Medium,
+23,Navigation,Use @Environment for dismiss,Programmatic navigation dismissal,@Environment(\.dismiss) var dismiss,presentationMode (deprecated),@Environment(\.dismiss) var dismiss,@Environment(\.presentationMode),Low,
+24,Lists,Use List for scrollable content,Built-in scrolling and styling,List for standard scrollable content,ScrollView + VStack for simple lists,List { ForEach(items) { } },ScrollView { VStack { ForEach } },Low,https://developer.apple.com/documentation/swiftui/list
+25,Lists,Provide stable identifiers,Use Identifiable or explicit id,Identifiable protocol or id parameter,Index as identifier,ForEach(items) where Item: Identifiable,"ForEach(items.indices, id: \.self)",High,
+26,Lists,Use onDelete and onMove,Standard list editing,onDelete for swipe to delete,Custom delete implementation,.onDelete(perform: delete),.onTapGesture for delete,Low,
+27,Forms,Use Form for settings,Grouped input controls,Form for settings screens,Manual grouping for forms,Form { Section { Toggle() } },VStack { Toggle() },Low,https://developer.apple.com/documentation/swiftui/form
+28,Forms,Use @FocusState for keyboard,Manage keyboard focus,@FocusState for text field focus,Manual first responder handling,@FocusState private var isFocused: Bool,UIKit first responder,Medium,https://developer.apple.com/documentation/swiftui/focusstate
+29,Forms,Validate input properly,Show validation feedback,Real-time validation feedback,Submit without validation,TextField with validation state,TextField without error handling,Medium,
+30,Async,Use .task for async work,Automatic cancellation on view disappear,.task for view lifecycle async,onAppear with Task,.task { await loadData() },onAppear { Task { await loadData() } },Medium,https://developer.apple.com/documentation/swiftui/view/task(priority:_:)
+31,Async,Handle loading states,Show progress during async operations,ProgressView during loading,Empty view during load,if isLoading { ProgressView() },No loading indicator,Medium,
+32,Async,Use @MainActor for UI updates,Ensure UI updates on main thread,@MainActor on view models,Manual DispatchQueue.main,@MainActor class ViewModel,DispatchQueue.main.async,Medium,
+33,Animation,Use withAnimation,Animate state changes,withAnimation for state transitions,No animation for state changes,withAnimation { isExpanded.toggle() },isExpanded.toggle(),Low,https://developer.apple.com/documentation/swiftui/withanimation(_:_:)
+34,Animation,Use .animation modifier,Apply animations to views,.animation(.spring()) on view,Manual animation timing,.animation(.easeInOut),CABasicAnimation equivalent,Low,
+35,Animation,Respect reduced motion,Check accessibility settings,Check accessibilityReduceMotion,Ignore motion preferences,@Environment(\.accessibilityReduceMotion),Always animate regardless,High,
+36,Preview,Use #Preview macro (Xcode 15+),Modern preview syntax,#Preview for view previews,PreviewProvider protocol,#Preview { ContentView() },struct ContentView_Previews: PreviewProvider,Low,
+37,Preview,Create multiple previews,Test different states and devices,Multiple previews for states,Single preview only,"#Preview(""Light"") { } #Preview(""Dark"") { }",Single preview configuration,Low,
+38,Preview,Use preview data,Dedicated preview mock data,Static preview data,Production data in previews,Item.preview for preview,Fetch real data in preview,Low,
+39,Performance,Avoid expensive body computations,Body should be fast to compute,Precompute in view model,Heavy computation in body,vm.computedValue in body,Complex calculation in body,High,
+40,Performance,Use Equatable views,Skip unnecessary view updates,Equatable for complex views,Default equality for all views,struct MyView: View Equatable,No Equatable conformance,Medium,
+41,Performance,Profile with Instruments,Measure before optimizing,Use SwiftUI Instruments,Guess at performance issues,Profile with Instruments,Optimize without measuring,Medium,
+42,Accessibility,Add accessibility labels,Describe UI elements,.accessibilityLabel for context,Missing labels,".accessibilityLabel(""Close button"")",Button without label,High,https://developer.apple.com/documentation/swiftui/view/accessibilitylabel(_:)-1d7jv
+43,Accessibility,Support Dynamic Type,Respect text size preferences,Scalable fonts and layouts,Fixed font sizes,.font(.body) with Dynamic Type,.font(.system(size: 16)),High,
+44,Accessibility,Use semantic views,Proper accessibility traits,Correct accessibilityTraits,Wrong semantic meaning,Button for actions Image for display,Image that acts like button,Medium,
+45,Testing,Use ViewInspector for testing,Third-party view testing,ViewInspector for unit tests,UI tests only,ViewInspector assertions,Only XCUITest,Medium,
+46,Testing,Test view models,Unit test business logic,XCTest for view model,Skip view model testing,Test ViewModel methods,No unit tests,Medium,
+47,Testing,Use preview as visual test,Previews catch visual regressions,Multiple preview configurations,No visual verification,Preview different states,Single preview only,Low,
+48,Architecture,Use MVVM pattern,Separate view and logic,ViewModel for business logic,Logic in View,ObservableObject ViewModel,@State for complex logic,Medium,
+49,Architecture,Keep views dumb,Views display view model state,View reads from ViewModel,Business logic in View,view.items from vm.items,Complex filtering in View,Medium,
+50,Architecture,Use dependency injection,Inject dependencies for testing,Initialize with dependencies,Hard-coded dependencies,init(service: ServiceProtocol),let service = RealService(),Medium,

.cursor/skills/ui-ux-pro-max/data/stacks/vue.csv

@@ -0,0 +1,50 @@
+No,Category,Guideline,Description,Do,Don't,Code Good,Code Bad,Severity,Docs URL
+1,Composition,Use Composition API for new projects,Composition API offers better TypeScript support and logic reuse,<script setup> for components,Options API for new projects,<script setup>,export default { data() },Medium,https://vuejs.org/guide/extras/composition-api-faq.html
+2,Composition,Use script setup syntax,Cleaner syntax with automatic exports,<script setup> with defineProps,setup() function manually,<script setup>,<script> setup() { return {} },Low,https://vuejs.org/api/sfc-script-setup.html
+3,Reactivity,Use ref for primitives,ref() for primitive values that need reactivity,ref() for strings numbers booleans,reactive() for primitives,const count = ref(0),const count = reactive(0),Medium,https://vuejs.org/guide/essentials/reactivity-fundamentals.html
+4,Reactivity,Use reactive for objects,reactive() for complex objects and arrays,reactive() for objects with multiple properties,ref() for complex objects,const state = reactive({ user: null }),const state = ref({ user: null }),Medium,
+5,Reactivity,Access ref values with .value,Remember .value in script unwrap in template,Use .value in script,Forget .value in script,count.value++,count++ (in script),High,
+6,Reactivity,Use computed for derived state,Computed properties cache and update automatically,computed() for derived values,Methods for derived values,const doubled = computed(() => count.value * 2),const doubled = () => count.value * 2,Medium,https://vuejs.org/guide/essentials/computed.html
+7,Reactivity,Use shallowRef for large objects,Avoid deep reactivity for performance,shallowRef for large data structures,ref for large nested objects,const bigData = shallowRef(largeObject),const bigData = ref(largeObject),Medium,https://vuejs.org/api/reactivity-advanced.html#shallowref
+8,Watchers,Use watchEffect for simple cases,Auto-tracks dependencies,watchEffect for simple reactive effects,watch with explicit deps when not needed,watchEffect(() => console.log(count.value)),"watch(count, (val) => console.log(val))",Low,https://vuejs.org/guide/essentials/watchers.html
+9,Watchers,Use watch for specific sources,Explicit control over what to watch,watch with specific refs,watchEffect for complex conditional logic,"watch(userId, fetchUser)",watchEffect with conditionals,Medium,
+10,Watchers,Clean up side effects,Return cleanup function in watchers,Return cleanup in watchEffect,Leave subscriptions open,watchEffect((onCleanup) => { onCleanup(unsub) }),watchEffect without cleanup,High,
+11,Props,Define props with defineProps,Type-safe prop definitions,defineProps with TypeScript,Props without types,defineProps<{ msg: string }>(),defineProps(['msg']),Medium,https://vuejs.org/guide/typescript/composition-api.html#typing-component-props
+12,Props,Use withDefaults for default values,Provide defaults for optional props,withDefaults with defineProps,Defaults in destructuring,"withDefaults(defineProps<Props>(), { count: 0 })",const { count = 0 } = defineProps(),Medium,
+13,Props,Avoid mutating props,Props should be read-only,Emit events to parent for changes,Direct prop mutation,"emit('update:modelValue', newVal)",props.modelValue = newVal,High,
+14,Emits,Define emits with defineEmits,Type-safe event emissions,defineEmits with types,Emit without definition,defineEmits<{ change: [id: number] }>(),"emit('change', id) without define",Medium,https://vuejs.org/guide/typescript/composition-api.html#typing-component-emits
+15,Emits,Use v-model for two-way binding,Simplified parent-child data flow,v-model with modelValue prop,:value + @input manually,"<Child v-model=""value""/>","<Child :value=""value"" @input=""value = $event""/>",Low,https://vuejs.org/guide/components/v-model.html
+16,Lifecycle,Use onMounted for DOM access,DOM is ready in onMounted,onMounted for DOM operations,Access DOM in setup directly,onMounted(() => el.value.focus()),el.value.focus() in setup,High,https://vuejs.org/api/composition-api-lifecycle.html
+17,Lifecycle,Clean up in onUnmounted,Remove listeners and subscriptions,onUnmounted for cleanup,Leave listeners attached,onUnmounted(() => window.removeEventListener()),No cleanup on unmount,High,
+18,Lifecycle,Avoid onBeforeMount for data,Use onMounted or setup for data fetching,Fetch in onMounted or setup,Fetch in onBeforeMount,onMounted(async () => await fetchData()),onBeforeMount(async () => await fetchData()),Low,
+19,Components,Use single-file components,Keep template script style together,.vue files for components,Separate template/script files,Component.vue with all parts,Component.js + Component.html,Low,
+20,Components,Use PascalCase for components,Consistent component naming,PascalCase in imports and templates,kebab-case in script,<MyComponent/>,<my-component/>,Low,https://vuejs.org/style-guide/rules-strongly-recommended.html
+21,Components,Prefer composition over mixins,Composables replace mixins,Composables for shared logic,Mixins for code reuse,const { data } = useApi(),mixins: [apiMixin],Medium,
+22,Composables,Name composables with use prefix,Convention for composable functions,useFetch useAuth useForm,getData or fetchApi,export function useFetch(),export function fetchData(),Medium,https://vuejs.org/guide/reusability/composables.html
+23,Composables,Return refs from composables,Maintain reactivity when destructuring,Return ref values,Return reactive objects that lose reactivity,return { data: ref(null) },return reactive({ data: null }),Medium,
+24,Composables,Accept ref or value params,Use toValue for flexible inputs,toValue() or unref() for params,Only accept ref or only value,const val = toValue(maybeRef),const val = maybeRef.value,Low,https://vuejs.org/api/reactivity-utilities.html#tovalue
+25,Templates,Use v-bind shorthand,Cleaner template syntax,:prop instead of v-bind:prop,Full v-bind syntax,"<div :class=""cls"">","<div v-bind:class=""cls"">",Low,
+26,Templates,Use v-on shorthand,Cleaner event binding,@event instead of v-on:event,Full v-on syntax,"<button @click=""handler"">","<button v-on:click=""handler"">",Low,
+27,Templates,Avoid v-if with v-for,v-if has higher priority causes issues,Wrap in template or computed filter,v-if on same element as v-for,<template v-for><div v-if>,<div v-for v-if>,High,https://vuejs.org/style-guide/rules-essential.html#avoid-v-if-with-v-for
+28,Templates,Use key with v-for,Proper list rendering and updates,Unique key for each item,Index as key for dynamic lists,"v-for=""item in items"" :key=""item.id""","v-for=""(item, i) in items"" :key=""i""",High,
+29,State,Use Pinia for global state,Official state management for Vue 3,Pinia stores for shared state,Vuex for new projects,const store = useCounterStore(),Vuex with mutations,Medium,https://pinia.vuejs.org/
+30,State,Define stores with defineStore,Composition API style stores,Setup stores with defineStore,Options stores for complex state,"defineStore('counter', () => {})","defineStore('counter', { state })",Low,
+31,State,Use storeToRefs for destructuring,Maintain reactivity when destructuring,storeToRefs(store),Direct destructuring,const { count } = storeToRefs(store),const { count } = store,High,https://pinia.vuejs.org/core-concepts/#destructuring-from-a-store
+32,Routing,Use useRouter and useRoute,Composition API router access,useRouter() useRoute() in setup,this.$router this.$route,const router = useRouter(),this.$router.push(),Medium,https://router.vuejs.org/guide/advanced/composition-api.html
+33,Routing,Lazy load route components,Code splitting for routes,() => import() for components,Static imports for all routes,component: () => import('./Page.vue'),component: Page,Medium,https://router.vuejs.org/guide/advanced/lazy-loading.html
+34,Routing,Use navigation guards,Protect routes and handle redirects,beforeEach for auth checks,Check auth in each component,router.beforeEach((to) => {}),Check auth in onMounted,Medium,
+35,Performance,Use v-once for static content,Skip re-renders for static elements,v-once on never-changing content,v-once on dynamic content,<div v-once>{{ staticText }}</div>,<div v-once>{{ dynamicText }}</div>,Low,https://vuejs.org/api/built-in-directives.html#v-once
+36,Performance,Use v-memo for expensive lists,Memoize list items,v-memo with dependency array,Re-render entire list always,"<div v-for v-memo=""[item.id]"">",<div v-for> without memo,Medium,https://vuejs.org/api/built-in-directives.html#v-memo
+37,Performance,Use shallowReactive for flat objects,Avoid deep reactivity overhead,shallowReactive for flat state,reactive for simple objects,shallowReactive({ count: 0 }),reactive({ count: 0 }),Low,
+38,Performance,Use defineAsyncComponent,Lazy load heavy components,defineAsyncComponent for modals dialogs,Import all components eagerly,defineAsyncComponent(() => import()),import HeavyComponent from,Medium,https://vuejs.org/guide/components/async.html
+39,TypeScript,Use generic components,Type-safe reusable components,Generic with defineComponent,Any types in components,"<script setup lang=""ts"" generic=""T"">",<script setup> without types,Medium,https://vuejs.org/guide/typescript/composition-api.html
+40,TypeScript,Type template refs,Proper typing for DOM refs,ref<HTMLInputElement>(null),ref(null) without type,const input = ref<HTMLInputElement>(null),const input = ref(null),Medium,
+41,TypeScript,Use PropType for complex props,Type complex prop types,PropType<User> for object props,Object without type,type: Object as PropType<User>,type: Object,Medium,
+42,Testing,Use Vue Test Utils,Official testing library,mount shallowMount for components,Manual DOM testing,import { mount } from '@vue/test-utils',document.createElement,Medium,https://test-utils.vuejs.org/
+43,Testing,Test component behavior,Focus on inputs and outputs,Test props emit and rendered output,Test internal implementation,expect(wrapper.text()).toContain(),expect(wrapper.vm.internalState),Medium,
+44,Forms,Use v-model modifiers,Built-in input handling,.lazy .number .trim modifiers,Manual input parsing,"<input v-model.number=""age"">","<input v-model=""age""> then parse",Low,https://vuejs.org/guide/essentials/forms.html#modifiers
+45,Forms,Use VeeValidate or FormKit,Form validation libraries,VeeValidate for complex forms,Manual validation logic,useField useForm from vee-validate,Custom validation in each input,Medium,
+46,Accessibility,Use semantic elements,Proper HTML elements in templates,button nav main for purpose,div for everything,<button @click>,<div @click>,High,
+47,Accessibility,Bind aria attributes dynamically,Keep ARIA in sync with state,":aria-expanded=""isOpen""",Static ARIA values,":aria-expanded=""menuOpen""","aria-expanded=""true""",Medium,
+48,SSR,Use Nuxt for SSR,Full-featured SSR framework,Nuxt 3 for SSR apps,Manual SSR setup,npx nuxi init my-app,Custom SSR configuration,Medium,https://nuxt.com/
+49,SSR,Handle hydration mismatches,Client/server content must match,ClientOnly for browser-only content,Different content server/client,<ClientOnly><BrowserWidget/></ClientOnly>,<div>{{ Date.now() }}</div>,High,

.cursor/skills/ui-ux-pro-max/data/styles.csv

@@ -0,0 +1,68 @@
+No,Style Category,Type,Keywords,Primary Colors,Secondary Colors,Effects & Animation,Best For,Do Not Use For,Light Mode ✓,Dark Mode ✓,Performance,Accessibility,Mobile-Friendly,Conversion-Focused,Framework Compatibility,Era/Origin,Complexity,AI Prompt Keywords,CSS/Technical Keywords,Implementation Checklist,Design System Variables
+1,Minimalism & Swiss Style,General,"Clean, simple, spacious, functional, white space, high contrast, geometric, sans-serif, grid-based, essential","Monochromatic, Black #000000, White #FFFFFF","Neutral (Beige #F5F1E8, Grey #808080, Taupe #B38B6D), Primary accent","Subtle hover (200-250ms), smooth transitions, sharp shadows if any, clear type hierarchy, fast loading","Enterprise apps, dashboards, documentation sites, SaaS platforms, professional tools","Creative portfolios, entertainment, playful brands, artistic experiments",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,◐ Medium,"Tailwind 10/10, Bootstrap 9/10, MUI 9/10",1950s Swiss,Low,"Design a minimalist landing page. Use: white space, geometric layouts, sans-serif fonts, high contrast, grid-based structure, essential elements only. Avoid shadows and gradients. Focus on clarity and functionality.","display: grid, gap: 2rem, font-family: sans-serif, color: #000 or #FFF, max-width: 1200px, clean borders, no box-shadow unless necessary","☐ Grid-based layout 12-16 columns, ☐ Typography hierarchy clear, ☐ No unnecessary decorations, ☐ WCAG AAA contrast verified, ☐ Mobile responsive grid","--spacing: 2rem, --border-radius: 0px, --font-weight: 400-700, --shadow: none, --accent-color: single primary only"
+2,Neumorphism,General,"Soft UI, embossed, debossed, convex, concave, light source, subtle depth, rounded (12-16px), monochromatic","Light pastels: Soft Blue #C8E0F4, Soft Pink #F5E0E8, Soft Grey #E8E8E8","Tints/shades (±30%), gradient subtlety, color harmony","Soft box-shadow (multiple: -5px -5px 15px, 5px 5px 15px), smooth press (150ms), inner subtle shadow","Health/wellness apps, meditation platforms, fitness trackers, minimal interaction UIs","Complex apps, critical accessibility, data-heavy dashboards, high-contrast required",✓ Full,◐ Partial,⚡ Good,⚠ Low contrast,✓ Good,◐ Medium,"Tailwind 8/10, CSS-in-JS 9/10",2020s Modern,Medium,"Create a neumorphic UI with soft 3D effects. Use light pastels, rounded corners (12-16px), subtle soft shadows (multiple layers), no hard lines, monochromatic color scheme with light/dark variations. Embossed/debossed effect on interactive elements.","border-radius: 12-16px, box-shadow: -5px -5px 15px rgba(0,0,0,0.1), 5px 5px 15px rgba(255,255,255,0.8), background: linear-gradient(145deg, color1, color2), transform: scale on press","☐ Rounded corners 12-16px consistent, ☐ Multiple shadow layers (2-3), ☐ Pastel color verified, ☐ Monochromatic palette checked, ☐ Press animation smooth 150ms","--border-radius: 14px, --shadow-soft-1: -5px -5px 15px, --shadow-soft-2: 5px 5px 15px, --color-light: #F5F5F5, --color-primary: single pastel"
+3,Glassmorphism,General,"Frosted glass, transparent, blurred background, layered, vibrant background, light source, depth, multi-layer","Translucent white: rgba(255,255,255,0.1-0.3)","Vibrant: Electric Blue #0080FF, Neon Purple #8B00FF, Vivid Pink #FF1493, Teal #20B2AA","Backdrop blur (10-20px), subtle border (1px solid rgba white 0.2), light reflection, Z-depth","Modern SaaS, financial dashboards, high-end corporate, lifestyle apps, modal overlays, navigation","Low-contrast backgrounds, critical accessibility, performance-limited, dark text on dark",✓ Full,✓ Full,⚠ Good,⚠ Ensure 4.5:1,✓ Good,✓ High,"Tailwind 9/10, MUI 8/10, Chakra 8/10",2020s Modern,Medium,"Design a glassmorphic interface with frosted glass effect. Use backdrop blur (10-20px), translucent overlays (rgba 10-30% opacity), vibrant background colors, subtle borders, light source reflection, layered depth. Perfect for modern overlays and cards.","backdrop-filter: blur(15px), background: rgba(255, 255, 255, 0.15), border: 1px solid rgba(255,255,255,0.2), -webkit-backdrop-filter: blur(15px), z-index layering for depth","☐ Backdrop-filter blur 10-20px, ☐ Translucent white 15-30% opacity, ☐ Subtle border 1px light, ☐ Vibrant background verified, ☐ Text contrast 4.5:1 checked","--blur-amount: 15px, --glass-opacity: 0.15, --border-color: rgba(255,255,255,0.2), --background: vibrant color, --text-color: light/dark based on BG"
+4,Brutalism,General,"Raw, unpolished, stark, high contrast, plain text, default fonts, visible borders, asymmetric, anti-design","Primary: Red #FF0000, Blue #0000FF, Yellow #FFFF00, Black #000000, White #FFFFFF","Limited: Neon Green #00FF00, Hot Pink #FF00FF, minimal secondary","No smooth transitions (instant), sharp corners (0px), bold typography (700+), visible grid, large blocks","Design portfolios, artistic projects, counter-culture brands, editorial/media sites, tech blogs","Corporate environments, conservative industries, critical accessibility, customer-facing professional",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,◐ Medium,✗ Low,"Tailwind 10/10, Bootstrap 7/10",1950s Brutalist,Low,"Create a brutalist design with raw, unpolished, stark aesthetic. Use pure primary colors (red, blue, yellow), black & white, no smooth transitions (instant), sharp corners, bold large typography, visible grid lines, default system fonts, intentional 'broken' design elements.","border-radius: 0px, transition: none or 0s, font-family: system-ui or monospace, font-weight: 700+, border: visible 2-4px, colors: #FF0000, #0000FF, #FFFF00, #000000, #FFFFFF","☐ No border-radius (0px), ☐ No transitions (instant), ☐ Bold typography (700+), ☐ Pure primary colors used, ☐ Visible grid/borders, ☐ Asymmetric layout intentional","--border-radius: 0px, --transition-duration: 0s, --font-weight: 700-900, --colors: primary only, --border-style: visible, --grid-visible: true"
+5,3D & Hyperrealism,General,"Depth, realistic textures, 3D models, spatial navigation, tactile, skeuomorphic elements, rich detail, immersive","Deep Navy #001F3F, Forest Green #228B22, Burgundy #800020, Gold #FFD700, Silver #C0C0C0","Complex gradients (5-10 stops), realistic lighting, shadow variations (20-40% darker)","WebGL/Three.js 3D, realistic shadows (layers), physics lighting, parallax (3-5 layers), smooth 3D (300-400ms)","Gaming, product showcase, immersive experiences, high-end e-commerce, architectural viz, VR/AR","Low-end mobile, performance-limited, critical accessibility, data tables/forms",◐ Partial,◐ Partial,❌ Poor,⚠ Not accessible,✗ Low,◐ Medium,"Three.js 10/10, R3F 10/10, Babylon.js 10/10",2020s Modern,High,"Build an immersive 3D interface using realistic textures, 3D models (Three.js/Babylon.js), complex shadows, realistic lighting, parallax scrolling (3-5 layers), physics-based motion. Include skeuomorphic elements with tactile detail.","transform: translate3d, perspective: 1000px, WebGL canvas, Three.js/Babylon.js library, box-shadow: complex multi-layer, background: complex gradients, filter: drop-shadow()","☐ WebGL/Three.js integrated, ☐ 3D models loaded, ☐ Parallax 3-5 layers, ☐ Realistic lighting verified, ☐ Complex shadows rendered, ☐ Physics animation smooth 300-400ms","--perspective: 1000px, --parallax-layers: 5, --lighting-intensity: realistic, --shadow-depth: 20-40%, --animation-duration: 300-400ms"
+6,Vibrant & Block-based,General,"Bold, energetic, playful, block layout, geometric shapes, high color contrast, duotone, modern, energetic","Neon Green #39FF14, Electric Purple #BF00FF, Vivid Pink #FF1493, Bright Cyan #00FFFF, Sunburst #FFAA00","Complementary: Orange #FF7F00, Shocking Pink #FF006E, Lime #CCFF00, triadic schemes","Large sections (48px+ gaps), animated patterns, bold hover (color shift), scroll-snap, large type (32px+), 200-300ms","Startups, creative agencies, gaming, social media, youth-focused, entertainment, consumer","Financial institutions, healthcare, formal business, government, conservative, elderly",✓ Full,✓ Full,⚡ Good,◐ Ensure WCAG,✓ High,✓ High,"Tailwind 10/10, Chakra 9/10, Styled 9/10",2020s Modern,Medium,"Design an energetic, vibrant interface with bold block layouts, geometric shapes, high color contrast, large typography (32px+), animated background patterns, duotone effects. Perfect for startups and youth-focused apps. Use 4-6 contrasting colors from complementary/triadic schemes.","display: flex/grid with large gaps (48px+), font-size: 32px+, background: animated patterns (CSS), color: neon/vibrant colors, animation: continuous pattern movement","☐ Block layout with 48px+ gaps, ☐ Large typography 32px+, ☐ 4-6 vibrant colors max, ☐ Animated patterns active, ☐ Scroll-snap enabled, ☐ High contrast verified (7:1+)","--block-gap: 48px, --typography-size: 32px+, --color-palette: 4-6 vibrant colors, --animation: continuous pattern, --contrast-ratio: 7:1+"
+7,Dark Mode (OLED),General,"Dark theme, low light, high contrast, deep black, midnight blue, eye-friendly, OLED, night mode, power efficient","Deep Black #000000, Dark Grey #121212, Midnight Blue #0A0E27","Vibrant accents: Neon Green #39FF14, Electric Blue #0080FF, Gold #FFD700, Plasma Purple #BF00FF","Minimal glow (text-shadow: 0 0 10px), dark-to-light transitions, low white emission, high readability, visible focus","Night-mode apps, coding platforms, entertainment, eye-strain prevention, OLED devices, low-light","Print-first content, high-brightness outdoor, color-accuracy-critical",✗ No,✓ Only,⚡ Excellent,✓ WCAG AAA,✓ High,◐ Low,"Tailwind 10/10, MUI 10/10, Chakra 10/10",2020s Modern,Low,"Create an OLED-optimized dark interface with deep black (#000000), dark grey (#121212), midnight blue accents. Use minimal glow effects, vibrant neon accents (green, blue, gold, purple), high contrast text. Optimize for eye comfort and OLED power saving.","background: #000000 or #121212, color: #FFFFFF or #E0E0E0, text-shadow: 0 0 10px neon-color (sparingly), filter: brightness(0.8) if needed, color-scheme: dark","☐ Deep black #000000 or #121212, ☐ Vibrant neon accents used, ☐ Text contrast 7:1+, ☐ Minimal glow effects, ☐ OLED power optimization, ☐ No white (#FFFFFF) background","--bg-black: #000000, --bg-dark-grey: #121212, --text-primary: #FFFFFF, --accent-neon: neon colors, --glow-effect: minimal, --oled-optimized: true"
+8,Accessible & Ethical,General,"High contrast, large text (16px+), keyboard navigation, screen reader friendly, WCAG compliant, focus state, semantic","WCAG AA/AAA (4.5:1 min), simple primary, clear secondary, high luminosity (7:1+)","Symbol-based colors (not color-only), supporting patterns, inclusive combinations","Clear focus rings (3-4px), ARIA labels, skip links, responsive design, reduced motion, 44x44px touch targets","Government, healthcare, education, inclusive products, large audience, legal compliance, public",None - accessibility universal,✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ High,All frameworks 10/10,Universal,Low,"Design with WCAG AAA compliance. Include: high contrast (7:1+), large text (16px+), keyboard navigation, screen reader compatibility, focus states visible (3-4px ring), semantic HTML, ARIA labels, skip links, reduced motion support (prefers-reduced-motion), 44x44px touch targets.","color-contrast: 7:1+, font-size: 16px+, outline: 3-4px on :focus-visible, aria-label, role attributes, @media (prefers-reduced-motion), touch-target: 44x44px, cursor: pointer","☐ WCAG AAA verified, ☐ 7:1+ contrast checked, ☐ Keyboard navigation tested, ☐ Screen reader tested, ☐ Focus visible 3-4px, ☐ Semantic HTML used, ☐ Touch targets 44x44px","--contrast-ratio: 7:1, --font-size-min: 16px, --focus-ring: 3-4px, --touch-target: 44x44px, --wcag-level: AAA, --keyboard-accessible: true, --sr-tested: true"
+9,Claymorphism,General,"Soft 3D, chunky, playful, toy-like, bubbly, thick borders (3-4px), double shadows, rounded (16-24px)","Pastel: Soft Peach #FDBCB4, Baby Blue #ADD8E6, Mint #98FF98, Lilac #E6E6FA, light BG","Soft gradients (pastel-to-pastel), light/dark variations (20-30%), gradient subtle","Inner+outer shadows (subtle, no hard lines), soft press (200ms ease-out), fluffy elements, smooth transitions","Educational apps, children's apps, SaaS platforms, creative tools, fun-focused, onboarding, casual games","Formal corporate, professional services, data-critical, serious/medical, legal apps, finance",✓ Full,◐ Partial,⚡ Good,⚠ Ensure 4.5:1,✓ High,✓ High,"Tailwind 9/10, CSS-in-JS 9/10",2020s Modern,Medium,"Design a playful, toy-like interface with soft 3D, chunky elements, bubbly aesthetic, rounded edges (16-24px), thick borders (3-4px), double shadows (inner + outer), pastel colors, smooth animations. Perfect for children's apps and creative tools.","border-radius: 16-24px, border: 3-4px solid, box-shadow: inset -2px -2px 8px, 4px 4px 8px, background: pastel-gradient, animation: soft bounce (cubic-bezier 0.34, 1.56)","☐ Border-radius 16-24px, ☐ Thick borders 3-4px, ☐ Double shadows (inner+outer), ☐ Pastel colors used, ☐ Soft bounce animations, ☐ Playful interactions","--border-radius: 20px, --border-width: 3-4px, --shadow-inner: inset -2px -2px 8px, --shadow-outer: 4px 4px 8px, --color-palette: pastels, --animation: bounce"
+10,Aurora UI,General,"Vibrant gradients, smooth blend, Northern Lights effect, mesh gradient, luminous, atmospheric, abstract","Complementary: Blue-Orange, Purple-Yellow, Electric Blue #0080FF, Magenta #FF1493, Cyan #00FFFF","Smooth transitions (Blue→Purple→Pink→Teal), iridescent effects, blend modes (screen, multiply)","Large flowing CSS/SVG gradients, subtle 8-12s animations, depth via color layering, smooth morph","Modern SaaS, creative agencies, branding, music platforms, lifestyle, premium products, hero sections","Data-heavy dashboards, critical accessibility, content-heavy where distraction issues",✓ Full,✓ Full,⚠ Good,⚠ Text contrast,✓ Good,✓ High,"Tailwind 9/10, CSS-in-JS 10/10",2020s Modern,Medium,"Create a vibrant gradient interface inspired by Northern Lights with mesh gradients, smooth color blends, flowing animations. Use complementary color pairs (blue-orange, purple-yellow), flowing background gradients, subtle continuous animations (8-12s loops), iridescent effects.","background: conic-gradient or radial-gradient with multiple stops, animation: @keyframes gradient (8-12s), background-size: 200% 200%, filter: saturate(1.2), blend-mode: screen or multiply","☐ Mesh/flowing gradients applied, ☐ 8-12s animation loop, ☐ Complementary colors used, ☐ Smooth color transitions, ☐ Iridescent effect subtle, ☐ Text contrast verified","--gradient-colors: complementary pairs, --animation-duration: 8-12s, --blend-mode: screen, --color-saturation: 1.2, --effect: iridescent, --loop-smooth: true"
+11,Retro-Futurism,General,"Vintage sci-fi, 80s aesthetic, neon glow, geometric patterns, CRT scanlines, pixel art, cyberpunk, synthwave","Neon Blue #0080FF, Hot Pink #FF006E, Cyan #00FFFF, Deep Black #1A1A2E, Purple #5D34D0","Metallic Silver #C0C0C0, Gold #FFD700, duotone, 80s Pink #FF10F0, neon accents","CRT scanlines (::before overlay), neon glow (text-shadow+box-shadow), glitch effects (skew/offset keyframes)","Gaming, entertainment, music platforms, tech brands, artistic projects, nostalgic, cyberpunk","Conservative industries, critical accessibility, professional/corporate, elderly, legal/finance",✓ Full,✓ Dark focused,⚠ Moderate,⚠ High contrast/strain,◐ Medium,◐ Medium,"Tailwind 8/10, CSS-in-JS 9/10",1980s Retro,Medium,"Build a retro-futuristic (cyberpunk/vaporwave) interface with neon colors (blue, pink, cyan), deep black background, 80s aesthetic, CRT scanlines, glitch effects, neon glow text/borders, monospace fonts, geometric patterns. Use neon text-shadow and animated glitch effects.","color: neon colors (#0080FF, #FF006E, #00FFFF), text-shadow: 0 0 10px neon, background: #000 or #1A1A2E, font-family: monospace, animation: glitch (skew+offset), filter: hue-rotate","☐ Neon colors used, ☐ CRT scanlines effect, ☐ Glitch animations active, ☐ Monospace font, ☐ Deep black background, ☐ Glow effects applied, ☐ 80s patterns present","--neon-colors: #0080FF #FF006E #00FFFF, --background: #000000, --font-family: monospace, --effect: glitch+glow, --scanline-opacity: 0.3, --crt-effect: true"
+12,Flat Design,General,"2D, minimalist, bold colors, no shadows, clean lines, simple shapes, typography-focused, modern, icon-heavy","Solid bright: Red, Orange, Blue, Green, limited palette (4-6 max)","Complementary colors, muted secondaries, high saturation, clean accents","No gradients/shadows, simple hover (color/opacity shift), fast loading, clean transitions (150-200ms ease), minimal icons","Web apps, mobile apps, cross-platform, startup MVPs, user-friendly, SaaS, dashboards, corporate","Complex 3D, premium/luxury, artistic portfolios, immersive experiences, high-detail",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ High,"Tailwind 10/10, Bootstrap 10/10, MUI 9/10",2010s Modern,Low,"Create a flat, 2D interface with bold colors, no shadows/gradients, clean lines, simple geometric shapes, icon-heavy, typography-focused, minimal ornamentation. Use 4-6 solid, bright colors in a limited palette with high saturation.","box-shadow: none, background: solid color, border-radius: 0-4px, color: solid (no gradients), fill: solid, stroke: 1-2px, font: bold sans-serif, icons: simplified SVG","☐ No shadows/gradients, ☐ 4-6 solid colors max, ☐ Clean lines consistent, ☐ Simple shapes used, ☐ Icon-heavy layout, ☐ High saturation colors, ☐ Fast loading verified","--shadow: none, --color-palette: 4-6 solid, --border-radius: 2px, --gradient: none, --icons: simplified SVG, --animation: minimal 150-200ms"
+13,Skeuomorphism,General,"Realistic, texture, depth, 3D appearance, real-world metaphors, shadows, gradients, tactile, detailed, material","Rich realistic: wood, leather, metal colors, detailed gradients (8-12 stops), metallic effects","Realistic lighting gradients, shadow variations (30-50% darker), texture overlays, material colors","Realistic shadows (layers), depth (perspective), texture details (noise, grain), realistic animations (300-500ms)","Legacy apps, gaming, immersive storytelling, premium products, luxury, realistic simulations, education","Modern enterprise, critical accessibility, low-performance, web (use Flat/Modern)",◐ Partial,◐ Partial,❌ Poor,⚠ Textures reduce readability,✗ Low,◐ Medium,"CSS-in-JS 7/10, Custom 8/10",2007-2012 iOS,High,"Design a realistic, textured interface with 3D depth, real-world metaphors (leather, wood, metal), complex gradients (8-12 stops), realistic shadows, grain/texture overlays, tactile press animations. Perfect for premium/luxury products.","background: complex gradient (8-12 stops), box-shadow: realistic multi-layer, background-image: texture overlay (noise, grain), filter: drop-shadow, transform: scale on press (300-500ms)","☐ Realistic textures applied, ☐ Complex gradients 8-12 stops, ☐ Multi-layer shadows, ☐ Texture overlays present, ☐ Tactile animations smooth, ☐ Depth effect pronounced","--gradient-stops: 8-12, --texture-overlay: noise+grain, --shadow-layers: 3+, --animation-duration: 300-500ms, --depth-effect: pronounced, --tactile: true"
+14,Liquid Glass,General,"Flowing glass, morphing, smooth transitions, fluid effects, translucent, animated blur, iridescent, chromatic aberration","Vibrant iridescent (rainbow spectrum), translucent base with opacity shifts, gradient fluidity","Chromatic aberration (Red-Cyan), iridescent oil-spill, fluid gradient blends, holographic effects","Morphing elements (SVG/CSS), fluid animations (400-600ms curves), dynamic blur (backdrop-filter), color transitions","Premium SaaS, high-end e-commerce, creative platforms, branding experiences, luxury portfolios","Performance-limited, critical accessibility, complex data, budget projects",✓ Full,✓ Full,⚠ Moderate-Poor,⚠ Text contrast,◐ Medium,✓ High,"Framer Motion 10/10, GSAP 10/10",2020s Modern,High,"Create a premium liquid glass effect with morphing shapes, flowing animations, chromatic aberration, iridescent gradients, smooth 400-600ms transitions. Use SVG morphing for shape changes, dynamic blur, smooth color transitions creating a fluid, premium feel.","animation: morphing SVG paths (400-600ms), backdrop-filter: blur + saturate, filter: hue-rotate + brightness, blend-mode: screen, background: iridescent gradient","☐ Morphing animations 400-600ms, ☐ Chromatic aberration applied, ☐ Dynamic blur active, ☐ Iridescent gradients, ☐ Smooth color transitions, ☐ Premium feel achieved","--morph-duration: 400-600ms, --blur-amount: 15px, --chromatic-aberration: true, --iridescent: true, --blend-mode: screen, --smooth-transitions: true"
+15,Motion-Driven,General,"Animation-heavy, microinteractions, smooth transitions, scroll effects, parallax, entrance anim, page transitions","Bold colors emphasize movement, high contrast animated, dynamic gradients, accent action colors","Transitional states, success (Green #22C55E), error (Red #EF4444), neutral feedback","Scroll anim (Intersection Observer), hover (300-400ms), entrance, parallax (3-5 layers), page transitions","Portfolio sites, storytelling platforms, interactive experiences, entertainment apps, creative, SaaS","Data dashboards, critical accessibility, low-power devices, content-heavy, motion-sensitive",✓ Full,✓ Full,⚠ Good,⚠ Prefers-reduced-motion,✓ Good,✓ High,"GSAP 10/10, Framer Motion 10/10",2020s Modern,High,"Build an animation-heavy interface with scroll-triggered animations, microinteractions, parallax scrolling (3-5 layers), smooth transitions (300-400ms), entrance animations, page transitions. Use Intersection Observer for scroll effects, transform for performance, GPU acceleration.","animation: @keyframes scroll-reveal, transform: translateY/X, Intersection Observer API, will-change: transform, scroll-behavior: smooth, animation-duration: 300-400ms","☐ Scroll animations active, ☐ Parallax 3-5 layers, ☐ Entrance animations smooth, ☐ Page transitions fluid, ☐ GPU accelerated, ☐ Prefers-reduced-motion respected","--animation-duration: 300-400ms, --parallax-layers: 5, --scroll-behavior: smooth, --gpu-accelerated: true, --entrance-animation: true, --page-transition: smooth"
+16,Micro-interactions,General,"Small animations, gesture-based, tactile feedback, subtle animations, contextual interactions, responsive","Subtle color shifts (10-20%), feedback: Green #22C55E, Red #EF4444, Amber #F59E0B","Accent feedback, neutral supporting, clear action indicators","Small hover (50-100ms), loading spinners, success/error state anim, gesture-triggered (swipe/pinch), haptic","Mobile apps, touchscreen UIs, productivity tools, user-friendly, consumer apps, interactive components","Desktop-only, critical performance, accessibility-first (alternatives needed)",✓ Full,✓ Full,⚡ Excellent,✓ Good,✓ High,✓ High,"Framer Motion 10/10, React Spring 9/10",2020s Modern,Medium,"Design with delightful micro-interactions: small 50-100ms animations, gesture-based responses, tactile feedback, loading spinners, success/error states, subtle hover effects, haptic feedback triggers for mobile. Focus on responsive, contextual interactions.","animation: short 50-100ms, transition: hover states, @media (hover: hover) for desktop, :active for press, haptic-feedback CSS/API, loading animation smooth loop","☐ Micro-animations 50-100ms, ☐ Gesture-responsive, ☐ Tactile feedback visual/haptic, ☐ Loading spinners smooth, ☐ Success/error states clear, ☐ Hover effects subtle","--micro-animation-duration: 50-100ms, --gesture-responsive: true, --haptic-feedback: true, --loading-animation: smooth, --state-feedback: success+error"
+17,Inclusive Design,General,"Accessible, color-blind friendly, high contrast, haptic feedback, voice interaction, screen reader, WCAG AAA, universal","WCAG AAA (7:1+ contrast), avoid red-green only, symbol-based indicators, high contrast primary","Supporting patterns (stripes, dots, hatch), symbols, combinations, clear non-color indicators","Haptic feedback (vibration), voice guidance, focus indicators (4px+ ring), motion options, alt content, semantic","Public services, education, healthcare, finance, government, accessible consumer, inclusive",None - accessibility universal,✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ High,All frameworks 10/10,Universal,Low,"Design for universal accessibility: high contrast (7:1+), large text (16px+), keyboard-only navigation, screen reader optimization, WCAG AAA compliance, symbol-based color indicators (not color-only), haptic feedback, voice interaction support, reduced motion options.","aria-* attributes complete, role attributes semantic, focus-visible: 3-4px ring, color-contrast: 7:1+, @media (prefers-reduced-motion), alt text on all images, form labels properly associated","☐ WCAG AAA verified, ☐ 7:1+ contrast all text, ☐ Keyboard accessible (Tab/Enter), ☐ Screen reader tested, ☐ Focus visible 3-4px, ☐ No color-only indicators, ☐ Haptic fallback","--contrast-ratio: 7:1, --font-size: 16px+, --keyboard-accessible: true, --sr-compatible: true, --wcag-level: AAA, --color-symbols: true, --haptic: enabled"
+18,Zero Interface,General,"Minimal visible UI, voice-first, gesture-based, AI-driven, invisible controls, predictive, context-aware, ambient","Neutral backgrounds: Soft white #FAFAFA, light grey #F0F0F0, warm off-white #F5F1E8","Subtle feedback: light green, light red, minimal UI elements, soft accents","Voice recognition UI, gesture detection, AI predictions (smooth reveal), progressive disclosure, smart suggestions","Voice assistants, AI platforms, future-forward UX, smart home, contextual computing, ambient experiences","Complex workflows, data-entry heavy, traditional systems, legacy support, explicit control",✓ Full,✓ Full,⚡ Excellent,✓ Excellent,✓ High,✓ High,"Tailwind 10/10, Custom 10/10",2020s AI-Era,Low,"Create a voice-first, gesture-based, AI-driven interface with minimal visible UI, progressive disclosure, voice recognition UI, gesture detection, AI predictions, smart suggestions, context-aware actions. Hide controls until needed.","voice-commands: Web Speech API, gesture-detection: touch events, AI-predictions: hidden by default (reveal on hover), progressive-disclosure: show on demand, minimal UI visible","☐ Voice commands responsive, ☐ Gesture detection active, ☐ AI predictions hidden/revealed, ☐ Progressive disclosure working, ☐ Minimal visible UI, ☐ Smart suggestions contextual","--voice-ui: enabled, --gesture-detection: active, --ai-predictions: smart, --progressive-disclosure: true, --visible-ui: minimal, --context-aware: true"
+19,Soft UI Evolution,General,"Evolved soft UI, better contrast, modern aesthetics, subtle depth, accessibility-focused, improved shadows, hybrid","Improved contrast pastels: Soft Blue #87CEEB, Soft Pink #FFB6C1, Soft Green #90EE90, better hierarchy","Better combinations, accessible secondary, supporting with improved contrast, modern accents","Improved shadows (softer than flat, clearer than neumorphism), modern (200-300ms), focus visible, WCAG AA/AAA","Modern enterprise apps, SaaS platforms, health/wellness, modern business tools, professional, hybrid","Extreme minimalism, critical performance, systems without modern OS",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA+,✓ High,✓ High,"Tailwind 9/10, MUI 9/10, Chakra 9/10",2020s Modern,Medium,"Design evolved neumorphism with improved contrast (WCAG AA+), modern aesthetics, subtle depth, accessibility focus. Use soft shadows (softer than flat but clearer than pure neumorphism), better color hierarchy, improved focus states, modern 200-300ms animations.","box-shadow: softer multi-layer (0 2px 4px), background: improved contrast pastels, border-radius: 8-12px, animation: 200-300ms smooth, outline: 2-3px on focus, contrast: 4.5:1+","☐ Improved contrast AA/AAA, ☐ Soft shadows modern, ☐ Border-radius 8-12px, ☐ Animations 200-300ms, ☐ Focus states visible, ☐ Color hierarchy clear","--shadow-soft: modern blend, --border-radius: 10px, --animation-duration: 200-300ms, --contrast-ratio: 4.5:1+, --color-hierarchy: improved, --wcag-level: AA+"
+20,Hero-Centric Design,Landing Page,"Large hero section, compelling headline, high-contrast CTA, product showcase, value proposition, hero image/video, dramatic visual","Brand primary color, white/light backgrounds for contrast, accent color for CTA","Supporting colors for secondary CTAs, accent highlights, trust elements (testimonials, logos)","Smooth scroll reveal, fade-in animations on hero, subtle background parallax, CTA glow/pulse effect","SaaS landing pages, product launches, service landing pages, B2B platforms, tech companies","Complex navigation, multi-page experiences, data-heavy applications",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,✓ Full,✓ Very High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a hero-centric landing page. Use: full-width hero section, compelling headline (60-80 chars), high-contrast CTA button, product screenshot or video, value proposition above fold, gradient or image background, clear visual hierarchy.","min-height: 100vh, display: flex, align-items: center, background: linear-gradient or image, text-shadow for readability, max-width: 800px for text, button with hover scale (1.05)","☐ Hero section full viewport height, ☐ Headline visible above fold, ☐ CTA button high contrast, ☐ Background image optimized (WebP), ☐ Text readable on background, ☐ Mobile responsive layout","--hero-min-height: 100vh, --headline-size: clamp(2rem, 5vw, 4rem), --cta-padding: 1rem 2rem, --overlay-opacity: 0.5, --text-shadow: 0 2px 4px rgba(0,0,0,0.3)"
+21,Conversion-Optimized,Landing Page,"Form-focused, minimalist design, single CTA focus, high contrast, urgency elements, trust signals, social proof, clear value","Primary brand color, high-contrast white/light backgrounds, warning/urgency colors for time-limited offers","Secondary CTA color (muted), trust element colors (testimonial highlights), accent for key benefits","Hover states on CTA (color shift, slight scale), form field focus animations, loading spinner, success feedback","E-commerce product pages, free trial signups, lead generation, SaaS pricing pages, limited-time offers","Complex feature explanations, multi-product showcases, technical documentation",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ Full (mobile-optimized),✓ Very High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a conversion-optimized landing page. Use: single primary CTA, minimal distractions, trust badges, urgency elements (limited time), social proof (testimonials), clear value proposition, form above fold, progress indicators.","form with focus states, input:focus ring, button: primary color high contrast, position: sticky for CTA, max-width: 600px for form, loading spinner, success/error states","☐ Single primary CTA visible, ☐ Form fields minimal (3-5), ☐ Trust badges present, ☐ Social proof above fold, ☐ Mobile form optimized, ☐ Loading states implemented, ☐ A/B test ready","--cta-color: high contrast primary, --form-max-width: 600px, --input-height: 48px, --focus-ring: 3px solid accent, --success-color: #22C55E, --error-color: #EF4444"
+22,Feature-Rich Showcase,Landing Page,"Multiple feature sections, grid layout, benefit cards, visual feature demonstrations, interactive elements, problem-solution pairs","Primary brand, bright secondary colors for feature cards, contrasting accent for CTAs","Supporting colors for: benefits (green), problems (red/orange), features (blue/purple), social proof (neutral)","Card hover effects (lift/scale), icon animations on scroll, feature toggle animations, smooth section transitions","Enterprise SaaS, software tools landing pages, platform services, complex product explanations, B2B products","Simple product pages, early-stage startups with few features, entertainment landing pages",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,✓ Good,✓ High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a feature showcase landing page. Use: grid layout for features (3-4 columns), feature cards with icons, benefit-focused copy, alternating sections, comparison tables, interactive demos, problem-solution pairs.","display: grid, grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)), gap: 2rem, card hover effects (translateY -4px), icon containers, alternating background colors","☐ Feature grid responsive, ☐ Icons consistent style, ☐ Card hover effects smooth, ☐ Alternating sections contrast, ☐ Benefits clearly stated, ☐ Mobile stacks properly","--card-padding: 2rem, --card-radius: 12px, --icon-size: 48px, --grid-gap: 2rem, --section-padding: 4rem 0, --hover-transform: translateY(-4px)"
+23,Minimal & Direct,Landing Page,"Minimal text, white space heavy, single column layout, direct messaging, clean typography, visual-centric, fast-loading","Monochromatic primary, white background, single accent color for CTA, black/dark grey text","Minimal secondary colors, reserved for critical CTAs only, neutral supporting elements","Very subtle hover effects, minimal animations, fast page load (no heavy animations), smooth scroll","Simple service landing pages, indie products, consulting services, micro SaaS, freelancer portfolios","Feature-heavy products, complex explanations, multi-product showcases",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ Full,✓ High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a minimal direct landing page. Use: single column layout, maximum white space, essential content only, one CTA, clean typography, no decorative elements, fast loading, direct messaging.","max-width: 680px, margin: 0 auto, padding: 4rem 2rem, font-size: 18-20px, line-height: 1.6, minimal animations, no box-shadow, clean borders only","☐ Single column centered, ☐ White space generous, ☐ One primary CTA only, ☐ No decorative images, ☐ Page weight < 500KB, ☐ Load time < 2s","--content-max-width: 680px, --spacing-large: 4rem, --font-size-body: 18px, --line-height: 1.6, --color-text: #1a1a1a, --color-bg: #ffffff"
+24,Social Proof-Focused,Landing Page,"Testimonials prominent, client logos displayed, case studies sections, reviews/ratings, user avatars, success metrics, credibility markers","Primary brand, trust colors (blue), success/growth colors (green), neutral backgrounds","Testimonial highlight colors, logo grid backgrounds (light grey), badge/achievement colors","Testimonial carousel animations, logo grid fade-in, stat counter animations (number count-up), review star ratings","B2B SaaS, professional services, premium products, e-commerce conversion pages, established brands","Startup MVPs, products without users, niche/experimental products",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,✓ Full,✓ High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a social proof landing page. Use: testimonials with photos, client logos grid, case study cards, review ratings (stars), user count metrics, success stories, trust indicators, before/after comparisons.","testimonial cards with avatar, logo grid (grayscale filter), star rating SVGs, counter animations (count-up), blockquote styling, carousel for testimonials, metric cards","☐ Testimonials with real photos, ☐ Logo grid 6-12 logos, ☐ Star ratings accessible, ☐ Metrics animated on scroll, ☐ Case studies linked, ☐ Mobile carousel works","--avatar-size: 64px, --logo-height: 40px, --star-color: #FBBF24, --metric-font-size: 3rem, --testimonial-bg: #F9FAFB, --blockquote-border: 4px solid accent"
+25,Interactive Product Demo,Landing Page,"Embedded product mockup/video, interactive elements, product walkthrough, step-by-step guides, hover-to-reveal features, embedded demos","Primary brand, interface colors matching product, demo highlight colors for interactive elements","Product UI colors, tutorial step colors (numbered progression), hover state indicators","Product animation playback, step progression animations, hover reveal effects, smooth zoom on interaction","SaaS platforms, tool/software products, productivity apps landing pages, developer tools, productivity software","Simple services, consulting, non-digital products, complexity-averse audiences",✓ Full,✓ Full,⚠ Good (video/interactive),✓ WCAG AA,✓ Good,✓ Very High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design an interactive demo landing page. Use: embedded product mockup, video walkthrough, step-by-step guide, hover-to-reveal features, live demo button, screenshot carousel, feature highlights on interaction.","video element with controls, position: relative for overlays, hover reveal (opacity transition), step indicators, modal for full demo, screenshot lightbox, play button overlay","☐ Demo video loads fast, ☐ Fallback for no-JS, ☐ Step indicators clear, ☐ Hover states obvious, ☐ Mobile touch friendly, ☐ Demo CTA prominent","--video-aspect-ratio: 16/9, --overlay-bg: rgba(0,0,0,0.7), --step-indicator-size: 32px, --play-button-size: 80px, --transition-duration: 300ms"
+26,Trust & Authority,Landing Page,"Certificates/badges displayed, expert credentials, case studies with metrics, before/after comparisons, industry recognition, security badges","Professional colors (blue/grey), trust colors, certification badge colors (gold/silver accents)","Certificate highlight colors, metric showcase colors, comparison highlight (success green)","Badge hover effects, metric pulse animations, certificate carousel, smooth stat reveal","Healthcare/medical landing pages, financial services, enterprise software, premium/luxury products, legal services","Casual products, entertainment, viral/social-first products",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ Full,✓ High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a trust-focused landing page. Use: certification badges, security indicators, expert credentials, industry awards, case study metrics, compliance logos (GDPR, SOC2), guarantee badges, professional photography.","badge grid layout, shield icons, lock icons for security, certificate styling, metric cards with icons, professional color scheme (blue/grey), subtle shadows for depth","☐ Security badges visible, ☐ Certifications verified, ☐ Metrics with sources, ☐ Professional imagery, ☐ Guarantee clearly stated, ☐ Contact info accessible","--badge-height: 48px, --trust-color: #1E40AF, --security-green: #059669, --card-shadow: 0 4px 6px rgba(0,0,0,0.1), --metric-highlight: #F59E0B"
+27,Storytelling-Driven,Landing Page,"Narrative flow, visual story progression, section transitions, consistent character/brand voice, emotional messaging, journey visualization","Brand primary, warm/emotional colors, varied accent colors per story section, high visual variety","Story section color coding, emotional state colors (calm, excitement, success), transitional gradients","Section-to-section animations, scroll-triggered reveals, character/icon animations, morphing transitions, parallax narrative","Brand/startup stories, mission-driven products, premium/lifestyle brands, documentary-style products, educational","Technical/complex products (unless narrative-driven), traditional enterprise software",✓ Full,✓ Full,⚠ Moderate (animations),✓ WCAG AA,✓ Good,✓ High,"Tailwind 10/10, Bootstrap 9/10",2020s Modern,Medium,"Design a storytelling landing page. Use: narrative flow sections, scroll-triggered reveals, chapter-like structure, emotional imagery, brand journey visualization, founder story, mission statement, timeline progression.","scroll-snap sections, Intersection Observer for reveals, parallax backgrounds, section transitions, timeline CSS, narrative typography (varied sizes), image-text alternating","☐ Story flows naturally, ☐ Scroll reveals smooth, ☐ Sections timed well, ☐ Emotional hooks present, ☐ Mobile story readable, ☐ Skip option available","--section-min-height: 100vh, --reveal-duration: 600ms, --narrative-font: serif, --chapter-spacing: 8rem, --timeline-color: accent, --parallax-speed: 0.5"
+28,Data-Dense Dashboard,BI/Analytics,"Multiple charts/widgets, data tables, KPI cards, minimal padding, grid layout, space-efficient, maximum data visibility","Neutral primary (light grey/white #F5F5F5), data colors (blue/green/red), dark text #333333","Chart colors: success (green #22C55E), warning (amber #F59E0B), alert (red #EF4444), neutral (grey)","Hover tooltips, chart zoom on click, row highlighting on hover, smooth filter animations, data loading spinners","Business intelligence dashboards, financial analytics, enterprise reporting, operational dashboards, data warehousing","Marketing dashboards, consumer-facing analytics, simple reporting",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a data-dense dashboard. Use: multiple chart widgets, KPI cards row, data tables with sorting, minimal padding (8-12px), efficient grid layout, filter sidebar, dense but readable typography, maximum information density.","display: grid, grid-template-columns: repeat(12, 1fr), gap: 8px, padding: 12px, font-size: 12-14px, overflow: auto for tables, compact card design, sticky headers","☐ Grid layout 12 columns, ☐ KPI cards responsive, ☐ Tables sortable, ☐ Filters functional, ☐ Loading states for data, ☐ Export functionality","--grid-gap: 8px, --card-padding: 12px, --font-size-small: 12px, --table-row-height: 36px, --sidebar-width: 240px, --header-height: 56px"
+29,Heat Map & Heatmap Style,BI/Analytics,"Color-coded grid/matrix, data intensity visualization, geographical heat maps, correlation matrices, cell-based representation, gradient coloring","Gradient scale: Cool (blue #0080FF) to hot (red #FF0000), neutral middle (white/yellow)","Support gradients: Light (cool blue) to dark (warm red), divergent for positive/negative data, monochromatic options","Color gradient transitions on data change, cell highlighting on hover, tooltip reveal on click, smooth color animation","Geographical analysis, performance matrices, correlation analysis, user behavior heatmaps, temperature/intensity data","Linear data representation, categorical comparisons (use bar charts), small datasets",✓ Full,✓ Full (with adjustments),⚡ Excellent,⚠ Colorblind considerations,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a heatmap visualization. Use: color gradient scale (cool to hot), cell-based grid, intensity legend, hover tooltips, geographic or matrix layout, divergent color scheme for +/- values, accessible color alternatives.","display: grid, background: linear-gradient for legend, cell hover states, tooltip positioning, color scale (blue→white→red), SVG for geographic, canvas for large datasets","☐ Color scale clear, ☐ Legend visible, ☐ Tooltips informative, ☐ Colorblind alternatives, ☐ Zoom/pan for geo, ☐ Performance for large data","--heatmap-cool: #0080FF, --heatmap-neutral: #FFFFFF, --heatmap-hot: #FF0000, --cell-size: 24px, --legend-width: 200px, --tooltip-bg: rgba(0,0,0,0.9)"
+30,Executive Dashboard,BI/Analytics,"High-level KPIs, large key metrics, minimal detail, summary view, trend indicators, at-a-glance insights, executive summary","Brand colors, professional palette (blue/grey/white), accent for KPIs, red for alerts/concerns","KPI highlight colors: positive (green), negative (red), neutral (grey), trend arrow colors","KPI value animations (count-up), trend arrow direction animations, metric card hover lift, alert pulse effect","C-suite dashboards, business summary reports, decision-maker dashboards, strategic planning views","Detailed analyst dashboards, technical deep-dives, operational monitoring",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✗ Low (not mobile-optimized),✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design an executive dashboard. Use: large KPI cards (4-6 max), trend sparklines, high-level summary only, clean layout with white space, traffic light indicators (red/yellow/green), at-a-glance insights, minimal detail.","display: flex for KPI row, large font-size (24-48px) for metrics, sparkline SVG inline, status indicators (border-left color), card shadows for hierarchy, responsive breakpoints","☐ KPIs 4-6 maximum, ☐ Trends visible, ☐ Status colors clear, ☐ One-page view, ☐ Mobile simplified, ☐ Print-friendly layout","--kpi-font-size: 48px, --sparkline-height: 32px, --status-green: #22C55E, --status-yellow: #F59E0B, --status-red: #EF4444, --card-min-width: 280px"
+31,Real-Time Monitoring,BI/Analytics,"Live data updates, status indicators, alert notifications, streaming data visualization, active monitoring, streaming charts","Alert colors: critical (red #FF0000), warning (orange #FFA500), normal (green #22C55E), updating (blue animation)","Status indicator colors, chart line colors varying by metric, streaming data highlight colors","Real-time chart animations, alert pulse/glow, status indicator blink animation, smooth data stream updates, loading effect","System monitoring dashboards, DevOps dashboards, real-time analytics, stock market dashboards, live event tracking","Historical analysis, long-term trend reports, archived data dashboards",✓ Full,✓ Full,⚡ Good (real-time load),✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a real-time monitoring dashboard. Use: live status indicators (pulsing), streaming charts, alert notifications, connection status, auto-refresh indicators, critical alerts prominent, system health overview.","animation: pulse for live, WebSocket for streaming, position: fixed for alerts, status-dot with animation, chart real-time updates, notification toast, connection indicator","☐ Live updates working, ☐ Alert sounds optional, ☐ Connection status shown, ☐ Auto-refresh indicated, ☐ Critical alerts prominent, ☐ Offline fallback","--pulse-animation: pulse 2s infinite, --alert-z-index: 1000, --live-indicator: #22C55E, --critical-color: #DC2626, --update-interval: 5s, --toast-duration: 5s"
+32,Drill-Down Analytics,BI/Analytics,"Hierarchical data exploration, expandable sections, interactive drill-down paths, summary-to-detail flow, context preservation","Primary brand, breadcrumb colors, drill-level indicator colors, hierarchy depth colors","Drill-down path indicator colors, level-specific colors, highlight colors for selected level, transition colors","Drill-down expand animations, breadcrumb click transitions, smooth detail reveal, level change smooth, data reload animation","Sales analytics, product analytics, funnel analysis, multi-dimensional data exploration, business intelligence","Simple linear data, single-metric dashboards, streaming real-time dashboards",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a drill-down analytics dashboard. Use: breadcrumb navigation, expandable sections, summary-to-detail flow, back button prominent, level indicators, context preservation, hierarchical data display.","breadcrumb nav with separators, details/summary for expand, transition for drill animation, position: sticky breadcrumb, nested grid layouts, smooth scroll to detail","☐ Breadcrumbs clear, ☐ Back navigation easy, ☐ Expand animation smooth, ☐ Context preserved, ☐ Mobile drill works, ☐ Deep links supported","--breadcrumb-separator: /, --expand-duration: 300ms, --level-indent: 24px, --back-button-size: 40px, --context-bar-height: 48px, --drill-transition: 300ms ease"
+33,Comparative Analysis Dashboard,BI/Analytics,"Side-by-side comparisons, period-over-period metrics, A/B test results, regional comparisons, performance benchmarks","Comparison colors: primary (blue), comparison (orange/purple), delta indicator (green/red)","Winning metric color (green), losing metric color (red), neutral comparison (grey), benchmark colors","Comparison bar animations (grow to value), delta indicator animations (direction arrows), highlight on compare","Period-over-period reporting, A/B test dashboards, market comparison, competitive analysis, regional performance","Single metric dashboards, future projections (use forecasting), real-time only (no historical)",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a comparison dashboard. Use: side-by-side metrics, period selectors (vs last month), delta indicators (+/-), benchmark lines, A/B comparison tables, winning/losing highlights, percentage change badges.","display: flex for side-by-side, gap for comparison spacing, color coding (green up, red down), arrow indicators, diff highlighting, comparison table zebra striping","☐ Period selector works, ☐ Deltas calculated, ☐ Colors meaningful, ☐ Benchmarks shown, ☐ Mobile stacks properly, ☐ Export comparison","--positive-color: #22C55E, --negative-color: #EF4444, --neutral-color: #6B7280, --comparison-gap: 2rem, --arrow-size: 16px, --badge-padding: 4px 8px"
+34,Predictive Analytics,BI/Analytics,"Forecast lines, confidence intervals, trend projections, scenario modeling, AI-driven insights, anomaly detection visualization","Forecast line color (distinct from actual), confidence interval shading, anomaly highlight (red alert), trend colors","High confidence (dark color), low confidence (light color), anomaly colors (red/orange), normal trend (green/blue)","Forecast line animation on draw, confidence band fade-in, anomaly pulse alert, smoothing function animations","Forecasting dashboards, anomaly detection systems, trend prediction dashboards, AI-powered analytics, budget planning","Historical-only dashboards, simple reporting, real-time operational dashboards",✓ Full,✓ Full,⚠ Good (computation),✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a predictive analytics dashboard. Use: forecast lines (dashed), confidence intervals (shaded bands), trend projections, anomaly highlights, scenario toggles, AI insight cards, probability indicators.","stroke-dasharray for forecast lines, fill-opacity for confidence bands, anomaly markers (circles), tooltip for predictions, toggle switches for scenarios, gradient for probability","☐ Forecast line distinct, ☐ Confidence bands visible, ☐ Anomalies highlighted, ☐ Scenarios switchable, ☐ Predictions dated, ☐ Accuracy shown","--forecast-dash: 5 5, --confidence-opacity: 0.2, --anomaly-color: #F59E0B, --prediction-color: #8B5CF6, --scenario-toggle-width: 48px, --ai-accent: #6366F1"
+35,User Behavior Analytics,BI/Analytics,"Funnel visualization, user flow diagrams, conversion tracking, engagement metrics, user journey mapping, cohort analysis","Funnel stage colors: high engagement (green), drop-off (red), conversion (blue), user flow arrows (grey)","Stage completion colors (success), abandonment colors (warning), engagement levels (gradient), cohort colors","Funnel animation (fill-down), flow diagram animations (connection draw), conversion pulse, engagement bar fill","Conversion funnel analysis, user journey tracking, engagement analytics, cohort analysis, retention tracking","Real-time operational metrics, technical system monitoring, financial transactions",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,✓ Good,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a user behavior analytics dashboard. Use: funnel visualization, user flow diagrams (Sankey), conversion metrics, engagement heatmaps, cohort tables, retention curves, session replay indicators.","SVG funnel with gradients, Sankey diagram library, percentage labels, cohort grid cells, retention chart (line/area), click heatmap overlay, session timeline","☐ Funnel stages clear, ☐ Flow diagram readable, ☐ Conversions calculated, ☐ Cohorts comparable, ☐ Retention trends visible, ☐ Privacy compliant","--funnel-width: 100%, --stage-colors: gradient, --flow-opacity: 0.6, --cohort-cell-size: 40px, --retention-line-color: #3B82F6, --engagement-scale: 5 levels"
+36,Financial Dashboard,BI/Analytics,"Revenue metrics, profit/loss visualization, budget tracking, financial ratios, portfolio performance, cash flow, audit trail","Financial colors: profit (green #22C55E), loss (red #EF4444), neutral (grey), trust (dark blue #003366)","Revenue highlight (green), expenses (red), budget variance (orange/red), balance (grey), accuracy (blue)","Number animations (count-up), trend direction indicators, percentage change animations, profit/loss color transitions","Financial reporting, accounting dashboards, portfolio tracking, budget monitoring, banking analytics","Simple business dashboards, entertainment/social metrics, non-financial data",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✗ Low,✗ Not applicable,"Recharts 9/10, Chart.js 9/10, D3.js 10/10",2020s Modern,Medium,"Design a financial dashboard. Use: revenue/expense charts, profit margins, budget vs actual, cash flow waterfall, financial ratios, audit trail table, currency formatting, period comparisons.","number formatting (Intl.NumberFormat), waterfall chart (positive/negative bars), variance coloring, table with totals row, sparkline for trends, sticky column headers","☐ Currency formatted, ☐ Decimals consistent, ☐ P&L clear, ☐ Budget variance shown, ☐ Audit trail complete, ☐ Export to Excel","--currency-symbol: $, --decimal-places: 2, --profit-color: #22C55E, --loss-color: #EF4444, --variance-threshold: 10%, --table-header-bg: #F3F4F6"
+37,Sales Intelligence Dashboard,BI/Analytics,"Deal pipeline, sales metrics, territory performance, sales rep leaderboard, win-loss analysis, quota tracking, forecast accuracy","Sales colors: won (green), lost (red), in-progress (blue), blocked (orange), quota met (gold), quota missed (grey)","Pipeline stage colors, rep performance colors, quota achievement colors, forecast accuracy colors","Deal movement animations, metric updates, leaderboard ranking changes, gauge needle movements, status change highlights","CRM dashboards, sales management, opportunity tracking, performance management, quota planning","Marketing analytics, customer support metrics, HR dashboards",✓ Full,✓ Full,⚡ Good,✓ WCAG AA,◐ Medium,✗ Not applicable,"Recharts 9/10, Chart.js 9/10",2020s Modern,Medium,"Design a sales intelligence dashboard. Use: pipeline funnel, deal cards (kanban), quota gauges, leaderboard table, territory map, win/loss ratios, forecast accuracy, activity timeline.","kanban columns (flex), gauge chart (SVG arc), leaderboard ranking styles, map integration (Mapbox/Google), timeline vertical, deal card with status border","☐ Pipeline stages shown, ☐ Deals draggable, ☐ Quotas visualized, ☐ Rankings updated, ☐ Territory clickable, ☐ CRM integration","--pipeline-colors: stage gradient, --gauge-track: #E5E7EB, --gauge-fill: primary, --rank-1-color: #FFD700, --rank-2-color: #C0C0C0, --rank-3-color: #CD7F32"
+38,Neubrutalism,General,"Bold borders, black outlines, primary colors, thick shadows, no gradients, flat colors, 45° shadows, playful, Gen Z","#FFEB3B (Yellow), #FF5252 (Red), #2196F3 (Blue), #000000 (Black borders)","Limited accent colors, high contrast combinations, no gradients allowed","box-shadow: 4px 4px 0 #000, border: 3px solid #000, no gradients, sharp corners (0px), bold typography","Gen Z brands, startups, creative agencies, Figma-style apps, Notion-style interfaces, tech blogs","Luxury brands, finance, healthcare, conservative industries (too playful)",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ High,"Tailwind 10/10, Bootstrap 8/10",2020s Modern,Low,"Design a neubrutalist interface. Use: high contrast, hard black borders (3px+), bright pop colors, no blur, sharp or slightly rounded corners, bold typography, hard shadows (offset 4px 4px), raw aesthetic but functional.","border: 3px solid black, box-shadow: 5px 5px 0px black, colors: #FFDB58 #FF6B6B #4ECDC4, font-weight: 700, no gradients","☐ Hard borders (2-4px), ☐ Hard offset shadows, ☐ High saturation colors, ☐ Bold typography, ☐ No blurs/gradients, ☐ Distinctive 'ugly-cute' look","--border-width: 3px, --shadow-offset: 4px, --shadow-color: #000, --colors: high saturation, --font: bold sans"
+39,Bento Box Grid,General,"Modular cards, asymmetric grid, varied sizes, Apple-style, dashboard tiles, negative space, clean hierarchy, cards","Neutral base + brand accent, #FFFFFF, #F5F5F5, brand primary","Subtle gradients, shadow variations, accent highlights for interactive cards","grid-template with varied spans, rounded-xl (16px), subtle shadows, hover scale (1.02), smooth transitions","Dashboards, product pages, portfolios, Apple-style marketing, feature showcases, SaaS","Dense data tables, text-heavy content, real-time monitoring",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"Tailwind 10/10, CSS Grid 10/10",2020s Apple,Low,"Design a Bento Box grid layout. Use: modular cards with varied sizes (1x1, 2x1, 2x2), Apple-style aesthetic, rounded corners (16-24px), soft shadows, clean hierarchy, asymmetric grid, neutral backgrounds (#F5F5F7), hover effects.","display: grid, grid-template-columns: repeat(4, 1fr), grid-auto-rows: 200px, gap: 16px, border-radius: 24px, background: #FFFFFF, box-shadow: 0 4px 6px rgba(0,0,0,0.05)","☐ Grid responsive (4→2→1 cols), ☐ Card spans varied, ☐ Rounded corners consistent, ☐ Shadows subtle, ☐ Content fits cards, ☐ Hover scale (1.02)","--grid-gap: 16px, --card-radius: 24px, --card-bg: #FFFFFF, --page-bg: #F5F5F7, --shadow: 0 4px 6px rgba(0,0,0,0.05), --hover-scale: 1.02"
+40,Y2K Aesthetic,General,"Neon pink, chrome, metallic, bubblegum, iridescent, glossy, retro-futurism, 2000s, futuristic nostalgia","#FF69B4 (Hot Pink), #00FFFF (Cyan), #C0C0C0 (Silver), #9400D3 (Purple)","Metallic gradients, glossy overlays, iridescent effects, chrome textures","linear-gradient metallic, glossy buttons, 3D chrome effects, glow animations, bubble shapes","Fashion brands, music platforms, Gen Z brands, nostalgia marketing, entertainment, youth-focused","B2B enterprise, healthcare, finance, conservative industries, elderly users",✓ Full,◐ Partial,⚠ Good,⚠ Check contrast,✓ Good,✓ High,"Tailwind 8/10, CSS-in-JS 9/10",Y2K 2000s,Medium,"Design a Y2K aesthetic interface. Use: neon pink/cyan colors, chrome/metallic textures, bubblegum gradients, glossy buttons, iridescent effects, 2000s futurism, star/sparkle decorations, bubble shapes, tech-optimistic vibe.","background: linear-gradient(135deg, #FF69B4, #00FFFF), filter: drop-shadow for glow, border-radius: 50% for bubbles, metallic gradients (silver/chrome), text-shadow: neon glow, ::before for sparkles","☐ Neon colors balanced, ☐ Chrome effects visible, ☐ Glossy buttons styled, ☐ Bubble shapes decorative, ☐ Sparkle animations, ☐ Retro fonts loaded","--neon-pink: #FF69B4, --neon-cyan: #00FFFF, --chrome-silver: #C0C0C0, --glossy-gradient: linear-gradient(180deg, white 0%, transparent 50%), --glow-blur: 10px"
+41,Cyberpunk UI,General,"Neon, dark mode, terminal, HUD, sci-fi, glitch, dystopian, futuristic, matrix, tech noir","#00FF00 (Matrix Green), #FF00FF (Magenta), #00FFFF (Cyan), #0D0D0D (Dark)","Neon gradients, scanline overlays, glitch colors, terminal green accents","Neon glow (text-shadow), glitch animations (skew/offset), scanlines (::before overlay), terminal fonts","Gaming platforms, tech products, crypto apps, sci-fi applications, developer tools, entertainment","Corporate enterprise, healthcare, family apps, conservative brands, elderly users",✗ No,✓ Only,⚠ Moderate,⚠ Limited (dark+neon),◐ Medium,◐ Medium,"Tailwind 8/10, Custom CSS 10/10",2020s Cyberpunk,Medium,"Design a cyberpunk interface. Use: neon colors on dark (#0D0D0D), terminal/HUD aesthetic, glitch effects, scanlines overlay, matrix green accents, monospace fonts, angular shapes, dystopian tech feel.","background: #0D0D0D, color: #00FF00 or #FF00FF, font-family: monospace, text-shadow: 0 0 10px neon, animation: glitch (transform skew), ::before scanlines (repeating-linear-gradient)","☐ Dark background only, ☐ Neon accents visible, ☐ Glitch effect subtle, ☐ Scanlines optional, ☐ Monospace font, ☐ Terminal aesthetic","--bg-dark: #0D0D0D, --neon-green: #00FF00, --neon-magenta: #FF00FF, --neon-cyan: #00FFFF, --scanline-opacity: 0.1, --glitch-duration: 0.3s"
+42,Organic Biophilic,General,"Nature, organic shapes, green, sustainable, rounded, flowing, wellness, earthy, natural textures","#228B22 (Forest Green), #8B4513 (Earth Brown), #87CEEB (Sky Blue), #F5F5DC (Beige)","Natural gradients, earth tones, sky blues, organic textures, wood/stone colors","Rounded corners (16-24px), organic curves (border-radius variations), natural shadows, flowing SVG shapes","Wellness apps, sustainability brands, eco products, health apps, meditation, organic food brands","Tech-focused products, gaming, industrial, urban brands",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"Tailwind 10/10, CSS 10/10",2020s Sustainable,Low,"Design a biophilic organic interface. Use: nature-inspired colors (greens, browns), organic curved shapes, rounded corners (16-24px), natural textures (wood, stone), flowing SVG elements, wellness aesthetic, earthy palette.","border-radius: 16-24px (varied), background: earth tones, SVG organic shapes (blob), box-shadow: natural soft, color: #228B22 #8B4513 #87CEEB, texture overlays (subtle)","☐ Earth tones dominant, ☐ Organic curves present, ☐ Natural textures subtle, ☐ Green accents, ☐ Rounded everywhere, ☐ Calming feel","--forest-green: #228B22, --earth-brown: #8B4513, --sky-blue: #87CEEB, --cream-bg: #F5F5DC, --organic-radius: 24px, --shadow-soft: 0 8px 32px rgba(0,0,0,0.08)"
+43,AI-Native UI,General,"Chatbot, conversational, voice, assistant, agentic, ambient, minimal chrome, streaming text, AI interactions","Neutral + single accent, #6366F1 (AI Purple), #10B981 (Success), #F5F5F5 (Background)","Status indicators, streaming highlights, context card colors, subtle accent variations","Typing indicators (3-dot pulse), streaming text animations, pulse animations, context cards, smooth reveals","AI products, chatbots, voice assistants, copilots, AI-powered tools, conversational interfaces","Traditional forms, data-heavy dashboards, print-first content",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"Tailwind 10/10, React 10/10",2020s AI-Era,Low,"Design an AI-native interface. Use: minimal chrome, conversational layout, streaming text area, typing indicators (3-dot pulse), context cards, subtle AI accent color (#6366F1), clean input field, response bubbles.","chat bubble layout (flex-direction: column), typing animation (3 dots pulse), streaming text (overflow: hidden + animation), input: sticky bottom, context cards (border-left accent), minimal borders","☐ Chat layout responsive, ☐ Typing indicator smooth, ☐ Input always visible, ☐ Context cards styled, ☐ AI responses distinct, ☐ User messages aligned right","--ai-accent: #6366F1, --user-bubble-bg: #E0E7FF, --ai-bubble-bg: #F9FAFB, --input-height: 48px, --typing-dot-size: 8px, --message-gap: 16px"
+44,Memphis Design,General,"80s, geometric, playful, postmodern, shapes, patterns, squiggles, triangles, neon, abstract, bold","#FF71CE (Hot Pink), #FFCE5C (Yellow), #86CCCA (Teal), #6A7BB4 (Blue Purple)","Complementary geometric colors, pattern fills, contrasting accent shapes","transform: rotate(), clip-path: polygon(), mix-blend-mode, repeating patterns, bold shapes","Creative agencies, music sites, youth brands, event promotion, artistic portfolios, entertainment","Corporate finance, healthcare, legal, elderly users, conservative brands",✓ Full,✓ Full,⚡ Excellent,⚠ Check contrast,✓ Good,◐ Medium,"Tailwind 9/10, CSS 10/10",1980s Postmodern,Medium,"Design a Memphis style interface. Use: bold geometric shapes (triangles, squiggles, circles), bright clashing colors, 80s postmodern aesthetic, playful patterns, dotted textures, asymmetric layouts, decorative elements.","clip-path: polygon() for shapes, background: repeating patterns, transform: rotate() for tilted elements, mix-blend-mode for overlays, border: dashed/dotted patterns, bold sans-serif","☐ Geometric shapes visible, ☐ Colors bold/clashing, ☐ Patterns present, ☐ Layout asymmetric, ☐ Playful decorations, ☐ 80s vibe achieved","--memphis-pink: #FF71CE, --memphis-yellow: #FFCE5C, --memphis-teal: #86CCCA, --memphis-purple: #6A7BB4, --pattern-size: 20px, --shape-rotation: 15deg"
+45,Vaporwave,General,"Synthwave, retro-futuristic, 80s-90s, neon, glitch, nostalgic, sunset gradient, dreamy, aesthetic","#FF71CE (Pink), #01CDFE (Cyan), #05FFA1 (Mint), #B967FF (Purple)","Sunset gradients, glitch overlays, VHS effects, neon accents, pastel variations","text-shadow glow, linear-gradient, filter: hue-rotate(), glitch animations, retro scan lines","Music platforms, gaming, creative portfolios, tech startups, entertainment, artistic projects","Business apps, e-commerce, education, healthcare, enterprise software",✓ Full,✓ Dark focused,⚠ Moderate,⚠ Poor (motion),◐ Medium,◐ Medium,"Tailwind 8/10, CSS-in-JS 9/10",1980s-90s Retro,Medium,"Design a vaporwave aesthetic interface. Use: sunset gradients (pink/cyan/purple), 80s-90s nostalgia, glitch effects, Greek statue imagery, palm trees, grid patterns, neon glow, retro-futuristic feel, dreamy atmosphere.","background: linear-gradient(180deg, #FF71CE, #01CDFE, #B967FF), filter: hue-rotate(), text-shadow: neon glow, retro grid (perspective + linear-gradient), VHS scanlines","☐ Sunset gradient present, ☐ Neon glow applied, ☐ Retro grid visible, ☐ Glitch effects subtle, ☐ Dreamy atmosphere, ☐ 80s-90s aesthetic","--vapor-pink: #FF71CE, --vapor-cyan: #01CDFE, --vapor-mint: #05FFA1, --vapor-purple: #B967FF, --grid-color: rgba(255,255,255,0.1), --glow-intensity: 15px"
+46,Dimensional Layering,General,"Depth, overlapping, z-index, layers, 3D, shadows, elevation, floating, cards, spatial hierarchy","Neutral base (#FFFFFF, #F5F5F5, #E0E0E0) + brand accent for elevated elements","Shadow variations (sm/md/lg/xl), elevation colors, highlight colors for top layers","z-index stacking, box-shadow elevation (4 levels), transform: translateZ(), backdrop-filter, parallax","Dashboards, card layouts, modals, navigation, product showcases, SaaS interfaces","Print-style layouts, simple blogs, low-end devices, flat design requirements",✓ Full,✓ Full,⚠ Good,⚠ Moderate (SR issues),✓ Good,✓ High,"Tailwind 10/10, MUI 10/10, Chakra 10/10",2020s Modern,Medium,"Design with dimensional layering. Use: z-index depth (multiple layers), overlapping cards, elevation shadows (4 levels), floating elements, parallax depth, backdrop blur for hierarchy, spatial UI feel.","z-index: 1-4 levels, box-shadow: elevation scale (sm/md/lg/xl), transform: translateZ(), backdrop-filter: blur(), position: relative for stacking, parallax on scroll","☐ Layers clearly defined, ☐ Shadows show depth, ☐ Overlaps intentional, ☐ Hierarchy clear, ☐ Performance optimized, ☐ Mobile depth maintained","--elevation-1: 0 1px 3px rgba(0,0,0,0.1), --elevation-2: 0 4px 6px rgba(0,0,0,0.1), --elevation-3: 0 10px 20px rgba(0,0,0,0.1), --elevation-4: 0 20px 40px rgba(0,0,0,0.15), --blur-amount: 8px"
+47,Exaggerated Minimalism,General,"Bold minimalism, oversized typography, high contrast, negative space, loud minimal, statement design","#000000 (Black), #FFFFFF (White), single vibrant accent only","Minimal - single accent color, no secondary colors, extreme restraint","font-size: clamp(3rem 10vw 12rem), font-weight: 900, letter-spacing: -0.05em, massive whitespace","Fashion, architecture, portfolios, agency landing pages, luxury brands, editorial","E-commerce catalogs, dashboards, forms, data-heavy, elderly users, complex apps",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"Tailwind 10/10, Typography.js 10/10",2020s Modern,Low,"Design with exaggerated minimalism. Use: oversized typography (clamp 3rem-12rem), extreme negative space, black/white primary, single accent color only, bold statements, minimal elements, dramatic contrast.","font-size: clamp(3rem, 10vw, 12rem), font-weight: 900, letter-spacing: -0.05em, color: #000 or #FFF, padding: 8rem+, single accent, no decorations","☐ Typography oversized, ☐ White space extreme, ☐ Black/white dominant, ☐ Single accent only, ☐ Elements minimal, ☐ Statement clear","--type-giant: clamp(3rem, 10vw, 12rem), --type-weight: 900, --spacing-huge: 8rem, --color-primary: #000000, --color-bg: #FFFFFF, --accent: single color only"
+48,Kinetic Typography,General,"Motion text, animated type, moving letters, dynamic, typing effect, morphing, scroll-triggered text","Flexible - high contrast recommended, bold colors for emphasis, animation-friendly palette","Accent colors for emphasis, transition colors, gradient text fills","@keyframes text animation, typing effect, background-clip: text, GSAP ScrollTrigger, split text","Hero sections, marketing sites, video platforms, storytelling, creative portfolios, landing pages","Long-form content, accessibility-critical, data interfaces, forms, elderly users",✓ Full,✓ Full,⚠ Moderate,❌ Poor (motion),✓ Good,✓ Very High,"GSAP 10/10, Framer Motion 10/10",2020s Modern,High,"Design with kinetic typography. Use: animated text, scroll-triggered reveals, typing effects, letter-by-letter animations, morphing text, gradient text fills, oversized hero text, text as the main visual element.","@keyframes for text animation, background-clip: text, GSAP SplitText, typing effect (steps()), transform on letters, scroll-triggered (Intersection Observer), variable fonts for morphing","☐ Text animations smooth, ☐ Prefers-reduced-motion respected, ☐ Fallback for no-JS, ☐ Mobile performance ok, ☐ Typing effect timed, ☐ Scroll triggers work","--text-animation-duration: 1s, --letter-delay: 0.05s, --typing-speed: 100ms, --gradient-text: linear-gradient(90deg, #color1, #color2), --morph-duration: 0.5s"
+49,Parallax Storytelling,General,"Scroll-driven, narrative, layered scrolling, immersive, progressive disclosure, cinematic, scroll-triggered","Story-dependent, often gradients and natural colors, section-specific palettes","Section transition colors, depth layer colors, narrative mood colors","transform: translateY(scroll), position: fixed/sticky, perspective: 1px, scroll-triggered animations","Brand storytelling, product launches, case studies, portfolios, annual reports, marketing campaigns","E-commerce, dashboards, mobile-first, SEO-critical, accessibility-required",✓ Full,✓ Full,❌ Poor,❌ Poor (motion),✗ Low,✓ High,"GSAP ScrollTrigger 10/10, Locomotive Scroll 10/10",2020s Modern,High,"Design a parallax storytelling page. Use: scroll-driven narrative, layered backgrounds (3-5 layers), fixed/sticky sections, cinematic transitions, progressive disclosure, full-screen chapters, depth perception.","position: fixed/sticky, transform: translateY(calc()), perspective: 1px, z-index layering, scroll-snap-type, Intersection Observer for triggers, will-change: transform","☐ Layers parallax smoothly, ☐ Story flows naturally, ☐ Mobile alternative provided, ☐ Performance optimized, ☐ Skip option available, ☐ Reduced motion fallback","--parallax-speed-bg: 0.3, --parallax-speed-mid: 0.6, --parallax-speed-fg: 1, --section-height: 100vh, --transition-duration: 600ms, --perspective: 1px"
+50,Swiss Modernism 2.0,General,"Grid system, Helvetica, modular, asymmetric, international style, rational, clean, mathematical spacing","#000000, #FFFFFF, #F5F5F5, single vibrant accent only","Minimal secondary, accent for emphasis only, no gradients","display: grid, grid-template-columns: repeat(12 1fr), gap: 1rem, mathematical ratios, clear hierarchy","Corporate sites, architecture, editorial, SaaS, museums, professional services, documentation","Playful brands, children's sites, entertainment, gaming, emotional storytelling",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ High,"Tailwind 10/10, Bootstrap 9/10, Foundation 10/10",1950s Swiss + 2020s,Low,"Design with Swiss Modernism 2.0. Use: strict grid system (12 columns), Helvetica/Inter fonts, mathematical spacing, asymmetric balance, high contrast, minimal decoration, clean hierarchy, single accent color.","display: grid, grid-template-columns: repeat(12, 1fr), gap: 1rem (8px base unit), font-family: Inter/Helvetica, font-weight: 400-700, color: #000/#FFF, single accent","☐ 12-column grid strict, ☐ Spacing mathematical, ☐ Typography hierarchy clear, ☐ Single accent only, ☐ No decorations, ☐ High contrast verified","--grid-columns: 12, --grid-gap: 1rem, --base-unit: 8px, --font-primary: Inter, --color-text: #000000, --color-bg: #FFFFFF, --accent: single vibrant"
+51,HUD / Sci-Fi FUI,General,"Futuristic, technical, wireframe, neon, data, transparency, iron man, sci-fi, interface","Neon Cyan #00FFFF, Holographic Blue #0080FF, Alert Red #FF0000","Transparent Black, Grid Lines #333333","Glow effects, scanning animations, ticker text, blinking markers, fine line drawing","Sci-fi games, space tech, cybersecurity, movie props, immersive dashboards","Standard corporate, reading heavy content, accessible public services",✓ Low,✓ Full,⚠ Moderate (renders),⚠ Poor (thin lines),◐ Medium,✗ Low,"React 9/10, Canvas 10/10",2010s Sci-Fi,High,"Design a futuristic HUD (Heads Up Display) or FUI. Use: thin lines (1px), neon cyan/blue on black, technical markers, decorative brackets, data visualization, monospaced tech fonts, glowing elements, transparency.","border: 1px solid rgba(0,255,255,0.5), color: #00FFFF, background: transparent or rgba(0,0,0,0.8), font-family: monospace, text-shadow: 0 0 5px cyan","☐ Fine lines 1px, ☐ Neon glow text/borders, ☐ Monospaced font, ☐ Dark/Transparent BG, ☐ Decorative tech markers, ☐ Holographic feel","--hud-color: #00FFFF, --bg-color: rgba(0,10,20,0.9), --line-width: 1px, --glow: 0 0 5px, --font: monospace"
+52,Pixel Art,General,"Retro, 8-bit, 16-bit, gaming, blocky, nostalgic, pixelated, arcade","Primary colors (NES Palette), brights, limited palette","Black outlines, shading via dithering or block colors","Frame-by-frame sprite animation, blinking cursor, instant transitions, marquee text","Indie games, retro tools, creative portfolios, nostalgia marketing, Web3/NFT","Professional corporate, modern SaaS, high-res photography sites",✓ Full,✓ Full,⚡ Excellent,✓ Good (if contrast ok),✓ High,◐ Medium,"CSS (box-shadow) 8/10, Canvas 10/10",1980s Arcade,Medium,"Design a pixel art inspired interface. Use: pixelated fonts, 8-bit or 16-bit aesthetic, sharp edges (image-rendering: pixelated), limited color palette, blocky UI elements, retro gaming feel.","font-family: 'Press Start 2P', image-rendering: pixelated, box-shadow: 4px 0 0 #000 (pixel border), no anti-aliasing","☐ Pixelated fonts loaded, ☐ Images sharp (no blur), ☐ CSS box-shadow for pixel borders, ☐ Retro palette, ☐ Blocky layout","--pixel-size: 4px, --font: pixel font, --border-style: pixel-shadow, --anti-alias: none"
+53,Bento Grids,General,"Apple-style, modular, cards, organized, clean, hierarchy, grid, rounded, soft","Off-white #F5F5F7, Clean White #FFFFFF, Text #1D1D1F","Subtle accents, soft shadows, blurred backdrops","Hover scale (1.02), soft shadow expansion, smooth layout shifts, content reveal","Product features, dashboards, personal sites, marketing summaries, galleries","Long-form reading, data tables, complex forms",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"CSS Grid 10/10, Tailwind 10/10",2020s Apple/Linear,Low,"Design a Bento Grid layout. Use: modular grid system, rounded corners (16-24px), different card sizes (1x1, 2x1, 2x2), card-based hierarchy, soft backgrounds (#F5F5F7), subtle borders, content-first, Apple-style aesthetic.","display: grid, grid-template-columns: repeat(auto-fit, minmax(...)), gap: 1rem, border-radius: 20px, background: #FFF, box-shadow: subtle","☐ Grid layout (CSS Grid), ☐ Rounded corners 16-24px, ☐ Varied card spans, ☐ Content fits card size, ☐ Responsive re-flow, ☐ Apple-like aesthetic","--grid-gap: 20px, --card-radius: 24px, --card-bg: #FFFFFF, --page-bg: #F5F5F7, --shadow: soft"
+55,Spatial UI (VisionOS),General,"Glass, depth, immersion, spatial, translucent, gaze, gesture, apple, vision-pro","Frosted Glass #FFFFFF (15-30% opacity), System White","Vibrant system colors for active states, deep shadows for depth","Parallax depth, dynamic lighting response, gaze-hover effects, smooth scale on focus","Spatial computing apps, VR/AR interfaces, immersive media, futuristic dashboards","Text-heavy documents, high-contrast requirements, non-3D capable devices",✓ Full,✓ Full,⚠ Moderate (blur cost),⚠ Contrast risks,✓ High (if adapted),✓ High,"SwiftUI, React (Three.js/Fiber)",2024 Spatial Era,High,"Design a VisionOS-style spatial interface. Use: frosted glass panels, depth layers, translucent backgrounds (15-30% opacity), vibrant colors for active states, gaze-hover effects, floating windows, immersive feel.","backdrop-filter: blur(40px) saturate(180%), background: rgba(255,255,255,0.2), border-radius: 24px, box-shadow: 0 8px 32px rgba(0,0,0,0.1), transform: scale on focus, depth via shadows","☐ Glass effect visible, ☐ Depth layers clear, ☐ Hover states defined, ☐ Colors vibrant on active, ☐ Floating feel achieved, ☐ Contrast maintained","--glass-bg: rgba(255,255,255,0.2), --glass-blur: 40px, --glass-saturate: 180%, --window-radius: 24px, --depth-shadow: 0 8px 32px rgba(0,0,0,0.1), --focus-scale: 1.02"
+56,E-Ink / Paper,General,"Paper-like, matte, high contrast, texture, reading, calm, slow tech, monochrome","Off-White #FDFBF7, Paper White #F5F5F5, Ink Black #1A1A1A","Pencil Grey #4A4A4A, Highlighter Yellow #FFFF00 (accent)","No motion blur, distinct page turns, grain/noise texture, sharp transitions (no fade)","Reading apps, digital newspapers, minimal journals, distraction-free writing, slow-living brands","Gaming, video platforms, high-energy marketing, dark mode dependent apps",✓ Full,✗ Low (inverted only),⚡ Excellent,✓ WCAG AAA,✓ High,✓ Medium,"Tailwind 10/10, CSS 10/10",2020s Digital Well-being,Low,"Design an e-ink/paper style interface. Use: high contrast black on off-white, paper texture, no animations (instant transitions), reading-focused, minimal UI chrome, distraction-free, calm aesthetic, monochrome.","background: #FDFBF7 (paper white), color: #1A1A1A, transition: none, font-family: serif for reading, no gradients, border: 1px solid #E0E0E0, texture overlay (noise)","☐ Paper background color, ☐ High contrast text, ☐ No animations, ☐ Reading optimized, ☐ Distraction-free, ☐ Print-friendly","--paper-bg: #FDFBF7, --ink-color: #1A1A1A, --pencil-grey: #4A4A4A, --border-color: #E0E0E0, --font-reading: Georgia, --transition: none"
+57,Gen Z Chaos / Maximalism,General,"Chaos, clutter, stickers, raw, collage, mixed media, loud, internet culture, ironic","Clashing Brights: #FF00FF, #00FF00, #FFFF00, #0000FF","Gradients, rainbow, glitch, noise, heavily saturated mix","Marquee scrolls, jitter, sticker layering, GIF overload, random placement, drag-and-drop","Gen Z lifestyle brands, music artists, creative portfolios, viral marketing, fashion","Corporate, government, healthcare, banking, serious tools",✓ Full,✓ Full,⚠ Poor (heavy assets),❌ Poor,◐ Medium,✓ High (Viral),CSS-in-JS 8/10,2023+ Internet Core,High,"Design a Gen Z chaos maximalist interface. Use: clashing bright colors, sticker overlays, collage aesthetic, raw/unpolished feel, mixed media, ironic elements, loud typography, GIF-heavy, internet culture references.","mix-blend-mode: multiply/screen, transform: rotate(random), animation: jitter, marquee text, position: absolute for scattered elements, filter: saturate(150%), z-index chaos","☐ Colors clash intentionally, ☐ Stickers/overlays present, ☐ Layout chaotic but usable, ☐ GIFs optimized, ☐ Mobile scrollable, ☐ Performance acceptable","--chaos-pink: #FF00FF, --chaos-green: #00FF00, --chaos-yellow: #FFFF00, --chaos-blue: #0000FF, --jitter-amount: 5deg, --saturate: 150%"
+58,Biomimetic / Organic 2.0,General,"Nature-inspired, cellular, fluid, breathing, generative, algorithms, life-like","Cellular Pink #FF9999, Chlorophyll Green #00FF41, Bioluminescent Blue","Deep Ocean #001E3C, Coral #FF7F50, Organic gradients","Breathing animations, fluid morphing, generative growth, physics-based movement","Sustainability tech, biotech, advanced health, meditation, generative art platforms","Standard SaaS, data grids, strict corporate, accounting",✓ Full,✓ Full,⚠ Moderate,✓ Good,✓ Good,✓ High,"Canvas 10/10, WebGL 10/10",2024+ Generative,High,"Design a biomimetic organic interface. Use: cellular/fluid shapes, breathing animations, generative patterns, bioluminescent colors, physics-based movement, nature algorithms, life-like elements, flowing gradients.","SVG morphing (SMIL or GSAP), canvas for generative, animation: breathing (scale pulse), filter: blur for organic, clip-path for cellular, WebGL for advanced, physics libraries","☐ Organic shapes present, ☐ Animations feel alive, ☐ Generative elements, ☐ Performance monitored, ☐ Mobile fallback, ☐ Accessibility alt content","--cellular-pink: #FF9999, --chlorophyll: #00FF41, --bioluminescent: #00FFFF, --breathing-duration: 4s, --morph-ease: cubic-bezier(0.4, 0, 0.2, 1), --organic-blur: 20px"
+59,Anti-Polish / Raw Aesthetic,General,"Hand-drawn, collage, scanned textures, unfinished, imperfect, authentic, human, sketch, raw marks, creative process","Paper White #FAFAF8, Pencil Grey #4A4A4A, Marker Black #1A1A1A, Kraft Brown #C4A77D","Watercolor washes, pencil shading, ink splatters, tape textures, aged paper tones","No smooth transitions, hand-drawn animations, paper texture overlays, jitter effects, sketch reveal","Creative portfolios, artist sites, indie brands, handmade products, authentic storytelling, editorial","Corporate enterprise, fintech, healthcare, government, polished SaaS",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"CSS 10/10, SVG 10/10",2025+ Anti-Digital,Low,"Design with anti-polish raw aesthetic. Use: hand-drawn elements, scanned textures, unfinished look, paper/pencil textures, collage style, authentic imperfection, sketch marks, tape/sticker overlays, human touch.","background: url(paper-texture.png), filter: grayscale() contrast(), border: hand-drawn SVG, transform: rotate(small random), no smooth transitions, sketch-style fonts, opacity variations","☐ Textures loaded, ☐ Hand-drawn elements present, ☐ Imperfections intentional, ☐ Authentic feel achieved, ☐ Performance ok with textures, ☐ Accessibility maintained","--paper-bg: #FAFAF8, --pencil-color: #4A4A4A, --marker-black: #1A1A1A, --kraft-brown: #C4A77D, --sketch-rotation: random(-3deg, 3deg), --texture-opacity: 0.3"
+60,Tactile Digital / Deformable UI,General,"Jelly buttons, chrome, clay, squishy, deformable, bouncy, physical, tactile feedback, press response","Gradient metallics, Chrome Silver #C0C0C0, Jelly Pink #FF9ECD, Soft Blue #87CEEB","Glossy highlights, shadow depth, reflection effects, material-specific colors","Press deformation (scale + squish), bounce-back (cubic-bezier), material response, haptic-like feedback, spring physics","Modern mobile apps, playful brands, entertainment, gaming UI, consumer products, interactive demos","Enterprise software, data dashboards, accessibility-critical, professional tools",✓ Full,✓ Full,⚠ Good,⚠ Motion sensitive,✓ High,✓ Very High,"Framer Motion 10/10, React Spring 10/10, GSAP 10/10",2025+ Tactile Era,Medium,"Design a tactile deformable interface. Use: jelly/squishy buttons, press deformation effect, bounce-back animations, chrome/clay materials, spring physics, haptic-like feedback, material response, 3D depth on interaction.","transform: scale(0.95) on active, animation: bounce (cubic-bezier(0.34, 1.56, 0.64, 1)), box-shadow: inset for press, filter: brightness on press, spring physics (react-spring/framer-motion)","☐ Press effect visible, ☐ Bounce-back smooth, ☐ Material feels tactile, ☐ Spring physics tuned, ☐ Mobile touch responsive, ☐ Reduced motion option","--press-scale: 0.95, --bounce-duration: 400ms, --spring-stiffness: 300, --spring-damping: 20, --material-glossy: linear-gradient(135deg, white 0%, transparent 60%), --depth-shadow: 0 10px 30px rgba(0,0,0,0.2)"
+61,Nature Distilled,General,"Muted earthy, skin tones, wood, soil, sand, terracotta, warmth, organic materials, handmade warmth","Terracotta #C67B5C, Sand Beige #D4C4A8, Warm Clay #B5651D, Soft Cream #F5F0E1","Earth Brown #8B4513, Olive Green #6B7B3C, Warm Stone #9C8B7A, muted gradients","Subtle parallax, natural easing (ease-out), texture overlays, grain effects, soft shadows","Wellness brands, sustainable products, artisan goods, organic food, spa/beauty, home decor","Tech startups, gaming, nightlife, corporate finance, high-energy brands",✓ Full,◐ Partial,⚡ Excellent,✓ WCAG AA,✓ High,✓ High,"Tailwind 10/10, CSS 10/10",2025+ Handmade Warmth,Low,"Design with nature distilled aesthetic. Use: muted earthy colors (terracotta, sand, olive), organic materials feel, warm tones, handmade warmth, natural textures, artisan quality, sustainable vibe, soft gradients.","background: warm earth tones, color: #C67B5C #D4C4A8 #6B7B3C, border-radius: organic (varied), box-shadow: soft natural, texture overlays (grain), font: humanist sans-serif","☐ Earth tones dominant, ☐ Warm feel achieved, ☐ Textures subtle, ☐ Handmade quality, ☐ Sustainable messaging, ☐ Calming aesthetic","--terracotta: #C67B5C, --sand-beige: #D4C4A8, --warm-clay: #B5651D, --soft-cream: #F5F0E1, --olive-green: #6B7B3C, --grain-opacity: 0.1"
+62,Interactive Cursor Design,General,"Custom cursor, cursor as tool, hover effects, cursor feedback, pointer transformation, cursor trail, magnetic cursor","Brand-dependent, cursor accent color, high contrast for visibility","Trail colors, hover state colors, magnetic zone indicators, feedback colors","Cursor scale on hover, magnetic pull to elements, cursor morphing, trail effects, blend mode cursors, click feedback","Creative portfolios, interactive experiences, agency sites, product showcases, gaming, entertainment","Mobile-first (no cursor), accessibility-critical, data-heavy dashboards, forms",✓ Full,✓ Full,⚡ Good,⚠ Not for touch/SR,✗ No cursor,✓ High,"GSAP 10/10, Framer Motion 10/10, Custom JS 10/10",2025+ Interactive,Medium,"Design with interactive cursor effects. Use: custom cursor, cursor morphing on hover, magnetic cursor pull, cursor trails, blend mode cursors, click feedback animations, cursor as interaction tool, pointer transformation.","cursor: none (custom), position: fixed for cursor element, mix-blend-mode: difference, transform on hover targets, magnetic effect (JS position lerp), trail with opacity fade, scale on click","☐ Custom cursor works, ☐ Hover morph smooth, ☐ Magnetic pull subtle, ☐ Trail performance ok, ☐ Click feedback visible, ☐ Touch fallback provided","--cursor-size: 20px, --cursor-hover-scale: 1.5, --magnetic-distance: 100px, --trail-length: 10, --trail-fade: 0.1, --blend-mode: difference"
+63,Voice-First Multimodal,General,"Voice UI, multimodal, audio feedback, conversational, hands-free, ambient, contextual, speech recognition","Calm neutrals: Soft White #FAFAFA, Muted Blue #6B8FAF, Gentle Purple #9B8FBB","Audio waveform colors, status indicators (listening/processing/speaking), success/error tones","Voice waveform visualization, listening pulse, processing spinner, speak animation, smooth transitions","Voice assistants, accessibility apps, hands-free tools, smart home, automotive UI, cooking apps","Visual-heavy content, data entry, complex forms, noisy environments",✓ Full,✓ Full,⚡ Excellent,✓ Excellent,✓ High,✓ High,"Web Speech API 10/10, React 10/10",2025+ Voice Era,Medium,"Design a voice-first multimodal interface. Use: voice waveform visualization, listening state indicator, speaking animation, minimal visible UI, audio feedback cues, hands-free optimized, conversational flow, ambient design.","Web Speech API integration, canvas for waveform, animation: pulse for listening, status indicators (color change), audio visualization (Web Audio API), minimal chrome, large touch targets","☐ Voice recognition works, ☐ Visual feedback clear, ☐ Listening state obvious, ☐ Speaking animation smooth, ☐ Fallback UI provided, ☐ Accessibility excellent","--listening-color: #6B8FAF, --speaking-color: #22C55E, --waveform-height: 60px, --pulse-duration: 1.5s, --indicator-size: 24px, --voice-accent: #9B8FBB"
+64,3D Product Preview,General,"360 product view, rotatable, zoomable, touch-to-spin, AR preview, product configurator, interactive 3D model","Product-dependent, neutral backgrounds: Soft Grey #E8E8E8, Pure White #FFFFFF","Shadow gradients, reflection planes, environment lighting colors, accent highlights","Drag-to-rotate, pinch-to-zoom, spin animation, AR placement, material switching, smooth orbit controls","E-commerce, furniture, fashion, automotive, electronics, jewelry, product configurators","Content-heavy sites, blogs, dashboards, low-bandwidth, accessibility-critical",◐ Partial,◐ Partial,❌ Poor (3D rendering),⚠ Alt content needed,◐ Medium,✓ Very High,"Three.js 10/10, model-viewer 10/10, Spline 9/10",2025+ E-commerce 3D,High,"Design a 3D product preview interface. Use: 360° rotation, drag-to-spin, pinch-to-zoom, AR preview button, material/color switcher, hotspot annotations, orbit controls, product configurator, smooth rendering.","Three.js or model-viewer, OrbitControls, touch events for rotation, WebXR for AR, canvas with WebGL, loading placeholder, LOD for performance, environment lighting","☐ 3D model loads fast, ☐ Rotation smooth, ☐ Zoom works (pinch/scroll), ☐ AR button functional, ☐ Colors switchable, ☐ Mobile touch works","--canvas-bg: #F5F5F5, --hotspot-color: #3B82F6, --loading-spinner: primary, --rotation-speed: 0.5, --zoom-min: 0.5, --zoom-max: 2"
+65,Gradient Mesh / Aurora Evolved,General,"Complex gradients, mesh gradients, multi-color blend, aurora effect, flowing colors, iridescent, holographic, prismatic","Multi-stop gradients: Cyan #00FFFF, Magenta #FF00FF, Yellow #FFFF00, Blue #0066FF, Green #00FF66","Complementary mesh points, smooth color transitions, iridescent overlays, chromatic shifts","CSS mesh-gradient (experimental), SVG gradients, canvas gradients, smooth color morphing, flowing animation","Hero sections, backgrounds, creative brands, music platforms, fashion, lifestyle, premium products","Data interfaces, text-heavy content, accessibility-critical, conservative brands",✓ Full,✓ Full,⚠ Good,⚠ Text contrast,✓ Good,✓ High,"CSS 8/10, SVG 10/10, Canvas 10/10",2025+ Gradient Evolution,Medium,"Design with gradient mesh aurora effect. Use: multi-color mesh gradients, flowing color transitions, aurora/northern lights feel, iridescent overlays, holographic shimmer, prismatic effects, smooth color morphing.","background: conic-gradient or mesh (SVG), animation: gradient flow (background-position), filter: hue-rotate for shimmer, mix-blend-mode: screen, canvas for complex mesh, multiple gradient layers","☐ Mesh gradient visible, ☐ Colors flow smoothly, ☐ Aurora effect achieved, ☐ Performance acceptable, ☐ Text remains readable, ☐ Mobile renders ok","--mesh-color-1: #00FFFF, --mesh-color-2: #FF00FF, --mesh-color-3: #FFFF00, --mesh-color-4: #00FF66, --flow-duration: 10s, --shimmer-intensity: 0.3"
+66,Editorial Grid / Magazine,General,"Magazine layout, asymmetric grid, editorial typography, pull quotes, drop caps, column layout, print-inspired","High contrast: Black #000000, White #FFFFFF, accent brand color","Muted supporting, pull quote highlights, byline colors, section dividers","Smooth scroll, reveal on scroll, parallax images, text animations, page-flip transitions","News sites, blogs, magazines, editorial content, long-form articles, journalism, publishing","Dashboards, apps, e-commerce catalogs, real-time data, short-form content",✓ Full,✓ Full,⚡ Excellent,✓ WCAG AAA,✓ High,✓ Medium,"CSS Grid 10/10, Tailwind 10/10",2020s Editorial Digital,Low,"Design an editorial magazine layout. Use: asymmetric grid, pull quotes, drop caps, multi-column text, large imagery, bylines, section dividers, print-inspired typography, article hierarchy, white space balance.","display: grid with named areas, column-count for text, ::first-letter for drop caps, blockquote styling, figure/figcaption, gap variations, font: serif for body, variable widths","☐ Grid asymmetric, ☐ Typography editorial, ☐ Pull quotes styled, ☐ Drop caps present, ☐ Images large/impactful, ☐ Mobile reflows well","--grid-cols: asymmetric, --body-font: Georgia/Merriweather, --heading-font: bold sans, --drop-cap-size: 4em, --pull-quote-size: 1.5em, --column-gap: 2rem"
+67,Chromatic Aberration / RGB Split,General,"RGB split, color fringing, glitch, retro tech, VHS, analog error, distortion, lens effect","Offset RGB: Red #FF0000, Green #00FF00, Blue #0000FF, Black #000000","Neon accents, scan lines, noise overlays, error colors","RGB offset animation, glitch timing, scan line movement, noise flicker, distortion on hover","Music platforms, gaming, tech brands, creative portfolios, nightlife, entertainment, video platforms","Corporate, healthcare, finance, accessibility-critical, elderly users",✓ Full,✓ Dark preferred,⚠ Good,⚠ Can cause strain,◐ Medium,✓ High,"CSS filters 10/10, GSAP 10/10",2020s Retro-Tech,Medium,"Design with chromatic aberration RGB split effect. Use: color channel offset (R/G/B), glitch aesthetic, retro tech feel, VHS error look, lens distortion, scan lines, noise overlay, analog imperfection.","filter: drop-shadow with offset colors, text-shadow: RGB offset (-2px 0 red, 2px 0 cyan), animation: glitch (random offset), ::before for scanlines, mix-blend-mode: screen for overlays","☐ RGB split visible, ☐ Glitch effect controlled, ☐ Scan lines subtle, ☐ Performance ok, ☐ Readability maintained, ☐ Reduced motion option","--rgb-offset: 2px, --red-channel: #FF0000, --green-channel: #00FF00, --blue-channel: #0000FF, --glitch-duration: 0.3s, --scanline-opacity: 0.1"
+68,Vintage Analog / Retro Film,General,"Film grain, VHS, cassette tape, polaroid, analog warmth, faded colors, light leaks, vintage photography","Faded Cream #F5E6C8, Warm Sepia #D4A574, Muted Teal #4A7B7C, Soft Pink #E8B4B8","Grain overlays, light leak oranges, shadow blues, vintage paper tones, desaturated accents","Film grain overlay, VHS tracking effect, polaroid shake, fade-in transitions, light leak animations","Photography portfolios, music/vinyl brands, vintage fashion, nostalgia marketing, film industry, cafes","Modern tech, SaaS, healthcare, children's apps, corporate enterprise",✓ Full,◐ Partial,⚡ Good,✓ WCAG AA,✓ High,✓ High,"CSS filters 10/10, Canvas 9/10",1970s-90s Analog Revival,Medium,"Design with vintage analog film aesthetic. Use: film grain overlay, faded/desaturated colors, warm sepia tones, light leaks, VHS tracking effect, polaroid frame, analog warmth, nostalgic photography feel.","filter: sepia() contrast() saturate(0.8), background: noise texture overlay, animation: VHS tracking (transform skew), light leak gradient overlay, border for polaroid frame, grain via SVG filter","☐ Film grain visible, ☐ Colors faded/warm, ☐ Light leaks present, ☐ Nostalgic feel achieved, ☐ Performance with filters, ☐ Images look vintage","--sepia-amount: 20%, --contrast: 1.1, --saturation: 0.8, --grain-opacity: 0.15, --light-leak-color: rgba(255,200,100,0.2), --warm-tint: #F5E6C8"

.cursor/skills/ui-ux-pro-max/data/typography.csv

@@ -0,0 +1,58 @@
+No,Font Pairing Name,Category,Heading Font,Body Font,Mood/Style Keywords,Best For,Google Fonts URL,CSS Import,Tailwind Config,Notes
+1,Classic Elegant,"Serif + Sans",Playfair Display,Inter,"elegant, luxury, sophisticated, timeless, premium, editorial","Luxury brands, fashion, spa, beauty, editorial, magazines, high-end e-commerce","https://fonts.google.com/share?selection.family=Inter:wght@300;400;500;600;700|Playfair+Display:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Playfair+Display:wght@400;500;600;700&display=swap');","fontFamily: { serif: ['Playfair Display', 'serif'], sans: ['Inter', 'sans-serif'] }","High contrast between elegant heading and clean body. Perfect for luxury/premium."
+2,Modern Professional,"Sans + Sans",Poppins,Open Sans,"modern, professional, clean, corporate, friendly, approachable","SaaS, corporate sites, business apps, startups, professional services","https://fonts.google.com/share?selection.family=Open+Sans:wght@300;400;500;600;700|Poppins:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Open+Sans:wght@300;400;500;600;700&family=Poppins:wght@400;500;600;700&display=swap');","fontFamily: { heading: ['Poppins', 'sans-serif'], body: ['Open Sans', 'sans-serif'] }","Geometric Poppins for headings, humanist Open Sans for readability."
+3,Tech Startup,"Sans + Sans",Space Grotesk,DM Sans,"tech, startup, modern, innovative, bold, futuristic","Tech companies, startups, SaaS, developer tools, AI products","https://fonts.google.com/share?selection.family=DM+Sans:wght@400;500;700|Space+Grotesk:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;700&family=Space+Grotesk:wght@400;500;600;700&display=swap');","fontFamily: { heading: ['Space Grotesk', 'sans-serif'], body: ['DM Sans', 'sans-serif'] }","Space Grotesk has unique character, DM Sans is highly readable."
+4,Editorial Classic,"Serif + Serif",Cormorant Garamond,Libre Baskerville,"editorial, classic, literary, traditional, refined, bookish","Publishing, blogs, news sites, literary magazines, book covers","https://fonts.google.com/share?selection.family=Cormorant+Garamond:wght@400;500;600;700|Libre+Baskerville:wght@400;700","@import url('https://fonts.googleapis.com/css2?family=Cormorant+Garamond:wght@400;500;600;700&family=Libre+Baskerville:wght@400;700&display=swap');","fontFamily: { heading: ['Cormorant Garamond', 'serif'], body: ['Libre Baskerville', 'serif'] }","All-serif pairing for traditional editorial feel."
+5,Minimal Swiss,"Sans + Sans",Inter,Inter,"minimal, clean, swiss, functional, neutral, professional","Dashboards, admin panels, documentation, enterprise apps, design systems","https://fonts.google.com/share?selection.family=Inter:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap');","fontFamily: { sans: ['Inter', 'sans-serif'] }","Single font family with weight variations. Ultimate simplicity."
+6,Playful Creative,"Display + Sans",Fredoka,Nunito,"playful, friendly, fun, creative, warm, approachable","Children's apps, educational, gaming, creative tools, entertainment","https://fonts.google.com/share?selection.family=Fredoka:wght@400;500;600;700|Nunito:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Fredoka:wght@400;500;600;700&family=Nunito:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Fredoka', 'sans-serif'], body: ['Nunito', 'sans-serif'] }","Rounded, friendly fonts perfect for playful UIs."
+7,Bold Statement,"Display + Sans",Bebas Neue,Source Sans 3,"bold, impactful, strong, dramatic, modern, headlines","Marketing sites, portfolios, agencies, event pages, sports","https://fonts.google.com/share?selection.family=Bebas+Neue|Source+Sans+3:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Bebas+Neue&family=Source+Sans+3:wght@300;400;500;600;700&display=swap');","fontFamily: { display: ['Bebas Neue', 'sans-serif'], body: ['Source Sans 3', 'sans-serif'] }","Bebas Neue for large headlines only. All-caps display font."
+8,Wellness Calm,"Serif + Sans",Lora,Raleway,"calm, wellness, health, relaxing, natural, organic","Health apps, wellness, spa, meditation, yoga, organic brands","https://fonts.google.com/share?selection.family=Lora:wght@400;500;600;700|Raleway:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Lora:wght@400;500;600;700&family=Raleway:wght@300;400;500;600;700&display=swap');","fontFamily: { serif: ['Lora', 'serif'], sans: ['Raleway', 'sans-serif'] }","Lora's organic curves with Raleway's elegant simplicity."
+9,Developer Mono,"Mono + Sans",JetBrains Mono,IBM Plex Sans,"code, developer, technical, precise, functional, hacker","Developer tools, documentation, code editors, tech blogs, CLI apps","https://fonts.google.com/share?selection.family=IBM+Plex+Sans:wght@300;400;500;600;700|JetBrains+Mono:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Sans:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500;600;700&display=swap');","fontFamily: { mono: ['JetBrains Mono', 'monospace'], sans: ['IBM Plex Sans', 'sans-serif'] }","JetBrains for code, IBM Plex for UI. Developer-focused."
+10,Retro Vintage,"Display + Serif",Abril Fatface,Merriweather,"retro, vintage, nostalgic, dramatic, decorative, bold","Vintage brands, breweries, restaurants, creative portfolios, posters","https://fonts.google.com/share?selection.family=Abril+Fatface|Merriweather:wght@300;400;700","@import url('https://fonts.googleapis.com/css2?family=Abril+Fatface&family=Merriweather:wght@300;400;700&display=swap');","fontFamily: { display: ['Abril Fatface', 'serif'], body: ['Merriweather', 'serif'] }","Abril Fatface for hero headlines only. High-impact vintage feel."
+11,Geometric Modern,"Sans + Sans",Outfit,Work Sans,"geometric, modern, clean, balanced, contemporary, versatile","General purpose, portfolios, agencies, modern brands, landing pages","https://fonts.google.com/share?selection.family=Outfit:wght@300;400;500;600;700|Work+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700&family=Work+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Outfit', 'sans-serif'], body: ['Work Sans', 'sans-serif'] }","Both geometric but Outfit more distinctive for headings."
+12,Luxury Serif,"Serif + Sans",Cormorant,Montserrat,"luxury, high-end, fashion, elegant, refined, premium","Fashion brands, luxury e-commerce, jewelry, high-end services","https://fonts.google.com/share?selection.family=Cormorant:wght@400;500;600;700|Montserrat:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Cormorant:wght@400;500;600;700&family=Montserrat:wght@300;400;500;600;700&display=swap');","fontFamily: { serif: ['Cormorant', 'serif'], sans: ['Montserrat', 'sans-serif'] }","Cormorant's elegance with Montserrat's geometric precision."
+13,Friendly SaaS,"Sans + Sans",Plus Jakarta Sans,Plus Jakarta Sans,"friendly, modern, saas, clean, approachable, professional","SaaS products, web apps, dashboards, B2B, productivity tools","https://fonts.google.com/share?selection.family=Plus+Jakarta+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Plus+Jakarta+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { sans: ['Plus Jakarta Sans', 'sans-serif'] }","Single versatile font. Modern alternative to Inter."
+14,News Editorial,"Serif + Sans",Newsreader,Roboto,"news, editorial, journalism, trustworthy, readable, informative","News sites, blogs, magazines, journalism, content-heavy sites","https://fonts.google.com/share?selection.family=Newsreader:wght@400;500;600;700|Roboto:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Newsreader:wght@400;500;600;700&family=Roboto:wght@300;400;500;700&display=swap');","fontFamily: { serif: ['Newsreader', 'serif'], sans: ['Roboto', 'sans-serif'] }","Newsreader designed for long-form reading. Roboto for UI."
+15,Handwritten Charm,"Script + Sans",Caveat,Quicksand,"handwritten, personal, friendly, casual, warm, charming","Personal blogs, invitations, creative portfolios, lifestyle brands","https://fonts.google.com/share?selection.family=Caveat:wght@400;500;600;700|Quicksand:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Caveat:wght@400;500;600;700&family=Quicksand:wght@300;400;500;600;700&display=swap');","fontFamily: { script: ['Caveat', 'cursive'], sans: ['Quicksand', 'sans-serif'] }","Use Caveat sparingly for accents. Quicksand for body."
+16,Corporate Trust,"Sans + Sans",Lexend,Source Sans 3,"corporate, trustworthy, accessible, readable, professional, clean","Enterprise, government, healthcare, finance, accessibility-focused","https://fonts.google.com/share?selection.family=Lexend:wght@300;400;500;600;700|Source+Sans+3:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Lexend:wght@300;400;500;600;700&family=Source+Sans+3:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Lexend', 'sans-serif'], body: ['Source Sans 3', 'sans-serif'] }","Lexend designed for readability. Excellent accessibility."
+17,Brutalist Raw,"Mono + Mono",Space Mono,Space Mono,"brutalist, raw, technical, monospace, minimal, stark","Brutalist designs, developer portfolios, experimental, tech art","https://fonts.google.com/share?selection.family=Space+Mono:wght@400;700","@import url('https://fonts.googleapis.com/css2?family=Space+Mono:wght@400;700&display=swap');","fontFamily: { mono: ['Space Mono', 'monospace'] }","All-mono for raw brutalist aesthetic. Limited weights."
+18,Fashion Forward,"Sans + Sans",Syne,Manrope,"fashion, avant-garde, creative, bold, artistic, edgy","Fashion brands, creative agencies, art galleries, design studios","https://fonts.google.com/share?selection.family=Manrope:wght@300;400;500;600;700|Syne:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Manrope:wght@300;400;500;600;700&family=Syne:wght@400;500;600;700&display=swap');","fontFamily: { heading: ['Syne', 'sans-serif'], body: ['Manrope', 'sans-serif'] }","Syne's unique character for headlines. Manrope for readability."
+19,Soft Rounded,"Sans + Sans",Varela Round,Nunito Sans,"soft, rounded, friendly, approachable, warm, gentle","Children's products, pet apps, friendly brands, wellness, soft UI","https://fonts.google.com/share?selection.family=Nunito+Sans:wght@300;400;500;600;700|Varela+Round","@import url('https://fonts.googleapis.com/css2?family=Nunito+Sans:wght@300;400;500;600;700&family=Varela+Round&display=swap');","fontFamily: { heading: ['Varela Round', 'sans-serif'], body: ['Nunito Sans', 'sans-serif'] }","Both rounded and friendly. Perfect for soft UI designs."
+20,Premium Sans,"Sans + Sans",Satoshi,General Sans,"premium, modern, clean, sophisticated, versatile, balanced","Premium brands, modern agencies, SaaS, portfolios, startups","https://fonts.google.com/share?selection.family=DM+Sans:wght@400;500;700","@import url('https://fonts.googleapis.com/css2?family=DM+Sans:wght@400;500;700&display=swap');","fontFamily: { sans: ['DM Sans', 'sans-serif'] }","Note: Satoshi/General Sans on Fontshare. DM Sans as Google alternative."
+21,Vietnamese Friendly,"Sans + Sans",Be Vietnam Pro,Noto Sans,"vietnamese, international, readable, clean, multilingual, accessible","Vietnamese sites, multilingual apps, international products","https://fonts.google.com/share?selection.family=Be+Vietnam+Pro:wght@300;400;500;600;700|Noto+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Be+Vietnam+Pro:wght@300;400;500;600;700&family=Noto+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { sans: ['Be Vietnam Pro', 'Noto Sans', 'sans-serif'] }","Be Vietnam Pro excellent Vietnamese support. Noto as fallback."
+22,Japanese Elegant,"Serif + Sans",Noto Serif JP,Noto Sans JP,"japanese, elegant, traditional, modern, multilingual, readable","Japanese sites, Japanese restaurants, cultural sites, anime/manga","https://fonts.google.com/share?selection.family=Noto+Sans+JP:wght@300;400;500;700|Noto+Serif+JP:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+JP:wght@300;400;500;700&family=Noto+Serif+JP:wght@400;500;600;700&display=swap');","fontFamily: { serif: ['Noto Serif JP', 'serif'], sans: ['Noto Sans JP', 'sans-serif'] }","Noto fonts excellent Japanese support. Traditional + modern feel."
+23,Korean Modern,"Sans + Sans",Noto Sans KR,Noto Sans KR,"korean, modern, clean, professional, multilingual, readable","Korean sites, K-beauty, K-pop, Korean businesses, multilingual","https://fonts.google.com/share?selection.family=Noto+Sans+KR:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+KR:wght@300;400;500;700&display=swap');","fontFamily: { sans: ['Noto Sans KR', 'sans-serif'] }","Clean Korean typography. Single font with weight variations."
+24,Chinese Traditional,"Serif + Sans",Noto Serif TC,Noto Sans TC,"chinese, traditional, elegant, cultural, multilingual, readable","Traditional Chinese sites, cultural content, Taiwan/Hong Kong markets","https://fonts.google.com/share?selection.family=Noto+Sans+TC:wght@300;400;500;700|Noto+Serif+TC:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+TC:wght@300;400;500;700&family=Noto+Serif+TC:wght@400;500;600;700&display=swap');","fontFamily: { serif: ['Noto Serif TC', 'serif'], sans: ['Noto Sans TC', 'sans-serif'] }","Traditional Chinese character support. Elegant pairing."
+25,Chinese Simplified,"Sans + Sans",Noto Sans SC,Noto Sans SC,"chinese, simplified, modern, professional, multilingual, readable","Simplified Chinese sites, mainland China market, business apps","https://fonts.google.com/share?selection.family=Noto+Sans+SC:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+SC:wght@300;400;500;700&display=swap');","fontFamily: { sans: ['Noto Sans SC', 'sans-serif'] }","Simplified Chinese support. Clean modern look."
+26,Arabic Elegant,"Serif + Sans",Noto Naskh Arabic,Noto Sans Arabic,"arabic, elegant, traditional, cultural, RTL, readable","Arabic sites, Middle East market, Islamic content, bilingual sites","https://fonts.google.com/share?selection.family=Noto+Naskh+Arabic:wght@400;500;600;700|Noto+Sans+Arabic:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Naskh+Arabic:wght@400;500;600;700&family=Noto+Sans+Arabic:wght@300;400;500;700&display=swap');","fontFamily: { serif: ['Noto Naskh Arabic', 'serif'], sans: ['Noto Sans Arabic', 'sans-serif'] }","RTL support. Naskh for traditional, Sans for modern Arabic."
+27,Thai Modern,"Sans + Sans",Noto Sans Thai,Noto Sans Thai,"thai, modern, readable, clean, multilingual, accessible","Thai sites, Southeast Asia, tourism, Thai restaurants","https://fonts.google.com/share?selection.family=Noto+Sans+Thai:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+Thai:wght@300;400;500;700&display=swap');","fontFamily: { sans: ['Noto Sans Thai', 'sans-serif'] }","Clean Thai typography. Excellent readability."
+28,Hebrew Modern,"Sans + Sans",Noto Sans Hebrew,Noto Sans Hebrew,"hebrew, modern, RTL, clean, professional, readable","Hebrew sites, Israeli market, Jewish content, bilingual sites","https://fonts.google.com/share?selection.family=Noto+Sans+Hebrew:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Noto+Sans+Hebrew:wght@300;400;500;700&display=swap');","fontFamily: { sans: ['Noto Sans Hebrew', 'sans-serif'] }","RTL support. Clean modern Hebrew typography."
+29,Legal Professional,"Serif + Sans",EB Garamond,Lato,"legal, professional, traditional, trustworthy, formal, authoritative","Law firms, legal services, contracts, formal documents, government","https://fonts.google.com/share?selection.family=EB+Garamond:wght@400;500;600;700|Lato:wght@300;400;700","@import url('https://fonts.googleapis.com/css2?family=EB+Garamond:wght@400;500;600;700&family=Lato:wght@300;400;700&display=swap');","fontFamily: { serif: ['EB Garamond', 'serif'], sans: ['Lato', 'sans-serif'] }","EB Garamond for authority. Lato for clean body text."
+30,Medical Clean,"Sans + Sans",Figtree,Noto Sans,"medical, clean, accessible, professional, healthcare, trustworthy","Healthcare, medical clinics, pharma, health apps, accessibility","https://fonts.google.com/share?selection.family=Figtree:wght@300;400;500;600;700|Noto+Sans:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Figtree:wght@300;400;500;600;700&family=Noto+Sans:wght@300;400;500;700&display=swap');","fontFamily: { heading: ['Figtree', 'sans-serif'], body: ['Noto Sans', 'sans-serif'] }","Clean, accessible fonts for medical contexts."
+31,Financial Trust,"Sans + Sans",IBM Plex Sans,IBM Plex Sans,"financial, trustworthy, professional, corporate, banking, serious","Banks, finance, insurance, investment, fintech, enterprise","https://fonts.google.com/share?selection.family=IBM+Plex+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { sans: ['IBM Plex Sans', 'sans-serif'] }","IBM Plex conveys trust and professionalism. Excellent for data."
+32,Real Estate Luxury,"Serif + Sans",Cinzel,Josefin Sans,"real estate, luxury, elegant, sophisticated, property, premium","Real estate, luxury properties, architecture, interior design","https://fonts.google.com/share?selection.family=Cinzel:wght@400;500;600;700|Josefin+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Cinzel:wght@400;500;600;700&family=Josefin+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { serif: ['Cinzel', 'serif'], sans: ['Josefin Sans', 'sans-serif'] }","Cinzel's elegance for headlines. Josefin for modern body."
+33,Restaurant Menu,"Serif + Sans",Playfair Display SC,Karla,"restaurant, menu, culinary, elegant, foodie, hospitality","Restaurants, cafes, food blogs, culinary, hospitality","https://fonts.google.com/share?selection.family=Karla:wght@300;400;500;600;700|Playfair+Display+SC:wght@400;700","@import url('https://fonts.googleapis.com/css2?family=Karla:wght@300;400;500;600;700&family=Playfair+Display+SC:wght@400;700&display=swap');","fontFamily: { display: ['Playfair Display SC', 'serif'], sans: ['Karla', 'sans-serif'] }","Small caps Playfair for menu headers. Karla for descriptions."
+34,Art Deco,"Display + Sans",Poiret One,Didact Gothic,"art deco, vintage, 1920s, elegant, decorative, gatsby","Vintage events, art deco themes, luxury hotels, classic cocktails","https://fonts.google.com/share?selection.family=Didact+Gothic|Poiret+One","@import url('https://fonts.googleapis.com/css2?family=Didact+Gothic&family=Poiret+One&display=swap');","fontFamily: { display: ['Poiret One', 'sans-serif'], sans: ['Didact Gothic', 'sans-serif'] }","Poiret One for art deco headlines only. Didact for body."
+35,Magazine Style,"Serif + Sans",Libre Bodoni,Public Sans,"magazine, editorial, publishing, refined, journalism, print","Magazines, online publications, editorial content, journalism","https://fonts.google.com/share?selection.family=Libre+Bodoni:wght@400;500;600;700|Public+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Libre+Bodoni:wght@400;500;600;700&family=Public+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { serif: ['Libre Bodoni', 'serif'], sans: ['Public Sans', 'sans-serif'] }","Bodoni's editorial elegance. Public Sans for clean UI."
+36,Crypto/Web3,"Sans + Sans",Orbitron,Exo 2,"crypto, web3, futuristic, tech, blockchain, digital","Crypto platforms, NFT, blockchain, web3, futuristic tech","https://fonts.google.com/share?selection.family=Exo+2:wght@300;400;500;600;700|Orbitron:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Exo+2:wght@300;400;500;600;700&family=Orbitron:wght@400;500;600;700&display=swap');","fontFamily: { display: ['Orbitron', 'sans-serif'], body: ['Exo 2', 'sans-serif'] }","Orbitron for futuristic headers. Exo 2 for readable body."
+37,Gaming Bold,"Display + Sans",Russo One,Chakra Petch,"gaming, bold, action, esports, competitive, energetic","Gaming, esports, action games, competitive sports, entertainment","https://fonts.google.com/share?selection.family=Chakra+Petch:wght@300;400;500;600;700|Russo+One","@import url('https://fonts.googleapis.com/css2?family=Chakra+Petch:wght@300;400;500;600;700&family=Russo+One&display=swap');","fontFamily: { display: ['Russo One', 'sans-serif'], body: ['Chakra Petch', 'sans-serif'] }","Russo One for impact. Chakra Petch for techy body text."
+38,Indie/Craft,"Display + Sans",Amatic SC,Cabin,"indie, craft, handmade, artisan, organic, creative","Craft brands, indie products, artisan, handmade, organic products","https://fonts.google.com/share?selection.family=Amatic+SC:wght@400;700|Cabin:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Amatic+SC:wght@400;700&family=Cabin:wght@400;500;600;700&display=swap');","fontFamily: { display: ['Amatic SC', 'sans-serif'], sans: ['Cabin', 'sans-serif'] }","Amatic for handwritten feel. Cabin for readable body."
+39,Startup Bold,"Sans + Sans",Clash Display,Satoshi,"startup, bold, modern, innovative, confident, dynamic","Startups, pitch decks, product launches, bold brands","https://fonts.google.com/share?selection.family=Outfit:wght@400;500;600;700|Rubik:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Outfit:wght@400;500;600;700&family=Rubik:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Outfit', 'sans-serif'], body: ['Rubik', 'sans-serif'] }","Note: Clash Display on Fontshare. Outfit as Google alternative."
+40,E-commerce Clean,"Sans + Sans",Rubik,Nunito Sans,"ecommerce, clean, shopping, product, retail, conversion","E-commerce, online stores, product pages, retail, shopping","https://fonts.google.com/share?selection.family=Nunito+Sans:wght@300;400;500;600;700|Rubik:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Nunito+Sans:wght@300;400;500;600;700&family=Rubik:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Rubik', 'sans-serif'], body: ['Nunito Sans', 'sans-serif'] }","Clean readable fonts perfect for product descriptions."
+41,Academic/Research,"Serif + Sans",Crimson Pro,Atkinson Hyperlegible,"academic, research, scholarly, accessible, readable, educational","Universities, research papers, academic journals, educational","https://fonts.google.com/share?selection.family=Atkinson+Hyperlegible:wght@400;700|Crimson+Pro:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Atkinson+Hyperlegible:wght@400;700&family=Crimson+Pro:wght@400;500;600;700&display=swap');","fontFamily: { serif: ['Crimson Pro', 'serif'], sans: ['Atkinson Hyperlegible', 'sans-serif'] }","Crimson for scholarly headlines. Atkinson for accessibility."
+42,Dashboard Data,"Mono + Sans",Fira Code,Fira Sans,"dashboard, data, analytics, code, technical, precise","Dashboards, analytics, data visualization, admin panels","https://fonts.google.com/share?selection.family=Fira+Code:wght@400;500;600;700|Fira+Sans:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Fira+Code:wght@400;500;600;700&family=Fira+Sans:wght@300;400;500;600;700&display=swap');","fontFamily: { mono: ['Fira Code', 'monospace'], sans: ['Fira Sans', 'sans-serif'] }","Fira family cohesion. Code for data, Sans for labels."
+43,Music/Entertainment,"Display + Sans",Righteous,Poppins,"music, entertainment, fun, energetic, bold, performance","Music platforms, entertainment, events, festivals, performers","https://fonts.google.com/share?selection.family=Poppins:wght@300;400;500;600;700|Righteous","@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&family=Righteous&display=swap');","fontFamily: { display: ['Righteous', 'sans-serif'], sans: ['Poppins', 'sans-serif'] }","Righteous for bold entertainment headers. Poppins for body."
+44,Minimalist Portfolio,"Sans + Sans",Archivo,Space Grotesk,"minimal, portfolio, designer, creative, clean, artistic","Design portfolios, creative professionals, minimalist brands","https://fonts.google.com/share?selection.family=Archivo:wght@300;400;500;600;700|Space+Grotesk:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Archivo:wght@300;400;500;600;700&family=Space+Grotesk:wght@300;400;500;600;700&display=swap');","fontFamily: { heading: ['Space Grotesk', 'sans-serif'], body: ['Archivo', 'sans-serif'] }","Space Grotesk for distinctive headers. Archivo for clean body."
+45,Kids/Education,"Display + Sans",Baloo 2,Comic Neue,"kids, education, playful, friendly, colorful, learning","Children's apps, educational games, kid-friendly content","https://fonts.google.com/share?selection.family=Baloo+2:wght@400;500;600;700|Comic+Neue:wght@300;400;700","@import url('https://fonts.googleapis.com/css2?family=Baloo+2:wght@400;500;600;700&family=Comic+Neue:wght@300;400;700&display=swap');","fontFamily: { display: ['Baloo 2', 'sans-serif'], sans: ['Comic Neue', 'sans-serif'] }","Fun, playful fonts for children. Comic Neue is readable comic style."
+46,Wedding/Romance,"Script + Serif",Great Vibes,Cormorant Infant,"wedding, romance, elegant, script, invitation, feminine","Wedding sites, invitations, romantic brands, bridal","https://fonts.google.com/share?selection.family=Cormorant+Infant:wght@300;400;500;600;700|Great+Vibes","@import url('https://fonts.googleapis.com/css2?family=Cormorant+Infant:wght@300;400;500;600;700&family=Great+Vibes&display=swap');","fontFamily: { script: ['Great Vibes', 'cursive'], serif: ['Cormorant Infant', 'serif'] }","Great Vibes for elegant accents. Cormorant for readable text."
+47,Science/Tech,"Sans + Sans",Exo,Roboto Mono,"science, technology, research, data, futuristic, precise","Science, research, tech documentation, data-heavy sites","https://fonts.google.com/share?selection.family=Exo:wght@300;400;500;600;700|Roboto+Mono:wght@300;400;500;700","@import url('https://fonts.googleapis.com/css2?family=Exo:wght@300;400;500;600;700&family=Roboto+Mono:wght@300;400;500;700&display=swap');","fontFamily: { sans: ['Exo', 'sans-serif'], mono: ['Roboto Mono', 'monospace'] }","Exo for modern tech feel. Roboto Mono for code/data."
+48,Accessibility First,"Sans + Sans",Atkinson Hyperlegible,Atkinson Hyperlegible,"accessible, readable, inclusive, WCAG, dyslexia-friendly, clear","Accessibility-critical sites, government, healthcare, inclusive design","https://fonts.google.com/share?selection.family=Atkinson+Hyperlegible:wght@400;700","@import url('https://fonts.googleapis.com/css2?family=Atkinson+Hyperlegible:wght@400;700&display=swap');","fontFamily: { sans: ['Atkinson Hyperlegible', 'sans-serif'] }","Designed for maximum legibility. Excellent for accessibility."
+49,Sports/Fitness,"Sans + Sans",Barlow Condensed,Barlow,"sports, fitness, athletic, energetic, condensed, action","Sports, fitness, gyms, athletic brands, competition","https://fonts.google.com/share?selection.family=Barlow+Condensed:wght@400;500;600;700|Barlow:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Barlow+Condensed:wght@400;500;600;700&family=Barlow:wght@300;400;500;600;700&display=swap');","fontFamily: { display: ['Barlow Condensed', 'sans-serif'], body: ['Barlow', 'sans-serif'] }","Condensed for impact headlines. Regular Barlow for body."
+50,Luxury Minimalist,"Serif + Sans",Bodoni Moda,Jost,"luxury, minimalist, high-end, sophisticated, refined, premium","Luxury minimalist brands, high-end fashion, premium products","https://fonts.google.com/share?selection.family=Bodoni+Moda:wght@400;500;600;700|Jost:wght@300;400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Bodoni+Moda:wght@400;500;600;700&family=Jost:wght@300;400;500;600;700&display=swap');","fontFamily: { serif: ['Bodoni Moda', 'serif'], sans: ['Jost', 'sans-serif'] }","Bodoni's high contrast elegance. Jost for geometric body."
+51,Tech/HUD Mono,"Mono + Mono",Share Tech Mono,Fira Code,"tech, futuristic, hud, sci-fi, data, monospaced, precise","Sci-fi interfaces, developer tools, cybersecurity, dashboards","https://fonts.google.com/share?selection.family=Fira+Code:wght@300;400;500;600;700|Share+Tech+Mono","@import url('https://fonts.googleapis.com/css2?family=Fira+Code:wght@300;400;500;600;700&family=Share+Tech+Mono&display=swap');","fontFamily: { hud: ['Share Tech Mono', 'monospace'], code: ['Fira Code', 'monospace'] }","Share Tech Mono has that classic sci-fi look."
+52,Pixel Retro,"Display + Sans",Press Start 2P,VT323,"pixel, retro, gaming, 8-bit, nostalgic, arcade","Pixel art games, retro websites, creative portfolios","https://fonts.google.com/share?selection.family=Press+Start+2P|VT323","@import url('https://fonts.googleapis.com/css2?family=Press+Start+2P&family=VT323&display=swap');","fontFamily: { pixel: ['Press Start 2P', 'cursive'], terminal: ['VT323', 'monospace'] }","Press Start 2P is very wide/large. VT323 is better for body text."
+53,Neubrutalist Bold,"Display + Sans",Lexend Mega,Public Sans,"bold, neubrutalist, loud, strong, geometric, quirky","Neubrutalist designs, Gen Z brands, bold marketing","https://fonts.google.com/share?selection.family=Lexend+Mega:wght@100..900|Public+Sans:wght@100..900","@import url('https://fonts.googleapis.com/css2?family=Lexend+Mega:wght@100..900&family=Public+Sans:wght@100..900&display=swap');","fontFamily: { mega: ['Lexend Mega', 'sans-serif'], body: ['Public Sans', 'sans-serif'] }","Lexend Mega has distinct character and variable weight."
+54,Academic/Archival,"Serif + Serif",EB Garamond,Crimson Text,"academic, old-school, university, research, serious, traditional","University sites, archives, research papers, history","https://fonts.google.com/share?selection.family=Crimson+Text:wght@400;600;700|EB+Garamond:wght@400;500;600;700;800","@import url('https://fonts.googleapis.com/css2?family=Crimson+Text:wght@400;600;700&family=EB+Garamond:wght@400;500;600;700;800&display=swap');","fontFamily: { classic: ['EB Garamond', 'serif'], text: ['Crimson Text', 'serif'] }","Classic academic aesthetic. Very legible."
+55,Spatial Clear,"Sans + Sans",Inter,Inter,"spatial, legible, glass, system, clean, neutral","Spatial computing, AR/VR, glassmorphism interfaces","https://fonts.google.com/share?selection.family=Inter:wght@300;400;500;600","@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600&display=swap');","fontFamily: { sans: ['Inter', 'sans-serif'] }","Optimized for readability on dynamic backgrounds."
+56,Kinetic Motion,"Display + Mono",Syncopate,Space Mono,"kinetic, motion, futuristic, speed, wide, tech","Music festivals, automotive, high-energy brands","https://fonts.google.com/share?selection.family=Space+Mono:wght@400;700|Syncopate:wght@400;700","@import url('https://fonts.googleapis.com/css2?family=Space+Mono:wght@400;700&family=Syncopate:wght@400;700&display=swap');","fontFamily: { display: ['Syncopate', 'sans-serif'], mono: ['Space Mono', 'monospace'] }","Syncopate's wide stance works well with motion effects."
+57,Gen Z Brutal,"Display + Sans",Anton,Epilogue,"brutal, loud, shouty, meme, internet, bold","Gen Z marketing, streetwear, viral campaigns","https://fonts.google.com/share?selection.family=Anton|Epilogue:wght@400;500;600;700","@import url('https://fonts.googleapis.com/css2?family=Anton&family=Epilogue:wght@400;500;600;700&display=swap');","fontFamily: { display: ['Anton', 'sans-serif'], body: ['Epilogue', 'sans-serif'] }","Anton is impactful and condensed. Good for stickers/badges."

.cursor/skills/ui-ux-pro-max/data/ui-reasoning.csv

@@ -0,0 +1,101 @@
+No,UI_Category,Recommended_Pattern,Style_Priority,Color_Mood,Typography_Mood,Key_Effects,Decision_Rules,Anti_Patterns,Severity
+1,SaaS (General),Hero + Features + CTA,Glassmorphism + Flat Design,Trust blue + Accent contrast,Professional + Hierarchy,Subtle hover (200-250ms) + Smooth transitions,"{""if_ux_focused"": ""prioritize-minimalism"", ""if_data_heavy"": ""add-glassmorphism""}",Excessive animation + Dark mode by default,HIGH
+2,Micro SaaS,Minimal & Direct + Demo,Flat Design + Vibrant & Block,Vibrant primary + White space,Bold + Clean typography,Large CTA hover (300ms) + Scroll reveal,"{""if_quick_onboarding"": ""reduce-steps"", ""if_demo_available"": ""feature-interactive-demo""}",Complex onboarding flow + Cluttered layout,HIGH
+3,E-commerce,Feature-Rich Showcase,Vibrant & Block-based,Brand primary + Success green,Engaging + Clear hierarchy,Card hover lift (200ms) + Scale effect,"{""if_luxury"": ""switch-to-liquid-glass"", ""if_conversion_focused"": ""add-urgency-colors""}",Flat design without depth + Text-heavy pages,HIGH
+4,E-commerce Luxury,Feature-Rich Showcase,Liquid Glass + Glassmorphism,Premium colors + Minimal accent,Elegant + Refined typography,Chromatic aberration + Fluid animations (400-600ms),"{""if_checkout"": ""emphasize-trust"", ""if_hero_needed"": ""use-3d-hyperrealism""}",Vibrant & Block-based + Playful colors,HIGH
+5,Healthcare App,Social Proof-Focused,Neumorphism + Accessible & Ethical,Calm blue + Health green,Readable + Large type (16px+),Soft box-shadow + Smooth press (150ms),"{""must_have"": ""wcag-aaa-compliance"", ""if_medication"": ""red-alert-colors""}",Bright neon colors + Motion-heavy animations + AI purple/pink gradients,HIGH
+6,Fintech/Crypto,Conversion-Optimized,Glassmorphism + Dark Mode (OLED),Dark tech colors + Vibrant accents,Modern + Confident typography,Real-time chart animations + Alert pulse/glow,"{""must_have"": ""security-badges"", ""if_real_time"": ""add-streaming-data""}",Light backgrounds + No security indicators,HIGH
+7,Education,Feature-Rich Showcase,Claymorphism + Micro-interactions,Playful colors + Clear hierarchy,Friendly + Engaging typography,Soft press (200ms) + Fluffy elements,"{""if_gamification"": ""add-progress-animation"", ""if_children"": ""increase-playfulness""}",Dark modes + Complex jargon,MEDIUM
+8,Portfolio/Personal,Storytelling-Driven,Motion-Driven + Minimalism,Brand primary + Artistic,Expressive + Variable typography,Parallax (3-5 layers) + Scroll-triggered reveals,"{""if_creative_field"": ""add-brutalism"", ""if_minimal_portfolio"": ""reduce-motion""}",Corporate templates + Generic layouts,MEDIUM
+9,Government/Public,Minimal & Direct,Accessible & Ethical + Minimalism,Professional blue + High contrast,Clear + Large typography,Clear focus rings (3-4px) + Skip links,"{""must_have"": ""wcag-aaa"", ""must_have"": ""keyboard-navigation""}",Ornate design + Low contrast + Motion effects + AI purple/pink gradients,HIGH
+10,Fintech (Banking),Trust & Authority,Minimalism + Accessible & Ethical,Navy + Trust Blue + Gold,Professional + Trustworthy,Smooth state transitions + Number animations,"{""must_have"": ""security-first"", ""if_dashboard"": ""use-dark-mode""}",Playful design + Unclear fees + AI purple/pink gradients,HIGH
+11,Social Media App,Feature-Rich Showcase,Vibrant & Block-based + Motion-Driven,Vibrant + Engagement colors,Modern + Bold typography,Large scroll animations + Icon animations,"{""if_engagement_metric"": ""add-motion"", ""if_content_focused"": ""minimize-chrome""}",Heavy skeuomorphism + Accessibility ignored,MEDIUM
+12,Startup Landing,Hero-Centric + Trust,Motion-Driven + Vibrant & Block,Bold primaries + Accent contrast,Modern + Energetic typography,Scroll-triggered animations + Parallax,"{""if_pre_launch"": ""use-waitlist-pattern"", ""if_video_ready"": ""add-hero-video""}",Static design + No video + Poor mobile,HIGH
+13,Gaming,Feature-Rich Showcase,3D & Hyperrealism + Retro-Futurism,Vibrant + Neon + Immersive,Bold + Impactful typography,WebGL 3D rendering + Glitch effects,"{""if_competitive"": ""add-real-time-stats"", ""if_casual"": ""increase-playfulness""}",Minimalist design + Static assets,HIGH
+14,Creative Agency,Storytelling-Driven,Brutalism + Motion-Driven,Bold primaries + Artistic freedom,Bold + Expressive typography,CRT scanlines + Neon glow + Glitch effects,"{""must_have"": ""case-studies"", ""if_boutique"": ""increase-artistic-freedom""}",Corporate minimalism + Hidden portfolio,HIGH
+15,Wellness/Mental Health,Social Proof-Focused,Neumorphism + Accessible & Ethical,Calm Pastels + Trust colors,Calming + Readable typography,Soft press + Breathing animations,"{""must_have"": ""privacy-first"", ""if_meditation"": ""add-breathing-animation""}",Bright neon + Motion overload,HIGH
+16,Restaurant/Food,Hero-Centric + Conversion,Vibrant & Block-based + Motion-Driven,Warm colors (Orange Red Brown),Appetizing + Clear typography,Food image reveal + Menu hover effects,"{""must_have"": ""high_quality_images"", ""if_delivery"": ""emphasize-speed""}",Low-quality imagery + Outdated hours,HIGH
+17,Real Estate,Hero-Centric + Feature-Rich,Glassmorphism + Minimalism,Trust Blue + Gold + White,Professional + Confident,3D property tour zoom + Map hover,"{""if_luxury"": ""add-3d-models"", ""must_have"": ""map-integration""}",Poor photos + No virtual tours,HIGH
+18,Travel/Tourism,Storytelling-Driven + Hero,Aurora UI + Motion-Driven,Vibrant destination + Sky Blue,Inspirational + Engaging,Destination parallax + Itinerary animations,"{""if_experience_focused"": ""use-storytelling"", ""must_have"": ""mobile-booking""}",Generic photos + Complex booking,HIGH
+19,SaaS Dashboard,Data-Dense Dashboard,Data-Dense + Heat Map,Cool to Hot gradients + Neutral grey,Clear + Readable typography,Hover tooltips + Chart zoom + Real-time pulse,"{""must_have"": ""real-time-updates"", ""if_large_dataset"": ""prioritize-performance""}",Ornate design + Slow rendering,HIGH
+20,B2B SaaS Enterprise,Feature-Rich Showcase,Trust & Authority + Minimal,Professional blue + Neutral grey,Formal + Clear typography,Subtle section transitions + Feature reveals,"{""must_have"": ""case-studies"", ""must_have"": ""roi-messaging""}",Playful design + Hidden features + AI purple/pink gradients,HIGH
+21,Music/Entertainment,Feature-Rich Showcase,Dark Mode (OLED) + Vibrant & Block-based,Dark (#121212) + Vibrant accents + Album art colors,Modern + Bold typography,Waveform visualization + Playlist animations,"{""must_have"": ""audio-player-ux"", ""if_discovery_focused"": ""add-playlist-recommendations""}",Cluttered layout + Poor audio player UX,HIGH
+22,Video Streaming/OTT,Hero-Centric + Feature-Rich,Dark Mode (OLED) + Motion-Driven,Dark bg + Poster colors + Brand accent,Bold + Engaging typography,Video player animations + Content carousel (parallax),"{""must_have"": ""continue-watching"", ""if_personalized"": ""add-recommendations""}",Static layout + Slow video player,HIGH
+23,Job Board/Recruitment,Conversion-Optimized + Feature-Rich,Flat Design + Minimalism,Professional Blue + Success Green + Neutral,Clear + Professional typography,Search/filter animations + Application flow,"{""must_have"": ""advanced-search"", ""if_salary_focused"": ""highlight-compensation""}",Outdated forms + Hidden filters,HIGH
+24,Marketplace (P2P),Feature-Rich Showcase + Social Proof,Vibrant & Block-based + Flat Design,Trust colors + Category colors + Success green,Modern + Engaging typography,Review star animations + Listing hover effects,"{""must_have"": ""seller-profiles"", ""must_have"": ""secure-payment""}",Low trust signals + Confusing layout,HIGH
+25,Logistics/Delivery,Feature-Rich Showcase + Real-Time,Minimalism + Flat Design,Blue (#2563EB) + Orange (tracking) + Green,Clear + Functional typography,Real-time tracking animation + Status pulse,"{""must_have"": ""tracking-map"", ""must_have"": ""delivery-updates""}",Static tracking + No map integration + AI purple/pink gradients,HIGH
+26,Agriculture/Farm Tech,Feature-Rich Showcase,Organic Biophilic + Flat Design,Earth Green (#4A7C23) + Brown + Sky Blue,Clear + Informative typography,Data visualization + Weather animations,"{""must_have"": ""sensor-dashboard"", ""if_crop_focused"": ""add-health-indicators""}",Generic design + Ignored accessibility + AI purple/pink gradients,MEDIUM
+27,Construction/Architecture,Hero-Centric + Feature-Rich,Minimalism + 3D & Hyperrealism,Grey (#4A4A4A) + Orange (safety) + Blueprint Blue,Professional + Bold typography,3D model viewer + Timeline animations,"{""must_have"": ""project-portfolio"", ""if_team_collaboration"": ""add-real-time-updates""}",2D-only layouts + Poor image quality + AI purple/pink gradients,HIGH
+28,Automotive/Car Dealership,Hero-Centric + Feature-Rich,Motion-Driven + 3D & Hyperrealism,Brand colors + Metallic + Dark/Light,Bold + Confident typography,360 product view + Configurator animations,"{""must_have"": ""vehicle-comparison"", ""must_have"": ""financing-calculator""}",Static product pages + Poor UX,HIGH
+29,Photography Studio,Storytelling-Driven + Hero-Centric,Motion-Driven + Minimalism,Black + White + Minimal accent,Elegant + Minimal typography,Full-bleed gallery + Before/after reveal,"{""must_have"": ""portfolio-showcase"", ""if_booking"": ""add-calendar-system""}",Heavy text + Poor image showcase,HIGH
+30,Coworking Space,Hero-Centric + Feature-Rich,Vibrant & Block-based + Glassmorphism,Energetic colors + Wood tones + Brand,Modern + Engaging typography,Space tour video + Amenity reveal animations,"{""must_have"": ""virtual-tour"", ""must_have"": ""booking-system""}",Outdated photos + Confusing layout,MEDIUM
+31,Cleaning Service,Conversion-Optimized + Trust,Soft UI Evolution + Flat Design,Fresh Blue (#00B4D8) + Clean White + Green,Friendly + Clear typography,Before/after gallery + Service package reveal,"{""must_have"": ""price-transparency"", ""must_have"": ""trust-badges""}",Poor before/after imagery + Hidden pricing,HIGH
+32,Home Services,Conversion-Optimized + Trust,Flat Design + Trust & Authority,Trust Blue + Safety Orange + Grey,Professional + Clear typography,Emergency contact highlight + Service menu animations,"{""must_have"": ""emergency-contact"", ""must_have"": ""certifications-display""}",Hidden contact info + No certifications,HIGH
+33,Childcare/Daycare,Social Proof-Focused + Trust,Claymorphism + Vibrant & Block-based,Playful pastels + Safe colors + Warm,Friendly + Playful typography,Parent portal animations + Activity gallery reveal,"{""must_have"": ""parent-communication"", ""must_have"": ""safety-certifications""}",Generic design + Hidden safety info,HIGH
+34,Senior Care/Elderly,Trust & Authority + Accessible,Accessible & Ethical + Soft UI Evolution,Calm Blue + Warm neutrals + Large text,Large + Clear typography (18px+),Large touch targets + Clear navigation,"{""must_have"": ""wcag-aaa"", ""must_have"": ""family-portal""}",Small text + Complex navigation + AI purple/pink gradients,HIGH
+35,Medical Clinic,Trust & Authority + Conversion,Accessible & Ethical + Minimalism,Medical Blue (#0077B6) + Trust White,Professional + Readable typography,Online booking flow + Doctor profile reveals,"{""must_have"": ""appointment-booking"", ""must_have"": ""insurance-info""}",Outdated interface + Confusing booking + AI purple/pink gradients,HIGH
+36,Pharmacy/Drug Store,Conversion-Optimized + Trust,Flat Design + Accessible & Ethical,Pharmacy Green + Trust Blue + Clean White,Clear + Functional typography,Prescription upload flow + Refill reminders,"{""must_have"": ""prescription-management"", ""must_have"": ""drug-interaction-warnings""}",Confusing layout + Privacy concerns + AI purple/pink gradients,HIGH
+37,Dental Practice,Social Proof-Focused + Conversion,Soft UI Evolution + Minimalism,Fresh Blue + White + Smile Yellow,Friendly + Professional typography,Before/after gallery + Patient testimonial carousel,"{""must_have"": ""before-after-gallery"", ""must_have"": ""appointment-system""}",Poor imagery + No testimonials,HIGH
+38,Veterinary Clinic,Social Proof-Focused + Trust,Claymorphism + Accessible & Ethical,Caring Blue + Pet colors + Warm,Friendly + Welcoming typography,Pet profile management + Service animations,"{""must_have"": ""pet-portal"", ""must_have"": ""emergency-contact""}",Generic design + Hidden services,MEDIUM
+39,News/Media Platform,Hero-Centric + Feature-Rich,Minimalism + Flat Design,Brand colors + High contrast,Clear + Readable typography,Breaking news badge + Article reveal animations,"{""must_have"": ""mobile-first-reading"", ""must_have"": ""category-navigation""}",Cluttered layout + Slow loading,HIGH
+40,Legal Services,Trust & Authority + Minimal,Trust & Authority + Minimalism,Navy Blue (#1E3A5F) + Gold + White,Professional + Authoritative typography,Practice area reveal + Attorney profile animations,"{""must_have"": ""case-results"", ""must_have"": ""credential-display""}",Outdated design + Hidden credentials + AI purple/pink gradients,HIGH
+41,Beauty/Spa/Wellness Service,Hero-Centric + Social Proof,Soft UI Evolution + Neumorphism,Soft pastels (Pink Sage Cream) + Gold accents,Elegant + Calming typography,Soft shadows + Smooth transitions (200-300ms) + Gentle hover,"{""must_have"": ""booking-system"", ""must_have"": ""before-after-gallery"", ""if_luxury"": ""add-gold-accents""}",Bright neon colors + Harsh animations + Dark mode,HIGH
+42,Service Landing Page,Hero-Centric + Trust & Authority,Minimalism + Social Proof-Focused,Brand primary + Trust colors,Professional + Clear typography,Testimonial carousel + CTA hover (200ms),"{""must_have"": ""social-proof"", ""must_have"": ""clear-cta""}",Complex navigation + Hidden contact info,HIGH
+43,B2B Service,Feature-Rich Showcase + Trust,Trust & Authority + Minimalism,Professional blue + Neutral grey,Formal + Clear typography,Section transitions + Feature reveals,"{""must_have"": ""case-studies"", ""must_have"": ""roi-messaging""}",Playful design + Hidden credentials + AI purple/pink gradients,HIGH
+44,Financial Dashboard,Data-Dense Dashboard,Dark Mode (OLED) + Data-Dense,Dark bg + Red/Green alerts + Trust blue,Clear + Readable typography,Real-time number animations + Alert pulse,"{""must_have"": ""real-time-updates"", ""must_have"": ""high-contrast""}",Light mode default + Slow rendering,HIGH
+45,Analytics Dashboard,Data-Dense + Drill-Down,Data-Dense + Heat Map,Cool→Hot gradients + Neutral grey,Clear + Functional typography,Hover tooltips + Chart zoom + Filter animations,"{""must_have"": ""data-export"", ""if_large_dataset"": ""virtualize-lists""}",Ornate design + No filtering,HIGH
+46,Productivity Tool,Interactive Demo + Feature-Rich,Flat Design + Micro-interactions,Clear hierarchy + Functional colors,Clean + Efficient typography,Quick actions (150ms) + Task animations,"{""must_have"": ""keyboard-shortcuts"", ""if_collaboration"": ""add-real-time-cursors""}",Complex onboarding + Slow performance,HIGH
+47,Design System/Component Library,Feature-Rich + Documentation,Minimalism + Accessible & Ethical,Clear hierarchy + Code-like structure,Monospace + Clear typography,Code copy animations + Component previews,"{""must_have"": ""search"", ""must_have"": ""code-examples""}",Poor documentation + No live preview,HIGH
+48,AI/Chatbot Platform,Interactive Demo + Minimal,AI-Native UI + Minimalism,Neutral + AI Purple (#6366F1),Modern + Clear typography,Streaming text + Typing indicators + Fade-in,"{""must_have"": ""conversational-ui"", ""must_have"": ""context-awareness""}",Heavy chrome + Slow response feedback,HIGH
+49,NFT/Web3 Platform,Feature-Rich Showcase,Cyberpunk UI + Glassmorphism,Dark + Neon + Gold (#FFD700),Bold + Modern typography,Wallet connect animations + Transaction feedback,"{""must_have"": ""wallet-integration"", ""must_have"": ""gas-fees-display""}",Light mode default + No transaction status,HIGH
+50,Creator Economy Platform,Social Proof + Feature-Rich,Vibrant & Block-based + Bento Box Grid,Vibrant + Brand colors,Modern + Bold typography,Engagement counter animations + Profile reveals,"{""must_have"": ""creator-profiles"", ""must_have"": ""monetization-display""}",Generic layout + Hidden earnings,MEDIUM
+51,Sustainability/ESG Platform,Trust & Authority + Data,Organic Biophilic + Minimalism,Green (#228B22) + Earth tones,Clear + Informative typography,Progress indicators + Impact animations,"{""must_have"": ""data-transparency"", ""must_have"": ""certification-badges""}",Greenwashing visuals + No data,HIGH
+52,Remote Work/Collaboration,Feature-Rich + Real-Time,Soft UI Evolution + Minimalism,Calm Blue + Neutral grey,Clean + Readable typography,Real-time presence indicators + Notification badges,"{""must_have"": ""status-indicators"", ""must_have"": ""video-integration""}",Cluttered interface + No presence,HIGH
+53,Pet Tech App,Storytelling + Feature-Rich,Claymorphism + Vibrant & Block-based,Playful + Warm colors,Friendly + Playful typography,Pet profile animations + Health tracking charts,"{""must_have"": ""pet-profiles"", ""if_health"": ""add-vet-integration""}",Generic design + No personality,MEDIUM
+54,Smart Home/IoT Dashboard,Real-Time Monitoring,Glassmorphism + Dark Mode (OLED),Dark + Status indicator colors,Clear + Functional typography,Device status pulse + Quick action animations,"{""must_have"": ""real-time-controls"", ""must_have"": ""energy-monitoring""}",Slow updates + No automation,HIGH
+55,EV/Charging Ecosystem,Hero-Centric + Feature-Rich,Minimalism + Aurora UI,Electric Blue (#009CD1) + Green,Modern + Clear typography,Range estimation animations + Map interactions,"{""must_have"": ""charging-map"", ""must_have"": ""range-calculator""}",Poor map UX + Hidden costs,HIGH
+56,Subscription Box Service,Feature-Rich + Conversion,Vibrant & Block-based + Motion-Driven,Brand + Excitement colors,Engaging + Clear typography,Unboxing reveal animations + Product carousel,"{""must_have"": ""personalization-quiz"", ""must_have"": ""subscription-management""}",Confusing pricing + No unboxing preview,HIGH
+57,Podcast Platform,Storytelling + Feature-Rich,Dark Mode (OLED) + Minimalism,Dark + Audio waveform accents,Modern + Clear typography,Waveform visualizations + Episode transitions,"{""must_have"": ""audio-player-ux"", ""must_have"": ""episode-discovery""}",Poor audio player + Cluttered layout,HIGH
+58,Dating App,Social Proof + Feature-Rich,Vibrant & Block-based + Motion-Driven,Warm + Romantic (Pink/Red gradients),Modern + Friendly typography,Profile card swipe + Match animations,"{""must_have"": ""profile-cards"", ""must_have"": ""safety-features""}",Generic profiles + No safety,HIGH
+59,Micro-Credentials/Badges,Trust & Authority + Feature,Minimalism + Flat Design,Trust Blue + Gold (#FFD700),Professional + Clear typography,Badge reveal animations + Progress tracking,"{""must_have"": ""credential-verification"", ""must_have"": ""progress-display""}",No verification + Hidden progress,MEDIUM
+60,Knowledge Base/Documentation,FAQ + Minimal,Minimalism + Accessible & Ethical,Clean hierarchy + Minimal color,Clear + Readable typography,Search highlight + Smooth scrolling,"{""must_have"": ""search-first"", ""must_have"": ""version-switching""}",Poor navigation + No search,HIGH
+61,Hyperlocal Services,Conversion + Feature-Rich,Minimalism + Vibrant & Block-based,Location markers + Trust colors,Clear + Functional typography,Map hover + Provider card reveals,"{""must_have"": ""map-integration"", ""must_have"": ""booking-system""}",No map + Hidden reviews,HIGH
+62,Luxury/Premium Brand,Storytelling + Feature-Rich,Liquid Glass + Glassmorphism,Black + Gold (#FFD700) + White,Elegant + Refined typography,Slow parallax + Premium reveals (400-600ms),"{""must_have"": ""high-quality-imagery"", ""must_have"": ""storytelling""}",Cheap visuals + Fast animations,HIGH
+63,Fitness/Gym App,Feature-Rich + Data,Vibrant & Block-based + Dark Mode (OLED),Energetic (Orange #FF6B35) + Dark bg,Bold + Motivational typography,Progress ring animations + Achievement unlocks,"{""must_have"": ""progress-tracking"", ""must_have"": ""workout-plans""}",Static design + No gamification,HIGH
+64,Hotel/Hospitality,Hero-Centric + Social Proof,Liquid Glass + Minimalism,Warm neutrals + Gold (#D4AF37),Elegant + Welcoming typography,Room gallery + Amenity reveals,"{""must_have"": ""room-booking"", ""must_have"": ""virtual-tour""}",Poor photos + Complex booking,HIGH
+65,Wedding/Event Planning,Storytelling + Social Proof,Soft UI Evolution + Aurora UI,Soft Pink (#FFD6E0) + Gold + Cream,Elegant + Romantic typography,Gallery reveals + Timeline animations,"{""must_have"": ""portfolio-gallery"", ""must_have"": ""planning-tools""}",Generic templates + No portfolio,HIGH
+66,Insurance Platform,Conversion + Trust,Trust & Authority + Flat Design,Trust Blue (#0066CC) + Green + Neutral,Clear + Professional typography,Quote calculator animations + Policy comparison,"{""must_have"": ""quote-calculator"", ""must_have"": ""policy-comparison""}",Confusing pricing + No trust signals + AI purple/pink gradients,HIGH
+67,Banking/Traditional Finance,Trust & Authority + Feature,Minimalism + Accessible & Ethical,Navy (#0A1628) + Trust Blue + Gold,Professional + Trustworthy typography,Smooth number animations + Security indicators,"{""must_have"": ""security-first"", ""must_have"": ""accessibility""}",Playful design + Poor security UX + AI purple/pink gradients,HIGH
+68,Online Course/E-learning,Feature-Rich + Social Proof,Claymorphism + Vibrant & Block-based,Vibrant learning colors + Progress green,Friendly + Engaging typography,Progress bar animations + Certificate reveals,"{""must_have"": ""progress-tracking"", ""must_have"": ""video-player""}",Boring design + No gamification,HIGH
+69,Non-profit/Charity,Storytelling + Trust,Accessible & Ethical + Organic Biophilic,Cause-related colors + Trust + Warm,Heartfelt + Readable typography,Impact counter animations + Story reveals,"{""must_have"": ""impact-stories"", ""must_have"": ""donation-transparency""}",No impact data + Hidden financials,HIGH
+70,Florist/Plant Shop,Hero-Centric + Conversion,Organic Biophilic + Vibrant & Block-based,Natural Green + Floral pinks/purples,Elegant + Natural typography,Product reveal + Seasonal transitions,"{""must_have"": ""delivery-scheduling"", ""must_have"": ""care-guides""}",Poor imagery + No seasonal content,MEDIUM
+71,Bakery/Cafe,Hero-Centric + Conversion,Vibrant & Block-based + Soft UI Evolution,Warm Brown + Cream + Appetizing accents,Warm + Inviting typography,Menu hover + Order animations,"{""must_have"": ""menu-display"", ""must_have"": ""online-ordering""}",Poor food photos + Hidden hours,HIGH
+72,Coffee Shop,Hero-Centric + Minimal,Minimalism + Organic Biophilic,Coffee Brown (#6F4E37) + Cream + Warm,Cozy + Clean typography,Menu transitions + Loyalty animations,"{""must_have"": ""menu"", ""if_loyalty"": ""add-rewards-system""}",Generic design + No atmosphere,MEDIUM
+73,Brewery/Winery,Storytelling + Hero-Centric,Motion-Driven + Storytelling-Driven,Deep amber/burgundy + Gold + Craft,Artisanal + Heritage typography,Tasting note reveals + Heritage timeline,"{""must_have"": ""product-showcase"", ""must_have"": ""story-heritage""}",Generic product pages + No story,HIGH
+74,Airline,Conversion + Feature-Rich,Minimalism + Glassmorphism,Sky Blue + Brand colors + Trust,Clear + Professional typography,Flight search animations + Boarding pass reveals,"{""must_have"": ""flight-search"", ""must_have"": ""mobile-first""}",Complex booking + Poor mobile,HIGH
+75,Magazine/Blog,Storytelling + Hero-Centric,Swiss Modernism 2.0 + Motion-Driven,Editorial colors + Brand + Clean white,Editorial + Elegant typography,Article transitions + Category reveals,"{""must_have"": ""article-showcase"", ""must_have"": ""newsletter-signup""}",Poor typography + Slow loading,HIGH
+76,Freelancer Platform,Feature-Rich + Conversion,Flat Design + Minimalism,Professional Blue + Success Green,Clear + Professional typography,Skill match animations + Review reveals,"{""must_have"": ""portfolio-display"", ""must_have"": ""skill-matching""}",Poor profiles + No reviews,HIGH
+77,Consulting Firm,Trust & Authority + Minimal,Trust & Authority + Minimalism,Navy + Gold + Professional grey,Authoritative + Clear typography,Case study reveals + Team profiles,"{""must_have"": ""case-studies"", ""must_have"": ""thought-leadership""}",Generic content + No credentials + AI purple/pink gradients,HIGH
+78,Marketing Agency,Storytelling + Feature-Rich,Brutalism + Motion-Driven,Bold brand colors + Creative freedom,Bold + Expressive typography,Portfolio reveals + Results animations,"{""must_have"": ""portfolio"", ""must_have"": ""results-metrics""}",Boring design + Hidden work,HIGH
+79,Event Management,Hero-Centric + Feature-Rich,Vibrant & Block-based + Motion-Driven,Event theme colors + Excitement accents,Bold + Engaging typography,Countdown timer + Registration flow,"{""must_have"": ""registration"", ""must_have"": ""agenda-display""}",Confusing registration + No countdown,HIGH
+80,Conference/Webinar Platform,Feature-Rich + Conversion,Glassmorphism + Minimalism,Professional Blue + Video accent,Professional + Clear typography,Live stream integration + Agenda transitions,"{""must_have"": ""registration"", ""must_have"": ""speaker-profiles""}",Poor video UX + No networking,HIGH
+81,Membership/Community,Social Proof + Conversion,Vibrant & Block-based + Soft UI Evolution,Community brand colors + Engagement,Friendly + Engaging typography,Member counter + Benefit reveals,"{""must_have"": ""member-benefits"", ""must_have"": ""pricing-tiers""}",Hidden benefits + No community proof,HIGH
+82,Newsletter Platform,Minimal + Conversion,Minimalism + Flat Design,Brand primary + Clean white + CTA,Clean + Readable typography,Subscribe form + Archive reveals,"{""must_have"": ""subscribe-form"", ""must_have"": ""sample-content""}",Complex signup + No preview,MEDIUM
+83,Digital Products/Downloads,Feature-Rich + Conversion,Vibrant & Block-based + Motion-Driven,Product colors + Brand + Success green,Modern + Clear typography,Product preview + Instant delivery animations,"{""must_have"": ""product-preview"", ""must_have"": ""instant-delivery""}",No preview + Slow delivery,HIGH
+84,Church/Religious Organization,Hero-Centric + Social Proof,Accessible & Ethical + Soft UI Evolution,Warm Gold + Deep Purple/Blue + White,Welcoming + Clear typography,Service time highlights + Event calendar,"{""must_have"": ""service-times"", ""must_have"": ""community-events""}",Outdated design + Hidden info,MEDIUM
+85,Sports Team/Club,Hero-Centric + Feature-Rich,Vibrant & Block-based + Motion-Driven,Team colors + Energetic accents,Bold + Impactful typography,Score animations + Schedule reveals,"{""must_have"": ""schedule"", ""must_have"": ""roster""}",Static content + Poor fan engagement,HIGH
+86,Museum/Gallery,Storytelling + Feature-Rich,Minimalism + Motion-Driven,Art-appropriate neutrals + Exhibition accents,Elegant + Minimal typography,Virtual tour + Collection reveals,"{""must_have"": ""virtual-tour"", ""must_have"": ""exhibition-info""}",Cluttered layout + No online access,HIGH
+87,Theater/Cinema,Hero-Centric + Conversion,Dark Mode (OLED) + Motion-Driven,Dark + Spotlight accents + Gold,Dramatic + Bold typography,Seat selection + Trailer reveals,"{""must_have"": ""showtimes"", ""must_have"": ""seat-selection""}",Poor booking UX + No trailers,HIGH
+88,Language Learning App,Feature-Rich + Social Proof,Claymorphism + Vibrant & Block-based,Playful colors + Progress indicators,Friendly + Clear typography,Progress animations + Achievement unlocks,"{""must_have"": ""progress-tracking"", ""must_have"": ""gamification""}",Boring design + No motivation,HIGH
+89,Coding Bootcamp,Feature-Rich + Social Proof,Dark Mode (OLED) + Minimalism,Code editor colors + Brand + Success,Technical + Clear typography,Terminal animations + Career outcome reveals,"{""must_have"": ""curriculum"", ""must_have"": ""career-outcomes""}",Light mode only + Hidden results,HIGH
+90,Cybersecurity Platform,Trust & Authority + Real-Time,Cyberpunk UI + Dark Mode (OLED),Matrix Green (#00FF00) + Deep Black,Technical + Clear typography,Threat visualization + Alert animations,"{""must_have"": ""real-time-monitoring"", ""must_have"": ""threat-display""}",Light mode + Poor data viz,HIGH
+91,Developer Tool/IDE,Minimal + Documentation,Dark Mode (OLED) + Minimalism,Dark syntax theme + Blue focus,Monospace + Functional typography,Syntax highlighting + Command palette,"{""must_have"": ""keyboard-shortcuts"", ""must_have"": ""documentation""}",Light mode default + Slow performance,HIGH
+92,Biotech/Life Sciences,Storytelling + Data,Glassmorphism + Clean Science,Sterile White + DNA Blue + Life Green,Scientific + Clear typography,Data visualization + Research reveals,"{""must_have"": ""data-accuracy"", ""must_have"": ""clean-aesthetic""}",Cluttered data + Poor credibility,HIGH
+93,Space Tech/Aerospace,Immersive + Feature-Rich,Holographic/HUD + Dark Mode,Deep Space Black + Star White + Metallic,Futuristic + Precise typography,Telemetry animations + 3D renders,"{""must_have"": ""high-tech-feel"", ""must_have"": ""precision-data""}",Generic design + No immersion,HIGH
+94,Architecture/Interior,Portfolio + Hero-Centric,Exaggerated Minimalism + High Imagery,Monochrome + Gold Accent + High Imagery,Architectural + Elegant typography,Project gallery + Blueprint reveals,"{""must_have"": ""high-res-images"", ""must_have"": ""project-portfolio""}",Poor imagery + Cluttered layout,HIGH
+95,Quantum Computing,Immersive + Interactive,Holographic/HUD + Dark Mode,Quantum Blue (#00FFFF) + Deep Black,Futuristic + Scientific typography,Probability visualizations + Qubit state animations,"{""must_have"": ""complexity-visualization"", ""must_have"": ""scientific-credibility""}",Generic tech design + No viz,HIGH
+96,Biohacking/Longevity App,Data-Dense + Storytelling,Biomimetic/Organic 2.0 + Minimalism,Cellular Pink/Red + DNA Blue + White,Scientific + Clear typography,Biological data viz + Progress animations,"{""must_have"": ""data-privacy"", ""must_have"": ""scientific-credibility""}",Generic health app + No privacy,HIGH
+97,Autonomous Drone Fleet,Real-Time + Feature-Rich,HUD/Sci-Fi FUI + Real-Time,Tactical Green + Alert Red + Map Dark,Technical + Functional typography,Telemetry animations + 3D spatial awareness,"{""must_have"": ""real-time-telemetry"", ""must_have"": ""safety-alerts""}",Slow updates + Poor spatial viz,HIGH
+98,Generative Art Platform,Showcase + Feature-Rich,Minimalism + Gen Z Chaos,Neutral (#F5F5F5) + User Content,Minimal + Content-focused typography,Gallery masonry + Minting animations,"{""must_have"": ""fast-loading"", ""must_have"": ""creator-attribution""}",Heavy chrome + Slow loading,HIGH
+99,Spatial Computing OS,Immersive + Interactive,Spatial UI (VisionOS) + Glassmorphism,Frosted Glass + System Colors + Depth,Spatial + Readable typography,Depth hierarchy + Gaze interactions,"{""must_have"": ""depth-hierarchy"", ""must_have"": ""environment-awareness""}",2D design + No spatial depth,HIGH
+100,Sustainable Energy/Climate,Data + Trust,Organic Biophilic + E-Ink/Paper,Earth Green + Sky Blue + Solar Yellow,Clear + Informative typography,Impact viz + Progress animations,"{""must_have"": ""data-transparency"", ""must_have"": ""impact-visualization""}",Greenwashing + No real data,HIGH

.cursor/skills/ui-ux-pro-max/data/ux-guidelines.csv

@@ -0,0 +1,100 @@
+No,Category,Issue,Platform,Description,Do,Don't,Code Example Good,Code Example Bad,Severity
+1,Navigation,Smooth Scroll,Web,Anchor links should scroll smoothly to target section,Use scroll-behavior: smooth on html element,Jump directly without transition,html { scroll-behavior: smooth; },<a href='#section'> without CSS,High
+2,Navigation,Sticky Navigation,Web,Fixed nav should not obscure content,Add padding-top to body equal to nav height,Let nav overlap first section content,pt-20 (if nav is h-20),No padding compensation,Medium
+3,Navigation,Active State,All,Current page/section should be visually indicated,Highlight active nav item with color/underline,No visual feedback on current location,text-primary border-b-2,All links same style,Medium
+4,Navigation,Back Button,Mobile,Users expect back to work predictably,Preserve navigation history properly,Break browser/app back button behavior,history.pushState(),location.replace(),High
+5,Navigation,Deep Linking,All,URLs should reflect current state for sharing,Update URL on state/view changes,Static URLs for dynamic content,Use query params or hash,Single URL for all states,Medium
+6,Navigation,Breadcrumbs,Web,Show user location in site hierarchy,Use for sites with 3+ levels of depth,Use for flat single-level sites,Home > Category > Product,Only on deep nested pages,Low
+7,Animation,Excessive Motion,All,Too many animations cause distraction and motion sickness,Animate 1-2 key elements per view maximum,Animate everything that moves,Single hero animation,animate-bounce on 5+ elements,High
+8,Animation,Duration Timing,All,Animations should feel responsive not sluggish,Use 150-300ms for micro-interactions,Use animations longer than 500ms for UI,transition-all duration-200,duration-1000,Medium
+9,Animation,Reduced Motion,All,Respect user's motion preferences,Check prefers-reduced-motion media query,Ignore accessibility motion settings,@media (prefers-reduced-motion: reduce),No motion query check,High
+10,Animation,Loading States,All,Show feedback during async operations,Use skeleton screens or spinners,Leave UI frozen with no feedback,animate-pulse skeleton,Blank screen while loading,High
+11,Animation,Hover vs Tap,All,Hover effects don't work on touch devices,Use click/tap for primary interactions,Rely only on hover for important actions,onClick handler,onMouseEnter only,High
+12,Animation,Continuous Animation,All,Infinite animations are distracting,Use for loading indicators only,Use for decorative elements,animate-spin on loader,animate-bounce on icons,Medium
+13,Animation,Transform Performance,Web,Some CSS properties trigger expensive repaints,Use transform and opacity for animations,Animate width/height/top/left properties,transform: translateY(),top: 10px animation,Medium
+14,Animation,Easing Functions,All,Linear motion feels robotic,Use ease-out for entering ease-in for exiting,Use linear for UI transitions,ease-out,linear,Low
+15,Layout,Z-Index Management,Web,Stacking context conflicts cause hidden elements,Define z-index scale system (10 20 30 50),Use arbitrary large z-index values,z-10 z-20 z-50,z-[9999],High
+16,Layout,Overflow Hidden,Web,Hidden overflow can clip important content,Test all content fits within containers,Blindly apply overflow-hidden,overflow-auto with scroll,overflow-hidden truncating content,Medium
+17,Layout,Fixed Positioning,Web,Fixed elements can overlap or be inaccessible,Account for safe areas and other fixed elements,Stack multiple fixed elements carelessly,Fixed nav + fixed bottom with gap,Multiple overlapping fixed elements,Medium
+18,Layout,Stacking Context,Web,New stacking contexts reset z-index,Understand what creates new stacking context,Expect z-index to work across contexts,Parent with z-index isolates children,z-index: 9999 not working,Medium
+19,Layout,Content Jumping,Web,Layout shift when content loads is jarring,Reserve space for async content,Let images/content push layout around,aspect-ratio or fixed height,No dimensions on images,High
+20,Layout,Viewport Units,Web,100vh can be problematic on mobile browsers,Use dvh or account for mobile browser chrome,Use 100vh for full-screen mobile layouts,min-h-dvh or min-h-screen,h-screen on mobile,Medium
+21,Layout,Container Width,Web,Content too wide is hard to read,Limit max-width for text content (65-75ch),Let text span full viewport width,max-w-prose or max-w-3xl,Full width paragraphs,Medium
+22,Touch,Touch Target Size,Mobile,Small buttons are hard to tap accurately,Minimum 44x44px touch targets,Tiny clickable areas,min-h-[44px] min-w-[44px],w-6 h-6 buttons,High
+23,Touch,Touch Spacing,Mobile,Adjacent touch targets need adequate spacing,Minimum 8px gap between touch targets,Tightly packed clickable elements,gap-2 between buttons,gap-0 or gap-1,Medium
+24,Touch,Gesture Conflicts,Mobile,Custom gestures can conflict with system,Avoid horizontal swipe on main content,Override system gestures,Vertical scroll primary,Horizontal swipe carousel only,Medium
+25,Touch,Tap Delay,Mobile,300ms tap delay feels laggy,Use touch-action CSS or fastclick,Default mobile tap handling,touch-action: manipulation,No touch optimization,Medium
+26,Touch,Pull to Refresh,Mobile,Accidental refresh is frustrating,Disable where not needed,Enable by default everywhere,overscroll-behavior: contain,Default overscroll,Low
+27,Touch,Haptic Feedback,Mobile,Tactile feedback improves interaction feel,Use for confirmations and important actions,Overuse vibration feedback,navigator.vibrate(10),Vibrate on every tap,Low
+28,Interaction,Focus States,All,Keyboard users need visible focus indicators,Use visible focus rings on interactive elements,Remove focus outline without replacement,focus:ring-2 focus:ring-blue-500,outline-none without alternative,High
+29,Interaction,Hover States,Web,Visual feedback on interactive elements,Change cursor and add subtle visual change,No hover feedback on clickable elements,hover:bg-gray-100 cursor-pointer,No hover style,Medium
+30,Interaction,Active States,All,Show immediate feedback on press/click,Add pressed/active state visual change,No feedback during interaction,active:scale-95,No active state,Medium
+31,Interaction,Disabled States,All,Clearly indicate non-interactive elements,Reduce opacity and change cursor,Confuse disabled with normal state,opacity-50 cursor-not-allowed,Same style as enabled,Medium
+32,Interaction,Loading Buttons,All,Prevent double submission during async actions,Disable button and show loading state,Allow multiple clicks during processing,disabled={loading} spinner,Button clickable while loading,High
+33,Interaction,Error Feedback,All,Users need to know when something fails,Show clear error messages near problem,Silent failures with no feedback,Red border + error message,No indication of error,High
+34,Interaction,Success Feedback,All,Confirm successful actions to users,Show success message or visual change,No confirmation of completed action,Toast notification or checkmark,Action completes silently,Medium
+35,Interaction,Confirmation Dialogs,All,Prevent accidental destructive actions,Confirm before delete/irreversible actions,Delete without confirmation,Are you sure modal,Direct delete on click,High
+36,Accessibility,Color Contrast,All,Text must be readable against background,Minimum 4.5:1 ratio for normal text,Low contrast text,#333 on white (7:1),#999 on white (2.8:1),High
+37,Accessibility,Color Only,All,Don't convey information by color alone,Use icons/text in addition to color,Red/green only for error/success,Red text + error icon,Red border only for error,High
+38,Accessibility,Alt Text,All,Images need text alternatives,Descriptive alt text for meaningful images,Empty or missing alt attributes,alt='Dog playing in park',alt='' for content images,High
+39,Accessibility,Heading Hierarchy,Web,Screen readers use headings for navigation,Use sequential heading levels h1-h6,Skip heading levels or misuse for styling,h1 then h2 then h3,h1 then h4,Medium
+40,Accessibility,ARIA Labels,All,Interactive elements need accessible names,Add aria-label for icon-only buttons,Icon buttons without labels,aria-label='Close menu',<button><Icon/></button>,High
+41,Accessibility,Keyboard Navigation,Web,All functionality accessible via keyboard,Tab order matches visual order,Keyboard traps or illogical tab order,tabIndex for custom order,Unreachable elements,High
+42,Accessibility,Screen Reader,All,Content should make sense when read aloud,Use semantic HTML and ARIA properly,Div soup with no semantics,<nav> <main> <article>,<div> for everything,Medium
+43,Accessibility,Form Labels,All,Inputs must have associated labels,Use label with for attribute or wrap input,Placeholder-only inputs,<label for='email'>,placeholder='Email' only,High
+44,Accessibility,Error Messages,All,Error messages must be announced,Use aria-live or role=alert for errors,Visual-only error indication,role='alert',Red border only,High
+45,Accessibility,Skip Links,Web,Allow keyboard users to skip navigation,Provide skip to main content link,No skip link on nav-heavy pages,Skip to main content link,100 tabs to reach content,Medium
+46,Performance,Image Optimization,All,Large images slow page load,Use appropriate size and format (WebP),Unoptimized full-size images,srcset with multiple sizes,4000px image for 400px display,High
+47,Performance,Lazy Loading,All,Load content as needed,Lazy load below-fold images and content,Load everything upfront,loading='lazy',All images eager load,Medium
+48,Performance,Code Splitting,Web,Large bundles slow initial load,Split code by route/feature,Single large bundle,dynamic import(),All code in main bundle,Medium
+49,Performance,Caching,Web,Repeat visits should be fast,Set appropriate cache headers,No caching strategy,Cache-Control headers,Every request hits server,Medium
+50,Performance,Font Loading,Web,Web fonts can block rendering,Use font-display swap or optional,Invisible text during font load,font-display: swap,FOIT (Flash of Invisible Text),Medium
+51,Performance,Third Party Scripts,Web,External scripts can block rendering,Load non-critical scripts async/defer,Synchronous third-party scripts,async or defer attribute,<script src='...'> in head,Medium
+52,Performance,Bundle Size,Web,Large JavaScript slows interaction,Monitor and minimize bundle size,Ignore bundle size growth,Bundle analyzer,No size monitoring,Medium
+53,Performance,Render Blocking,Web,CSS/JS can block first paint,Inline critical CSS defer non-critical,Large blocking CSS files,Critical CSS inline,All CSS in head,Medium
+54,Forms,Input Labels,All,Every input needs a visible label,Always show label above or beside input,Placeholder as only label,<label>Email</label><input>,placeholder='Email' only,High
+55,Forms,Error Placement,All,Errors should appear near the problem,Show error below related input,Single error message at top of form,Error under each field,All errors at form top,Medium
+56,Forms,Inline Validation,All,Validate as user types or on blur,Validate on blur for most fields,Validate only on submit,onBlur validation,Submit-only validation,Medium
+57,Forms,Input Types,All,Use appropriate input types,Use email tel number url etc,Text input for everything,type='email',type='text' for email,Medium
+58,Forms,Autofill Support,Web,Help browsers autofill correctly,Use autocomplete attribute properly,Block or ignore autofill,autocomplete='email',autocomplete='off' everywhere,Medium
+59,Forms,Required Indicators,All,Mark required fields clearly,Use asterisk or (required) text,No indication of required fields,* required indicator,Guess which are required,Medium
+60,Forms,Password Visibility,All,Let users see password while typing,Toggle to show/hide password,No visibility toggle,Show/hide password button,Password always hidden,Medium
+61,Forms,Submit Feedback,All,Confirm form submission status,Show loading then success/error state,No feedback after submit,Loading -> Success message,Button click with no response,High
+62,Forms,Input Affordance,All,Inputs should look interactive,Use distinct input styling,Inputs that look like plain text,Border/background on inputs,Borderless inputs,Medium
+63,Forms,Mobile Keyboards,Mobile,Show appropriate keyboard for input type,Use inputmode attribute,Default keyboard for all inputs,inputmode='numeric',Text keyboard for numbers,Medium
+64,Responsive,Mobile First,Web,Design for mobile then enhance for larger,Start with mobile styles then add breakpoints,Desktop-first causing mobile issues,Default mobile + md: lg: xl:,Desktop default + max-width queries,Medium
+65,Responsive,Breakpoint Testing,Web,Test at all common screen sizes,Test at 320 375 414 768 1024 1440,Only test on your device,Multiple device testing,Single device development,Medium
+66,Responsive,Touch Friendly,Web,Mobile layouts need touch-sized targets,Increase touch targets on mobile,Same tiny buttons on mobile,Larger buttons on mobile,Desktop-sized targets on mobile,High
+67,Responsive,Readable Font Size,All,Text must be readable on all devices,Minimum 16px body text on mobile,Tiny text on mobile,text-base or larger,text-xs for body text,High
+68,Responsive,Viewport Meta,Web,Set viewport for mobile devices,Use width=device-width initial-scale=1,Missing or incorrect viewport,<meta name='viewport'...>,No viewport meta tag,High
+69,Responsive,Horizontal Scroll,Web,Avoid horizontal scrolling,Ensure content fits viewport width,Content wider than viewport,max-w-full overflow-x-hidden,Horizontal scrollbar on mobile,High
+70,Responsive,Image Scaling,Web,Images should scale with container,Use max-width: 100% on images,Fixed width images overflow,max-w-full h-auto,width='800' fixed,Medium
+71,Responsive,Table Handling,Web,Tables can overflow on mobile,Use horizontal scroll or card layout,Wide tables breaking layout,overflow-x-auto wrapper,Table overflows viewport,Medium
+72,Typography,Line Height,All,Adequate line height improves readability,Use 1.5-1.75 for body text,Cramped or excessive line height,leading-relaxed (1.625),leading-none (1),Medium
+73,Typography,Line Length,Web,Long lines are hard to read,Limit to 65-75 characters per line,Full-width text on large screens,max-w-prose,Full viewport width text,Medium
+74,Typography,Font Size Scale,All,Consistent type hierarchy aids scanning,Use consistent modular scale,Random font sizes,Type scale (12 14 16 18 24 32),Arbitrary sizes,Medium
+75,Typography,Font Loading,Web,Fonts should load without layout shift,Reserve space with fallback font,Layout shift when fonts load,font-display: swap + similar fallback,No fallback font,Medium
+76,Typography,Contrast Readability,All,Body text needs good contrast,Use darker text on light backgrounds,Gray text on gray background,text-gray-900 on white,text-gray-400 on gray-100,High
+77,Typography,Heading Clarity,All,Headings should stand out from body,Clear size/weight difference,Headings similar to body text,Bold + larger size,Same size as body,Medium
+78,Feedback,Loading Indicators,All,Show system status during waits,Show spinner/skeleton for operations > 300ms,No feedback during loading,Skeleton or spinner,Frozen UI,High
+79,Feedback,Empty States,All,Guide users when no content exists,Show helpful message and action,Blank empty screens,No items yet. Create one!,Empty white space,Medium
+80,Feedback,Error Recovery,All,Help users recover from errors,Provide clear next steps,Error without recovery path,Try again button + help link,Error message only,Medium
+81,Feedback,Progress Indicators,All,Show progress for multi-step processes,Step indicators or progress bar,No indication of progress,Step 2 of 4 indicator,No step information,Medium
+82,Feedback,Toast Notifications,All,Transient messages for non-critical info,Auto-dismiss after 3-5 seconds,Toasts that never disappear,Auto-dismiss toast,Persistent toast,Medium
+83,Feedback,Confirmation Messages,All,Confirm successful actions,Brief success message,Silent success,Saved successfully toast,No confirmation,Medium
+84,Content,Truncation,All,Handle long content gracefully,Truncate with ellipsis and expand option,Overflow or broken layout,line-clamp-2 with expand,Overflow or cut off,Medium
+85,Content,Date Formatting,All,Use locale-appropriate date formats,Use relative or locale-aware dates,Ambiguous date formats,2 hours ago or locale format,01/02/03,Low
+86,Content,Number Formatting,All,Format large numbers for readability,Use thousand separators or abbreviations,Long unformatted numbers,"1.2K or 1,234",1234567,Low
+87,Content,Placeholder Content,All,Show realistic placeholders during dev,Use realistic sample data,Lorem ipsum everywhere,Real sample content,Lorem ipsum,Low
+88,Onboarding,User Freedom,All,Users should be able to skip tutorials,Provide Skip and Back buttons,Force linear unskippable tour,Skip Tutorial button,Locked overlay until finished,Medium
+89,Search,Autocomplete,Web,Help users find results faster,Show predictions as user types,Require full type and enter,Debounced fetch + dropdown,No suggestions,Medium
+90,Search,No Results,Web,Dead ends frustrate users,Show 'No results' with suggestions,Blank screen or '0 results',Try searching for X instead,No results found.,Medium
+91,Data Entry,Bulk Actions,Web,Editing one by one is tedious,Allow multi-select and bulk edit,Single row actions only,Checkbox column + Action bar,Repeated actions per row,Low
+92,AI Interaction,Disclaimer,All,Users need to know they talk to AI,Clearly label AI generated content,Present AI as human,AI Assistant label,Fake human name without label,High
+93,AI Interaction,Streaming,All,Waiting for full text is slow,Stream text response token by token,Show loading spinner for 10s+,Typewriter effect,Spinner until 100% complete,Medium
+94,Spatial UI,Gaze Hover,VisionOS,Elements should respond to eye tracking before pinch,Scale/highlight element on look,Static element until pinch,hoverEffect(),onTap only,High
+95,Spatial UI,Depth Layering,VisionOS,UI needs Z-depth to separate content from environment,Use glass material and z-offset,Flat opaque panels blocking view,.glassBackgroundEffect(),bg-white,Medium
+96,Sustainability,Auto-Play Video,Web,Video consumes massive data and energy,Click-to-play or pause when off-screen,Auto-play high-res video loops,playsInline muted preload='none',autoplay loop,Medium
+97,Sustainability,Asset Weight,Web,Heavy 3D/Image assets increase carbon footprint,Compress and lazy load 3D models,Load 50MB textures,Draco compression,Raw .obj files,Medium
+98,AI Interaction,Feedback Loop,All,AI needs user feedback to improve,Thumps up/down or 'Regenerate',Static output only,Feedback component,Read-only text,Low
+99,Accessibility,Motion Sensitivity,All,Parallax/Scroll-jacking causes nausea,Respect prefers-reduced-motion,Force scroll effects,@media (prefers-reduced-motion),ScrollTrigger.create(),High

.cursor/skills/ui-ux-pro-max/data/web-interface.csv

@@ -0,0 +1,31 @@
+No,Category,Issue,Keywords,Platform,Description,Do,Don't,Code Example Good,Code Example Bad,Severity
+1,Accessibility,Icon Button Labels,icon button aria-label,Web,Icon-only buttons must have accessible names,Add aria-label to icon buttons,Icon button without label,"<button aria-label='Close'><XIcon /></button>","<button><XIcon /></button>",Critical
+2,Accessibility,Form Control Labels,form input label aria,Web,All form controls need labels or aria-label,Use label element or aria-label,Input without accessible name,"<label for='email'>Email</label><input id='email' />","<input placeholder='Email' />",Critical
+3,Accessibility,Keyboard Handlers,keyboard onclick onkeydown,Web,Interactive elements must support keyboard interaction,Add onKeyDown alongside onClick,Click-only interaction,"<div onClick={fn} onKeyDown={fn} tabIndex={0}>","<div onClick={fn}>",High
+4,Accessibility,Semantic HTML,semantic button a label,Web,Use semantic HTML before ARIA attributes,Use button/a/label elements,Div with role attribute,"<button onClick={fn}>Submit</button>","<div role='button' onClick={fn}>Submit</div>",High
+5,Accessibility,Aria Live,aria-live polite async,Web,Async updates need aria-live for screen readers,Add aria-live='polite' for dynamic content,Silent async updates,"<div aria-live='polite'>{status}</div>","<div>{status}</div> // no announcement",Medium
+6,Accessibility,Decorative Icons,aria-hidden decorative icon,Web,Decorative icons should be hidden from screen readers,Add aria-hidden='true' to decorative icons,Decorative icon announced,"<Icon aria-hidden='true' />","<Icon /> // announced as 'image'",Medium
+7,Focus,Visible Focus States,focus-visible outline ring,Web,All interactive elements need visible focus states,Use :focus-visible with ring/outline,No focus indication,"focus-visible:ring-2 focus-visible:ring-blue-500","outline-none // no replacement",Critical
+8,Focus,Never Remove Outline,outline-none focus replacement,Web,Never remove outline without providing replacement,Replace outline with visible alternative,Remove outline completely,"focus:outline-none focus:ring-2","focus:outline-none // nothing else",Critical
+9,Focus,Checkbox Radio Hit Target,checkbox radio label target,Web,Checkbox/radio must share hit target with label,Wrap input and label together,Separate tiny checkbox,"<label class='flex gap-2'><input type='checkbox' /><span>Option</span></label>","<input type='checkbox' id='x' /><label for='x'>Option</label>",Medium
+10,Forms,Autocomplete Attribute,autocomplete input form,Web,Inputs need autocomplete attribute for autofill,Add appropriate autocomplete value,Missing autocomplete,"<input autocomplete='email' type='email' />","<input type='email' />",High
+11,Forms,Semantic Input Types,input type email tel url,Web,Use semantic input type attributes,Use email/tel/url/number types,text type for everything,"<input type='email' />","<input type='text' /> // for email",Medium
+12,Forms,Never Block Paste,paste onpaste password,Web,Never prevent paste functionality,Allow paste on all inputs,Block paste on password/code,"<input type='password' />","<input onPaste={e => e.preventDefault()} />",High
+13,Forms,Spellcheck Disable,spellcheck email code,Web,Disable spellcheck on emails and codes,Set spellcheck='false' on codes,Spellcheck on technical input,"<input spellCheck='false' type='email' />","<input type='email' /> // red squiggles",Low
+14,Forms,Submit Button Enabled,submit button disabled loading,Web,Keep submit enabled and show spinner during requests,Show loading spinner keep enabled,Disable button during submit,"<button>{loading ? <Spinner /> : 'Submit'}</button>","<button disabled={loading}>Submit</button>",Medium
+15,Forms,Inline Errors,error message inline focus,Web,Show error messages inline near the problem field,Inline error with focus on first error,Single error at top,"<input /><span class='text-red-500'>{error}</span>","<div class='error'>{allErrors}</div> // at top",High
+16,Performance,Virtualize Lists,virtualize list 50 items,Web,Virtualize lists exceeding 50 items,Use virtual list for large datasets,Render all items,"<VirtualList items={items} />","items.map(item => <Item />)",High
+17,Performance,Avoid Layout Reads,layout read render getboundingclientrect,Web,Avoid layout reads during render phase,Read layout in effects or callbacks,getBoundingClientRect in render,"useEffect(() => { el.getBoundingClientRect() })","const rect = el.getBoundingClientRect() // in render",Medium
+18,Performance,Batch DOM Operations,batch dom write read,Web,Group DOM operations to minimize reflows,Batch writes then reads,Interleave reads and writes,"writes.forEach(w => w()); reads.forEach(r => r())","write(); read(); write(); read(); // thrashing",Medium
+19,Performance,Preconnect CDN,preconnect link cdn,Web,Add preconnect links for CDN domains,Preconnect to known domains,"<link rel='preconnect' href='https://cdn.example.com' />","// no preconnect hint",Low
+20,Performance,Lazy Load Images,lazy loading image below-fold,Web,Lazy-load images below the fold,Use loading='lazy' for below-fold images,Load all images eagerly,"<img loading='lazy' src='...' />","<img src='...' /> // above fold only",Medium
+21,State,URL Reflects State,url state query params,Web,URL should reflect current UI state,Sync filters/tabs/pagination to URL,State only in memory,"?tab=settings&page=2","useState only // lost on refresh",High
+22,State,Deep Linking,deep link stateful component,Web,Stateful components should support deep-linking,Enable sharing current view via URL,No shareable state,"router.push({ query: { ...filters } })","setFilters(f) // not in URL",Medium
+23,State,Confirm Destructive Actions,confirm destructive delete modal,Web,Destructive actions require confirmation,Show confirmation dialog before delete,Delete without confirmation,"if (confirm('Delete?')) delete()","onClick={delete} // no confirmation",High
+24,Typography,Proper Unicode,unicode ellipsis quotes,Web,Use proper Unicode characters,Use ... curly quotes proper dashes,ASCII approximations,"'Hello...' with proper ellipsis","'Hello...' with three dots",Low
+25,Typography,Text Overflow,truncate line-clamp overflow,Web,Handle text overflow properly,Use truncate/line-clamp/break-words,Text overflows container,"<p class='truncate'>Long text...</p>","<p>Long text...</p> // overflows",Medium
+26,Typography,Non-Breaking Spaces,nbsp unit brand,Web,Use non-breaking spaces for units and brand names,Use &nbsp; between number and unit,"10&nbsp;kg or Next.js&nbsp;14","10 kg // may wrap",Low
+27,Anti-Pattern,No Zoom Disable,viewport zoom disable,Web,Never disable zoom in viewport meta,Allow user zoom,"<meta name='viewport' content='width=device-width'>","<meta name='viewport' content='maximum-scale=1'>",Critical
+28,Anti-Pattern,No Transition All,transition all specific,Web,Avoid transition: all - specify properties,Transition specific properties,transition: all,"transition-colors duration-200","transition-all duration-200",Medium
+29,Anti-Pattern,Outline Replacement,outline-none ring focus,Web,Never use outline-none without replacement,Provide visible focus replacement,Remove outline with nothing,"focus:outline-none focus:ring-2 focus:ring-blue-500","focus:outline-none // alone",Critical
+30,Anti-Pattern,No Hardcoded Dates,date format intl locale,Web,Use Intl for date/number formatting,Use Intl.DateTimeFormat,Hardcoded date format,"new Intl.DateTimeFormat('en').format(date)","date.toLocaleDateString() // or manual format",Medium

.cursor/skills/ui-ux-pro-max/scripts/core.py

@@ -0,0 +1,253 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+UI/UX Pro Max Core - BM25 search engine for UI/UX style guides
+"""
+
+import csv
+import re
+from pathlib import Path
+from math import log
+from collections import defaultdict
+
+# ============ CONFIGURATION ============
+DATA_DIR = Path(__file__).parent.parent / "data"
+MAX_RESULTS = 3
+
+CSV_CONFIG = {
+    "style": {
+        "file": "styles.csv",
+        "search_cols": ["Style Category", "Keywords", "Best For", "Type", "AI Prompt Keywords"],
+        "output_cols": ["Style Category", "Type", "Keywords", "Primary Colors", "Effects & Animation", "Best For", "Performance", "Accessibility", "Framework Compatibility", "Complexity", "AI Prompt Keywords", "CSS/Technical Keywords", "Implementation Checklist", "Design System Variables"]
+    },
+    "color": {
+        "file": "colors.csv",
+        "search_cols": ["Product Type", "Notes"],
+        "output_cols": ["Product Type", "Primary (Hex)", "Secondary (Hex)", "CTA (Hex)", "Background (Hex)", "Text (Hex)", "Notes"]
+    },
+    "chart": {
+        "file": "charts.csv",
+        "search_cols": ["Data Type", "Keywords", "Best Chart Type", "Accessibility Notes"],
+        "output_cols": ["Data Type", "Keywords", "Best Chart Type", "Secondary Options", "Color Guidance", "Accessibility Notes", "Library Recommendation", "Interactive Level"]
+    },
+    "landing": {
+        "file": "landing.csv",
+        "search_cols": ["Pattern Name", "Keywords", "Conversion Optimization", "Section Order"],
+        "output_cols": ["Pattern Name", "Keywords", "Section Order", "Primary CTA Placement", "Color Strategy", "Conversion Optimization"]
+    },
+    "product": {
+        "file": "products.csv",
+        "search_cols": ["Product Type", "Keywords", "Primary Style Recommendation", "Key Considerations"],
+        "output_cols": ["Product Type", "Keywords", "Primary Style Recommendation", "Secondary Styles", "Landing Page Pattern", "Dashboard Style (if applicable)", "Color Palette Focus"]
+    },
+    "ux": {
+        "file": "ux-guidelines.csv",
+        "search_cols": ["Category", "Issue", "Description", "Platform"],
+        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
+    },
+    "typography": {
+        "file": "typography.csv",
+        "search_cols": ["Font Pairing Name", "Category", "Mood/Style Keywords", "Best For", "Heading Font", "Body Font"],
+        "output_cols": ["Font Pairing Name", "Category", "Heading Font", "Body Font", "Mood/Style Keywords", "Best For", "Google Fonts URL", "CSS Import", "Tailwind Config", "Notes"]
+    },
+    "icons": {
+        "file": "icons.csv",
+        "search_cols": ["Category", "Icon Name", "Keywords", "Best For"],
+        "output_cols": ["Category", "Icon Name", "Keywords", "Library", "Import Code", "Usage", "Best For", "Style"]
+    },
+    "react": {
+        "file": "react-performance.csv",
+        "search_cols": ["Category", "Issue", "Keywords", "Description"],
+        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
+    },
+    "web": {
+        "file": "web-interface.csv",
+        "search_cols": ["Category", "Issue", "Keywords", "Description"],
+        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
+    }
+}
+
+STACK_CONFIG = {
+    "html-tailwind": {"file": "stacks/html-tailwind.csv"},
+    "react": {"file": "stacks/react.csv"},
+    "nextjs": {"file": "stacks/nextjs.csv"},
+    "astro": {"file": "stacks/astro.csv"},
+    "vue": {"file": "stacks/vue.csv"},
+    "nuxtjs": {"file": "stacks/nuxtjs.csv"},
+    "nuxt-ui": {"file": "stacks/nuxt-ui.csv"},
+    "svelte": {"file": "stacks/svelte.csv"},
+    "swiftui": {"file": "stacks/swiftui.csv"},
+    "react-native": {"file": "stacks/react-native.csv"},
+    "flutter": {"file": "stacks/flutter.csv"},
+    "shadcn": {"file": "stacks/shadcn.csv"},
+    "jetpack-compose": {"file": "stacks/jetpack-compose.csv"}
+}
+
+# Common columns for all stacks
+_STACK_COLS = {
+    "search_cols": ["Category", "Guideline", "Description", "Do", "Don't"],
+    "output_cols": ["Category", "Guideline", "Description", "Do", "Don't", "Code Good", "Code Bad", "Severity", "Docs URL"]
+}
+
+AVAILABLE_STACKS = list(STACK_CONFIG.keys())
+
+
+# ============ BM25 IMPLEMENTATION ============
+class BM25:
+    """BM25 ranking algorithm for text search"""
+
+    def __init__(self, k1=1.5, b=0.75):
+        self.k1 = k1
+        self.b = b
+        self.corpus = []
+        self.doc_lengths = []
+        self.avgdl = 0
+        self.idf = {}
+        self.doc_freqs = defaultdict(int)
+        self.N = 0
+
+    def tokenize(self, text):
+        """Lowercase, split, remove punctuation, filter short words"""
+        text = re.sub(r'[^\w\s]', ' ', str(text).lower())
+        return [w for w in text.split() if len(w) > 2]
+
+    def fit(self, documents):
+        """Build BM25 index from documents"""
+        self.corpus = [self.tokenize(doc) for doc in documents]
+        self.N = len(self.corpus)
+        if self.N == 0:
+            return
+        self.doc_lengths = [len(doc) for doc in self.corpus]
+        self.avgdl = sum(self.doc_lengths) / self.N
+
+        for doc in self.corpus:
+            seen = set()
+            for word in doc:
+                if word not in seen:
+                    self.doc_freqs[word] += 1
+                    seen.add(word)
+
+        for word, freq in self.doc_freqs.items():
+            self.idf[word] = log((self.N - freq + 0.5) / (freq + 0.5) + 1)
+
+    def score(self, query):
+        """Score all documents against query"""
+        query_tokens = self.tokenize(query)
+        scores = []
+
+        for idx, doc in enumerate(self.corpus):
+            score = 0
+            doc_len = self.doc_lengths[idx]
+            term_freqs = defaultdict(int)
+            for word in doc:
+                term_freqs[word] += 1
+
+            for token in query_tokens:
+                if token in self.idf:
+                    tf = term_freqs[token]
+                    idf = self.idf[token]
+                    numerator = tf * (self.k1 + 1)
+                    denominator = tf + self.k1 * (1 - self.b + self.b * doc_len / self.avgdl)
+                    score += idf * numerator / denominator
+
+            scores.append((idx, score))
+
+        return sorted(scores, key=lambda x: x[1], reverse=True)
+
+
+# ============ SEARCH FUNCTIONS ============
+def _load_csv(filepath):
+    """Load CSV and return list of dicts"""
+    with open(filepath, 'r', encoding='utf-8') as f:
+        return list(csv.DictReader(f))
+
+
+def _search_csv(filepath, search_cols, output_cols, query, max_results):
+    """Core search function using BM25"""
+    if not filepath.exists():
+        return []
+
+    data = _load_csv(filepath)
+
+    # Build documents from search columns
+    documents = [" ".join(str(row.get(col, "")) for col in search_cols) for row in data]
+
+    # BM25 search
+    bm25 = BM25()
+    bm25.fit(documents)
+    ranked = bm25.score(query)
+
+    # Get top results with score > 0
+    results = []
+    for idx, score in ranked[:max_results]:
+        if score > 0:
+            row = data[idx]
+            results.append({col: row.get(col, "") for col in output_cols if col in row})
+
+    return results
+
+
+def detect_domain(query):
+    """Auto-detect the most relevant domain from query"""
+    query_lower = query.lower()
+
+    domain_keywords = {
+        "color": ["color", "palette", "hex", "#", "rgb"],
+        "chart": ["chart", "graph", "visualization", "trend", "bar", "pie", "scatter", "heatmap", "funnel"],
+        "landing": ["landing", "page", "cta", "conversion", "hero", "testimonial", "pricing", "section"],
+        "product": ["saas", "ecommerce", "e-commerce", "fintech", "healthcare", "gaming", "portfolio", "crypto", "dashboard"],
+        "style": ["style", "design", "ui", "minimalism", "glassmorphism", "neumorphism", "brutalism", "dark mode", "flat", "aurora", "prompt", "css", "implementation", "variable", "checklist", "tailwind"],
+        "ux": ["ux", "usability", "accessibility", "wcag", "touch", "scroll", "animation", "keyboard", "navigation", "mobile"],
+        "typography": ["font", "typography", "heading", "serif", "sans"],
+        "icons": ["icon", "icons", "lucide", "heroicons", "symbol", "glyph", "pictogram", "svg icon"],
+        "react": ["react", "next.js", "nextjs", "suspense", "memo", "usecallback", "useeffect", "rerender", "bundle", "waterfall", "barrel", "dynamic import", "rsc", "server component"],
+        "web": ["aria", "focus", "outline", "semantic", "virtualize", "autocomplete", "form", "input type", "preconnect"]
+    }
+
+    scores = {domain: sum(1 for kw in keywords if kw in query_lower) for domain, keywords in domain_keywords.items()}
+    best = max(scores, key=scores.get)
+    return best if scores[best] > 0 else "style"
+
+
+def search(query, domain=None, max_results=MAX_RESULTS):
+    """Main search function with auto-domain detection"""
+    if domain is None:
+        domain = detect_domain(query)
+
+    config = CSV_CONFIG.get(domain, CSV_CONFIG["style"])
+    filepath = DATA_DIR / config["file"]
+
+    if not filepath.exists():
+        return {"error": f"File not found: {filepath}", "domain": domain}
+
+    results = _search_csv(filepath, config["search_cols"], config["output_cols"], query, max_results)
+
+    return {
+        "domain": domain,
+        "query": query,
+        "file": config["file"],
+        "count": len(results),
+        "results": results
+    }
+
+
+def search_stack(query, stack, max_results=MAX_RESULTS):
+    """Search stack-specific guidelines"""
+    if stack not in STACK_CONFIG:
+        return {"error": f"Unknown stack: {stack}. Available: {', '.join(AVAILABLE_STACKS)}"}
+
+    filepath = DATA_DIR / STACK_CONFIG[stack]["file"]
+
+    if not filepath.exists():
+        return {"error": f"Stack file not found: {filepath}", "stack": stack}
+
+    results = _search_csv(filepath, _STACK_COLS["search_cols"], _STACK_COLS["output_cols"], query, max_results)
+
+    return {
+        "domain": "stack",
+        "stack": stack,
+        "query": query,
+        "file": STACK_CONFIG[stack]["file"],
+        "count": len(results),
+        "results": results
+    }

.cursor/skills/ui-ux-pro-max/scripts/search.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+UI/UX Pro Max Search - BM25 search engine for UI/UX style guides
+Usage: python search.py "<query>" [--domain <domain>] [--stack <stack>] [--max-results 3]
+       python search.py "<query>" --design-system [-p "Project Name"]
+       python search.py "<query>" --design-system --persist [-p "Project Name"] [--page "dashboard"]
+
+Domains: style, prompt, color, chart, landing, product, ux, typography
+Stacks: html-tailwind, react, nextjs
+
+Persistence (Master + Overrides pattern):
+  --persist    Save design system to design-system/MASTER.md
+  --page       Also create a page-specific override file in design-system/pages/
+"""
+
+import argparse
+import sys
+import io
+from core import CSV_CONFIG, AVAILABLE_STACKS, MAX_RESULTS, search, search_stack
+from design_system import generate_design_system, persist_design_system
+
+# Force UTF-8 for stdout/stderr to handle emojis on Windows (cp1252 default)
+if sys.stdout.encoding and sys.stdout.encoding.lower() != 'utf-8':
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
+if sys.stderr.encoding and sys.stderr.encoding.lower() != 'utf-8':
+    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8')
+
+
+def format_output(result):
+    """Format results for Claude consumption (token-optimized)"""
+    if "error" in result:
+        return f"Error: {result['error']}"
+
+    output = []
+    if result.get("stack"):
+        output.append(f"## UI Pro Max Stack Guidelines")
+        output.append(f"**Stack:** {result['stack']} | **Query:** {result['query']}")
+    else:
+        output.append(f"## UI Pro Max Search Results")
+        output.append(f"**Domain:** {result['domain']} | **Query:** {result['query']}")
+    output.append(f"**Source:** {result['file']} | **Found:** {result['count']} results\n")
+
+    for i, row in enumerate(result['results'], 1):
+        output.append(f"### Result {i}")
+        for key, value in row.items():
+            value_str = str(value)
+            if len(value_str) > 300:
+                value_str = value_str[:300] + "..."
+            output.append(f"- **{key}:** {value_str}")
+        output.append("")
+
+    return "\n".join(output)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="UI Pro Max Search")
+    parser.add_argument("query", help="Search query")
+    parser.add_argument("--domain", "-d", choices=list(CSV_CONFIG.keys()), help="Search domain")
+    parser.add_argument("--stack", "-s", choices=AVAILABLE_STACKS, help="Stack-specific search (html-tailwind, react, nextjs)")
+    parser.add_argument("--max-results", "-n", type=int, default=MAX_RESULTS, help="Max results (default: 3)")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    # Design system generation
+    parser.add_argument("--design-system", "-ds", action="store_true", help="Generate complete design system recommendation")
+    parser.add_argument("--project-name", "-p", type=str, default=None, help="Project name for design system output")
+    parser.add_argument("--format", "-f", choices=["ascii", "markdown"], default="ascii", help="Output format for design system")
+    # Persistence (Master + Overrides pattern)
+    parser.add_argument("--persist", action="store_true", help="Save design system to design-system/MASTER.md (creates hierarchical structure)")
+    parser.add_argument("--page", type=str, default=None, help="Create page-specific override file in design-system/pages/")
+    parser.add_argument("--output-dir", "-o", type=str, default=None, help="Output directory for persisted files (default: current directory)")
+
+    args = parser.parse_args()
+
+    # Design system takes priority
+    if args.design_system:
+        result = generate_design_system(
+            args.query, 
+            args.project_name, 
+            args.format,
+            persist=args.persist,
+            page=args.page,
+            output_dir=args.output_dir
+        )
+        print(result)
+        
+        # Print persistence confirmation
+        if args.persist:
+            project_slug = args.project_name.lower().replace(' ', '-') if args.project_name else "default"
+            print("\n" + "=" * 60)
+            print(f"✅ Design system persisted to design-system/{project_slug}/")
+            print(f"   📄 design-system/{project_slug}/MASTER.md (Global Source of Truth)")
+            if args.page:
+                page_filename = args.page.lower().replace(' ', '-')
+                print(f"   📄 design-system/{project_slug}/pages/{page_filename}.md (Page Overrides)")
+            print("")
+            print(f"📖 Usage: When building a page, check design-system/{project_slug}/pages/[page].md first.")
+            print(f"   If exists, its rules override MASTER.md. Otherwise, use MASTER.md.")
+            print("=" * 60)
+    # Stack search
+    elif args.stack:
+        result = search_stack(args.query, args.stack, args.max_results)
+        if args.json:
+            import json
+            print(json.dumps(result, indent=2, ensure_ascii=False))
+        else:
+            print(format_output(result))
+    # Domain search
+    else:
+        result = search(args.query, args.domain, args.max_results)
+        if args.json:
+            import json
+            print(json.dumps(result, indent=2, ensure_ascii=False))
+        else:
+            print(format_output(result))

.cursorrules

@@ -0,0 +1,124 @@
+# zkxw 工程 Cursor 规则
+
+本仓库含 Web 管理端（`web-admin`）、小程序端（`miniprogram`）等子工程。实现或修改 UI 时，**以文档为权威来源**，本文件仅作快速索引与强约束摘要。
+
+## 权威文档（必读路径）
+
+- **Web 管理端（Fresh Mint）**：`docs/web-admin-ui-spec-fresh-mint.md` 
+  适用范围：`web-admin`（Vue 3 + Element Plus + SCSS/Tailwind）。色值、布局、列表、弹窗、树形路径等均以该文档及其中引用的 `fresh-mint-green.html` 为准。
+- **界面模式索引（选型 + 参考页）**：`docs/web-admin-ui-pattern-index.md`  
+  新功能开发前按「功能特征 → 模式编号 P01–P27 → Hash/源码」选型；与 Demo 模板页、业务参考页对照。
+- **小程序端（三墙 Demo 体系）**：`docs/miniprogram-ui-spec-sanqiang.md`  
+  适用范围：`miniprogram`（客户端 / 供应商端 / 配送员端）。视觉以该文档及 `mobile-ui/sanqiang-*.html` 为准。
+
+修改对应子工程前，若涉及界面，应先检索上述文档中的章节（类名、Token、结构顺序）。
+
+## OpenSpec 工程规范
+
+详见 **Cursor 项目规则**：`.cursor/rules/openspec-zkxw-standards.mdc`（`alwaysApply: true`，与 Cursor 2.x 推荐方式一致）。根目录本文件保留 UI 与工程摘要；OpenSpec 路径与 SHALL 门禁以该 `.mdc` 为准。
+
+---
+
+## Web 管理端（`web-admin`）摘要
+
+**列表主标题竖条、新增/编辑弹窗两列～五列、`dialog-form-layout` 限高与正文滚动** 等实现约定：见 Cursor 规则 **`.cursor/rules/web-admin-crud-dialog.mdc`**（编辑 `web-admin` 下 `.vue` / `.scss` 时由 Cursor 按 glob 自动附加该规则）。
+
+### 技术栈与实现方式
+
+- Vue 3 + Element Plus；主题与皮肤通过 **CSS 变量 + Element 主题变量 + 全局覆盖** 对齐规范，**勿随意改 Token 色值**。
+- 树形主数据全路径：`web-admin/src/utils/tree-path.ts`（如 `buildTreePathLabelFromFlat`、`buildPathLabelMapFromTreeRoots`、`resolveTreePathDisplay`）。路径分隔符统一为 **` / `**（半角斜杠两侧各一空格）。
+
+### 页面级 UI 模板（固定五页 + 工作台入口）
+
+上述页面均挂在侧栏 **「Demo」** 菜单下。新开发的列表/表单页**对照以下页面实现**，勿另起一套布局与类名习惯；仍须同时遵守 `docs/web-admin-ui-spec-fresh-mint.md`。
+
+| 用途 | Hash 路由 | 源码 |
+|------|-----------|------|
+| 工作台（入口与说明） | `/#/demo/console` | `web-admin/src/views/dashboard/console/index.vue` |
+| 标准列表（筛选、工具栏、表格、分页） | `/#/demo/unit` | `web-admin/src/views/system/unit/index.vue` |
+| 复杂业务列表（状态、操作列等） | `/#/demo/order` | `web-admin/src/views/system/order/index.vue` |
+| 商品类列表与查看弹窗联动 | `/#/demo/product` | `web-admin/src/views/system/product/index.vue` |
+| 树形主数据 | `/#/demo/category` | `web-admin/src/views/system/category/index.vue` |
+| 系统用户类 CRUD | `/#/demo/user` | `web-admin/src/views/system/user/index.vue` |
+
+商品**只读查看弹窗**结构对齐：`web-admin/src/components/business/product-view-dialog/index.vue`（由商品管理页打开，可与上表第三行一并参照）。
+
+### 视觉与 Token（与规范一致）
+
+- 主色链：`--primary` `#10b981`、`--primary-dark` `#059669`、`--primary-bg` `#ecfdf5`；中性字与边框见规范第 2 节表格。
+- 风格：清爽 B 端、薄荷绿 + Slate；**避免一屏多种高饱和色**；次要信息用 muted 与 `.tag.muted`。
+- 字体：Inter + 系统栈；正文 14px / line-height 1.5。
+
+### 布局与页面骨架
+
+- 侧栏 220px、顶栏 56px、内容区 padding 24px；面板圆角 10px，输入/按钮等 8px 级圆角见规范。
+- 列表页典型顺序：**筛选 `filter-block`（可选）→ 列表工具栏 → `list-body` / `list-wrap`（含 `el-table`）→ 分页**。
+- **单标题**：列表面板仅一个 `panel-top` 主标题；筛选区内不要再加「筛选条件」等重复标题。
+- **单分隔线**：工具栏与列表之间靠 `list-body` 顶边框；列表与分页之间保留列表底边与分页顶边规则，避免双线叠加（见规范列表与分页章节）。
+
+### 筛选与表单
+
+- 筛选栅格、label 11px、控件高度 36px、placeholder 规则等见规范第 5 节。
+- 筛选区内部：**不要用横向分割线** 区分多行条件与展开区，仅用 gap / margin。
+- 弹窗表单：**`label-position="top"`**；两列可用 `form-grid-2`；长字段 `grid-column: 1 / -1`。
+- 弹窗底栏：取消/确定建议 **Close / Check** 图标，图标与文字间距 **6px**；footer 按钮高度与圆角等见规范 `el-dialog` 小节。
+- 长表单：`el-form` 建议 **`scroll-to-error`** 与 **`scroll-into-view-options`**；校验失败可配合 `ElMessageBox.alert` 提示（与已有页一致）。
+- 遮罩：**无背景模糊**（`backdrop-filter: none`、`modal-class` 等与现有 `order-module-dialog-mask` 等策略一致）。
+
+### 列表工具栏与表格
+
+- 工具栏：**「已选 N 项」在最前**，其后从左到右排列主按钮与批量操作；**禁止**用 `space-between` 把整组按钮推到行末。
+- **同一行仅第一个主行动** 使用主色实心（`type="primary"` / `btn-main`）；批量删除、导入导出等为中性描边。
+- **操作列**：`fixed="right"`，预留足够宽度（建议 min-width ≥ 260px），避免按钮被裁切。
+- 主表：`list-table` + `stripe`；与参考页「订单列表」`/#/demo/order` 一致时 **勿随意加 `border`**（以规范及上表模板页为准）。
+- 分页：表格与 **`el-pagination`** 同放在 **`list-body.list-wrap`** 内；外层 **`.pagination.list-pager-bar`**，`margin-top: 0`，上边框与 padding 见规范第 7.9 节。
+
+### 树形选择器与查看态
+
+- 下拉树节点文案：**本级名称**；选中后输入框、表格列、导出、查看弹窗：**全路径**（见规范树形与第 5.6 节）。
+
+### 状态与业务色
+
+- 进行中/主状态：浅绿底 + 深绿字；警告琥珀 `#d97706` 系；危险红系用于强提醒；与订单/配送枚举映射时保持语义一致（见规范第 12 节）。
+
+---
+
+## 小程序端（`miniprogram`）摘要
+
+### Token 与适配
+
+- 品牌绿：`#0a9f6d` / `#087f57` / `#e9f9f2`；大麦黄辅助：`#d6a343` / `#fff7e8`；中性背景与边框见规范第 2.1 节。
+- 主基线宽度 **375px**，兼容 **414px**；间距节奏 8–16；卡片圆角 12–16px，大容器 18–22px。
+
+### 三端统一骨架
+
+- 顺序一般为：Header（绿渐变）→ 统计/提示（可选）→ 功能宫格 → 主列表/任务 → 底部固定区（客户端：结算条 + TabBar）。
+- Header：绿色渐变、标题左对齐、操作右对齐、下缘大圆角（约 20–24px）。
+
+### 组件与媒体（强约束）
+
+- 列表缩略图：**1:1**，`aspectFill`；轮播：**4:3**，`aspectFill`；详情图：**widthFix**；视频建议 720p 内、尽量短（见规范第 7.0 节）。
+- 状态标签语义：`warning` 琥珀待处理、`success` 绿色进行中或完成、`danger` 红色异常；避免同屏过多高饱和色。
+- 底部结算条：数量 → 总价 → 主按钮；主按钮视觉优先级最高。
+- 触达区域不小于 **44×44**；注意横滑与纵向滚动冲突（尤其一级分类横滑）。
+
+### 从 Demo 到页面
+
+- 规范第 11 节给出 Demo class 到 `pages/**/*.vue` 的建议类名；优先统一 Token 与骨架，再收敛公共样式到 `src/styles` 或公共组件。
+- 新增页面类型应先在 `docs/miniprogram-ui-spec-sanqiang.md` 补充结构说明再落代码（见规范第 10 节）。
+
+---
+
+## 通用开发原则
+
+- **最小必要改动**：不扩大范围、不做无关重构；新增代码与周边文件的命名、类型、导入风格保持一致。
+- **跨端颜色不要混用**：管理端用 Fresh Mint 链（`#10b981` 等）；小程序用三墙 Token（`#0a9f6d` 等）；除非产品明确要求对齐，否则不要简单复制另一端的色值。
+- **后端/API 变更**：若 UI 改动依赖接口字段（如树节点 id、分类全路径），需同步评估接口与类型定义，避免前端仅末级展示造成歧义。
+- 提交信息使用完整句子，说明「改了什么、为何」，避免无意义前缀堆砌。
+
+---
+
+## 语言
+
+- 与用户沟通时：若用户使用简体中文，助手回复使用**简体中文**。
+- 代码注释与用户可见文案：遵循项目现有语言习惯（中文业务文案以产品为准）。

.dockerignore

@@ -0,0 +1,29 @@
+# Web 镜像构建上下文为仓库根目录（deploy/docker/web-admin/Dockerfile）
+# 后端镜像使用 backend/ 子目录上下文，不受本文件影响
+
+backend/
+miniprogram/
+mobile-ui/
+docs/
+openspec/
+.cursor/
+.agents/
+dist/
+*.tar.gz
+
+# web-admin/.dockerignore 在根上下文下不生效，须在此显式排除
+web-admin/node_modules
+web-admin/dist
+web-admin/.git
+web-admin/graphify-out
+web-admin/src/graphify-out
+web-admin/.husky
+web-admin/CHANGELOG*
+web-admin/demo-*.html
+web-admin/playwright-report
+web-admin/test-results
+web-admin/.DS_Store
+web-admin/**/*.local
+web-admin/.env
+web-admin/.env.*
+!web-admin/.env.docker

.gitignore

@@ -0,0 +1,86 @@
+# macOS
+.DS_Store
+.AppleDouble
+.LSOverride
+._*
+
+# Windows
+Thumbs.db
+ehthumbs.db
+Desktop.ini
+
+# Linux
+*~
+
+# 编辑器 / IDE
+.history/
+.idea/
+*.iml
+*.swp
+*.swo
+*~
+.project
+.classpath
+.settings/
+
+# VS Code / Cursor（保留团队共享配置时可按需取消注释）
+# .vscode/*
+# !.vscode/extensions.json
+# !.vscode/settings.json
+
+# 依赖与构建产物
+node_modules/
+dist/
+build/
+out/
+target/
+*.egg-info/
+.eggs/
+__pycache__/
+*.py[cod]
+*$py.class
+.Python
+*.class
+*.jar
+*.war
+*.ear
+
+# 环境与密钥
+.env
+.env.*
+!.env.example
+*.pem
+*.key
+*.p12
+secrets/
+
+# 日志与临时文件
+*.log
+logs/
+tmp/
+temp/
+*.tmp
+*.bak
+*.cache
+
+# 测试与覆盖率
+coverage/
+.nyc_output/
+htmlcov/
+.pytest_cache/
+.tox/
+.coverage
+*.lcov
+
+# 数据库与本地数据
+*.sqlite
+*.sqlite3
+*.db
+
+# 上传与导出（业务附件、导出文件等本地目录）
+uploads/
+exports/
+.superpowers/
+
+# Local git worktrees (isolated feature checkouts)
+.worktrees/

.opencode/commands/opsx-apply.md

@@ -0,0 +1,149 @@
+---
+description: Implement tasks from an OpenSpec change (Experimental)
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name (e.g., `/opsx-apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx-apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx-continue`
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! You can archive this change with `/opsx-archive`.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly

.opencode/commands/opsx-archive.md

@@ -0,0 +1,154 @@
+---
+description: Archive a completed change in the experimental workflow
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name after `/opsx-archive` (e.g., `/opsx-archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Spec sync status (synced / sync skipped / no delta specs)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success (No Delta Specs)**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** No delta specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success With Warnings**
+
+```
+## Archive Complete (with warnings)
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** Sync skipped (user chose to skip)
+
+**Warnings:**
+- Archived with 2 incomplete artifacts
+- Archived with 3 incomplete tasks
+- Delta spec sync was skipped (user chose to skip)
+
+Review the archive if this was not intentional.
+```
+
+**Output On Error (Archive Exists)**
+
+```
+## Archive Failed
+
+**Change:** <change-name>
+**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
+
+Target archive directory already exists.
+
+**Options:**
+1. Rename the existing archive
+2. Delete the existing archive if it's a duplicate
+3. Wait until a different date to archive
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting

.opencode/commands/opsx-explore.md

@@ -0,0 +1,170 @@
+---
+description: Enter explore mode - think through ideas, investigate problems, clarify requirements
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+**Input**: The argument after `/opsx-explore` is whatever the user wants to think about. Could be:
+- A vague idea: "real-time collaboration"
+- A specific problem: "the auth system is getting unwieldy"
+- A change name: "add-dark-mode" (to explore in context of that change)
+- A comparison: "postgres vs sqlite for this"
+- Nothing (just enter explore mode)
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+If the user mentioned a specific change name, read its artifacts for context.
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own

.opencode/commands/opsx-propose.md

@@ -0,0 +1,103 @@
+---
+description: Propose a new change - create it and generate all artifacts in one step
+---
+
+Propose a new change - create the change and generate all artifacts in one step.
+
+I'll create a change with artifacts:
+- proposal.md (what & why)
+- design.md (how)
+- tasks.md (implementation steps)
+
+When ready to implement, run /opsx-apply
+
+---
+
+**Input**: The argument after `/opsx-propose` is the change name (kebab-case), OR a description of what the user wants to build.
+
+**Steps**
+
+1. **If no input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx-apply` to start implementing."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, ask if user wants to continue it or create a new one
+- Verify each artifact file exists after writing before proceeding to next

.opencode/interaction-convention.md

@@ -0,0 +1,5 @@
+# 交互规范
+
+- 所有回复和思考必须使用中文
+- 每次回复开头称呼用户为"龙舞"
+- 视觉读取（图片分析、截图识别等）优先使用自身能力

.opencode/skills/openspec-apply-change/SKILL.md

@@ -0,0 +1,156 @@
+---
+name: openspec-apply-change
+description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx-apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! Ready to archive this change.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly

.opencode/skills/openspec-archive-change/SKILL.md

@@ -0,0 +1,114 @@
+---
+name: openspec-archive-change
+description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Whether specs were synced (if applicable)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
+
+All artifacts complete. All tasks complete.
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use openspec-sync-specs approach (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting

.opencode/skills/openspec-explore/SKILL.md

@@ -0,0 +1,288 @@
+---
+name: openspec-explore
+description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Handling Different Entry Points
+
+**User brings a vague idea:**
+```
+User: I'm thinking about adding real-time collaboration
+
+You: Real-time collab is a big space. Let me think about this...
+
+      COLLABORATION SPECTRUM
+      ════════════════════════════════════════════
+
+      Awareness          Coordination         Sync
+          │                   │                 │
+          ▼                   ▼                 ▼
+      ┌────────┐         ┌────────┐        ┌────────┐
+      │Presence│         │Cursors │        │  CRDT  │
+      │  "3    │         │ Multi  │        │Conflict│
+      │online" │         │ select │        │  free  │
+      └────────┘         └────────┘        └────────┘
+          │                   │                 │
+       trivial            moderate           complex
+
+      Where's your head at?
+```
+
+**User brings a specific problem:**
+```
+User: The auth system is a mess
+
+You: [reads codebase]
+
+     ┌─────────────────────────────────────────────┐
+     │              CURRENT AUTH FLOW              │
+     └─────────────────────────────────────────────┘
+                        │
+          ┌─────────────┼─────────────┐
+          ▼             ▼             ▼
+     ┌─────────┐  ┌─────────┐  ┌─────────┐
+     │ Google  │  │  GitHub │  │  Email  │
+     │  OAuth  │  │  OAuth  │  │  Magic  │
+     └────┬────┘  └────┬────┘  └────┬────┘
+          │             │             │
+          └─────────────┼─────────────┘
+                        ▼
+                  ┌───────────┐
+                  │  Session  │
+                  └─────┬─────┘
+                        │
+                        ▼
+                  ┌───────────┐
+                  │   Perms   │
+                  └───────────┘
+
+     I see three tangles. Which one's burning?
+```
+
+**User is stuck mid-implementation:**
+```
+User: /opsx-explore add-auth-system
+      The OAuth integration is more complex than expected
+
+You: [reads change artifacts]
+
+     You're on task 4: "Implement OAuth flow"
+
+     Let me trace what's involved...
+
+     [draws diagram, explores options, suggests paths]
+
+     Want to update the design to reflect this?
+     Or add a spike task to investigate?
+```
+
+**User wants to compare options:**
+```
+User: Should we use Postgres or SQLite?
+
+You: Generic answer is boring. What's the context?
+
+User: A CLI tool that tracks local dev environments
+
+You: That changes everything.
+
+     ┌─────────────────────────────────────────────────┐
+     │          CLI TOOL DATA STORAGE                  │
+     └─────────────────────────────────────────────────┘
+
+     Key constraints:
+     • No daemon running
+     • Must work offline
+     • Single user
+
+                  SQLite          Postgres
+     Deployment   embedded ✓      needs server ✗
+     Offline      yes ✓           no ✗
+     Single file  yes ✓           no ✗
+
+     SQLite. Not even close.
+
+     Unless... is there a sync component?
+```
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When it feels like things are crystallizing, you might summarize:
+
+```
+## What We Figured Out
+
+**The problem**: [crystallized understanding]
+
+**The approach**: [if one emerged]
+
+**Open questions**: [if any remain]
+
+**Next steps** (if ready):
+- Create a change proposal
+- Keep exploring: just keep talking
+```
+
+But this summary is optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own

.opencode/skills/openspec-propose/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: openspec-propose
+description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Propose a new change - create the change and generate all artifacts in one step.
+
+I'll create a change with artifacts:
+- proposal.md (what & why)
+- design.md (how)
+- tasks.md (implementation steps)
+
+When ready to implement, run /opsx-apply
+
+---
+
+**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
+
+**Steps**
+
+1. **If no clear input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx-apply` or ask me to implement to start working on the tasks."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, ask if user wants to continue it or create a new one
+- Verify each artifact file exists after writing before proceeding to next

.playwright-mcp/page-2026-05-16T05-37-34-857Z.yml

@@ -0,0 +1,5 @@
+- generic [ref=e1]:
+  - generic "Toggle devtools panel" [ref=e2] [cursor=pointer]:
+    - img [ref=e3]
+  - generic "Toggle Component Inspector" [ref=e8] [cursor=pointer]:
+    - img [ref=e9]

.playwright-mcp/page-2026-05-16T05-37-57-758Z.yml

@@ -0,0 +1,119 @@
+- generic [active] [ref=e13]:
+  - generic [ref=e64]:
+    - complementary [ref=e65]:
+      - generic [ref=e67]:
+        - generic [ref=e68] [cursor=pointer]:
+          - img "中科兴皖" [ref=e70]
+          - paragraph [ref=e71]: 中科兴皖
+        - menubar [ref=e75]:
+          - menuitem "工作台" [ref=e76] [cursor=pointer]:
+            - generic [ref=e78]: 工作台
+          - menuitem "运营支撑" [expanded] [ref=e79]:
+            - generic [ref=e80] [cursor=pointer]:
+              - img [ref=e83]
+              - generic [ref=e85]: 运营支撑
+              - img [ref=e87]
+            - menu [ref=e89]:
+              - menuitem "洁净室管理" [ref=e90] [cursor=pointer]:
+                - generic [ref=e91]: 洁净室管理
+              - menuitem "库位管理" [ref=e92] [cursor=pointer]:
+                - generic [ref=e93]: 库位管理
+              - menuitem "展馆预约" [ref=e94] [cursor=pointer]:
+                - generic [ref=e95]: 展馆预约
+              - menuitem "demo" [ref=e96] [cursor=pointer]:
+                - generic [ref=e97]: demo
+          - menuitem "基础信息管理" [expanded] [ref=e98]:
+            - generic [ref=e99] [cursor=pointer]:
+              - img [ref=e102]
+              - generic [ref=e104]: 基础信息管理
+              - img [ref=e106]
+            - menu [ref=e108]:
+              - menuitem "客户管理" [ref=e109] [cursor=pointer]:
+                - generic [ref=e110]: 客户管理
+              - menuitem "细胞样本类型管理" [ref=e111] [cursor=pointer]:
+                - generic [ref=e112]: 细胞样本类型管理
+              - menuitem "采集地区及医院管理" [ref=e113] [cursor=pointer]:
+                - generic [ref=e114]: 采集地区及医院管理
+              - menuitem "采集协议号管理" [ref=e115] [cursor=pointer]:
+                - generic [ref=e116]: 采集协议号管理
+              - menuitem "样本编码管理" [ref=e117] [cursor=pointer]:
+                - generic [ref=e118]: 样本编码管理
+          - menuitem "细胞存储管理" [expanded] [ref=e119]:
+            - generic [ref=e120] [cursor=pointer]:
+              - img [ref=e123]
+              - generic [ref=e125]: 细胞存储管理
+              - img [ref=e127]
+            - menu [ref=e129]:
+              - menuitem "采集协议单" [ref=e130] [cursor=pointer]:
+                - generic [ref=e131]: 采集协议单
+              - menuitem "采集协议单审核" [ref=e132] [cursor=pointer]:
+                - generic [ref=e133]: 采集协议单审核
+              - menuitem "收款确认（财务）" [ref=e134] [cursor=pointer]:
+                - generic [ref=e135]: 收款确认（财务）
+              - menuitem "退费确认（财务）" [ref=e136] [cursor=pointer]:
+                - generic [ref=e137]: 退费确认（财务）
+              - menuitem "分期缴费预警" [ref=e138] [cursor=pointer]:
+                - generic [ref=e139]: 分期缴费预警
+          - menuitem "工作流管理" [expanded] [ref=e140]:
+            - generic [ref=e141] [cursor=pointer]:
+              - img [ref=e144]
+              - generic [ref=e147]: 工作流管理
+              - img [ref=e149]
+            - menu [ref=e151]:
+              - menuitem "流程配置" [ref=e152] [cursor=pointer]:
+                - generic [ref=e153]: 流程配置
+              - menuitem "待办中心" [ref=e154] [cursor=pointer]:
+                - generic [ref=e155]: 待办中心
+              - menuitem "已办中心" [ref=e156] [cursor=pointer]:
+                - generic [ref=e157]: 已办中心
+              - menuitem "我的申请" [ref=e158] [cursor=pointer]:
+                - generic [ref=e159]: 我的申请
+              - menuitem "请假申请" [ref=e160] [cursor=pointer]:
+                - generic [ref=e161]: 请假申请
+    - main [ref=e162]:
+      - generic [ref=e164]:
+        - generic [ref=e165]:
+          - generic [ref=e166]:
+            - img [ref=e169] [cursor=pointer]
+            - img [ref=e173] [cursor=pointer]
+            - navigation "breadcrumb" [ref=e175]:
+              - list [ref=e176]:
+                - listitem [ref=e177]:
+                  - generic [ref=e179]: 工作台
+          - generic [ref=e180]:
+            - img [ref=e183] [cursor=pointer]
+            - img [ref=e187] [cursor=pointer]
+        - generic [ref=e188]:
+          - list [ref=e190]:
+            - listitem [ref=e191] [cursor=pointer]: 工作台
+          - img [ref=e195] [cursor=pointer]
+      - generic [ref=e199]:
+        - generic [ref=e200]:
+          - heading "工作台" [level=1] [ref=e201]
+          - paragraph [ref=e202]: 以下为固定参考页，新增管理端界面请对照布局与类名；视觉以文档为准。
+        - generic [ref=e203]:
+          - heading "快速入口" [level=2] [ref=e205]: 快速入口
+          - generic [ref=e207]:
+            - paragraph [ref=e208]: "详见仓库根目录 `.cursorrules` 中「页面级 UI 模板（固定五页）」。"
+            - generic [ref=e209]:
+              - button "商品单位" [ref=e210] [cursor=pointer]:
+                - generic [ref=e211]: 商品单位
+              - button "用户管理" [ref=e212] [cursor=pointer]:
+                - generic [ref=e213]: 用户管理
+              - button "商品分类" [ref=e214] [cursor=pointer]:
+                - generic [ref=e215]: 商品分类
+              - button "租户管理" [ref=e216] [cursor=pointer]:
+                - generic [ref=e217]: 租户管理
+              - button "客户管理" [ref=e218] [cursor=pointer]:
+                - generic [ref=e219]: 客户管理
+  - generic [ref=e1]:
+    - generic "Toggle devtools panel" [ref=e2] [cursor=pointer]:
+      - img [ref=e3]
+    - generic "Toggle Component Inspector" [ref=e8] [cursor=pointer]:
+      - img [ref=e9]
+  - alert [ref=e220]:
+    - img [ref=e222]
+    - generic [ref=e224]:
+      - heading "登录成功" [level=2] [ref=e225]
+      - paragraph [ref=e227]: 欢迎回来，系统管理员！
+      - img [ref=e229] [cursor=pointer]

.playwright-mcp/page-2026-05-16T05-40-18-880Z.yml

@@ -0,0 +1,29 @@
+- generic [active] [ref=e13]:
+  - generic [ref=e231]:
+    - generic [ref=e233]:
+      - img "中科兴皖" [ref=e235]
+      - heading "一体化管理门户" [level=1] [ref=e236]
+      - paragraph [ref=e237]: 安全 · 高效 · 可扩展
+      - generic [ref=e238]:
+        - generic [ref=e240]: 系统管理
+        - generic [ref=e242]: 权限配置
+        - generic [ref=e244]: 数据统计
+    - generic [ref=e246]:
+      - generic [ref=e247]:
+        - heading "欢迎登录" [level=2] [ref=e248]
+        - paragraph [ref=e249]: 请输入您的账号信息
+      - generic [ref=e250]:
+        - generic [ref=e254]:
+          - img [ref=e257]
+          - textbox "请输入用户名" [ref=e259]
+        - generic [ref=e263]:
+          - img [ref=e266]
+          - textbox "请输入密码" [ref=e269]
+        - button "登 录" [ref=e272] [cursor=pointer]:
+          - generic [ref=e273]: 登 录
+      - generic [ref=e274]: 中科兴皖 © 2026
+  - generic [ref=e1]:
+    - generic "Toggle devtools panel" [ref=e2] [cursor=pointer]:
+      - img [ref=e3]
+    - generic "Toggle Component Inspector" [ref=e8] [cursor=pointer]:
+      - img [ref=e9]