Release v4.4.0: UI Design Workflow V3 - Layout/Style Separation Architecture

## Breaking Changes

- **Command Renamed**: `extract` → `style-extract`
- **New Required Phase**: `layout-extract` now mandatory before `generate`
- **Workflow Changed**: Old flow (extract → consolidate → generate)
  → New flow (style-extract → consolidate → layout-extract → generate)

## Added

**New Command: layout-extract**
- Extract structural layout separate from visual style
- Agent-powered with ui-design-agent
- Dual-mode: imitate (high-fidelity) / explore (multiple variants)
- Device-aware: desktop, mobile, tablet, responsive
- MCP-integrated layout pattern research (explore mode)
- Output: layout-templates.json with DOM structure + CSS layout rules

**Enhanced Architecture**
- Layout/Style Separation: Clear responsibility boundaries
- Pure Assembler: generate command combines pre-extracted components
- Device-Aware Layouts: Optimized structures for different devices
- Token-Based CSS: var() placeholders for spacing/breakpoints

## Changed

**style-extract (Renamed from extract)**
- File renamed: extract.md → style-extract.md
- Scope clarified: Visual style only (colors, typography, spacing)
- No functionality change, all features preserved

**generate (Refactored to Pure Assembler)**
- Before: Agent designed layout + applied style
- After: Pure assembly - combines layout-templates.json + design-tokens.json
- No design logic: All decisions made in previous phases
- Simplified agent instructions: Focus on assembly only

**Workflow Commands Updated**
- imitate-auto: Added Phase 2.5 (layout extraction)
- explore-auto: Added Phase 2.5 (layout extraction)
- Both workflows now include layout-extract step

## Removed

- ❌ V2 Commands: generate-v2, explore-auto-v2 (merged into main commands)
- ❌ Old extract command (renamed to style-extract)
- ❌ ui-generate-preview-v2.sh (merged into ui-generate-preview.sh)

## Files Changed

- Renamed: extract.md → style-extract.md
- Added: layout-extract.md (370+ lines)
- Modified: generate.md, imitate-auto.md, explore-auto.md, consolidate.md
- Removed: 2 deprecated v2 command files
- Updated: CHANGELOG.md, README.md

## Benefits

- ✅ Single Responsibility: Each phase has one clear job
- ✅ Better Layout Variety: Explore mode generates structurally distinct layouts
- ✅ Reusability: Layout templates work with any style
- ✅ Clarity: All structural decisions visible in layout-templates.json
- ✅ Testability: Layout structure and visual style tested independently

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.claude/commands/workflow/ui-design/batch-generate.md

@@ -0,0 +1,469 @@
+---
+name: batch-generate
+description: Prompt-driven batch UI generation using target-style-centric parallel execution
+usage: /workflow:ui-design:batch-generate --prompt "<description>" [--targets "<list>"] [--target-type "page|component"] [--device-type "desktop|mobile|tablet|responsive"] [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
+examples:
+  - /workflow:ui-design:batch-generate --prompt "Dashboard with metrics cards" --style-variants 3
+  - /workflow:ui-design:batch-generate --prompt "Auth pages: login, signup" --session WFS-auth
+  - /workflow:ui-design:batch-generate --prompt "Navbar, hero, footer components" --target-type component
+  - /workflow:ui-design:batch-generate --prompt "Mobile e-commerce app" --device-type mobile
+allowed-tools: TodoWrite(*), Read(*), Write(*), Task(ui-design-agent), Bash(*), mcp__exa__web_search_exa(*)
+---
+
+# Batch Generate UI Prototypes (/workflow:ui-design:batch-generate)
+
+## Overview
+Prompt-driven UI generation with intelligent target extraction and **target-style-centric batch execution**. Each agent handles all layouts for one target × style combination.
+
+**Strategy**: Prompt → Targets → Batched Generation
+- **Prompt-driven**: Describe what to build, command extracts targets
+- **Agent scope**: Each of `T × S` agents generates `L` layouts
+- **Parallel batching**: Max 6 concurrent agents for optimal throughput
+- **Component isolation**: Complete task independence
+- **Style-aware**: HTML adapts to design_attributes
+- **Self-contained CSS**: Direct token values (no var() refs)
+
+**Supports**: Pages (full layouts) and components (isolated elements)
+
+## Phase 1: Setup & Validation
+
+### Step 1: Parse Prompt & Resolve Configuration
+```bash
+# Parse required parameters
+prompt_text = --prompt
+device_type = --device-type OR "responsive"
+
+# Extract targets from prompt
+IF --targets:
+    target_list = split_and_clean(--targets)
+ELSE:
+    target_list = extract_targets_from_prompt(prompt_text)  # See helpers
+    IF NOT target_list: target_list = ["home"]  # Fallback
+
+# Detect target type
+target_type = --target-type OR detect_target_type(target_list)
+
+# Resolve base path
+IF --base-path:
+    base_path = --base-path
+ELSE IF --session:
+    bash(find .workflow/WFS-{session} -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+ELSE:
+    bash(find .workflow -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+
+# Get variant counts
+style_variants = --style-variants OR bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+layout_variants = --layout-variants OR 3
+```
+
+**Output**: `base_path`, `target_list[]`, `target_type`, `device_type`, `style_variants`, `layout_variants`
+
+### Step 2: Detect Token Sources
+```bash
+# Check consolidated (priority 1) or proposed (priority 2)
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "consolidated")
+# OR
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "proposed")
+
+# If proposed: Create temp consolidation dirs + write tokens
+FOR style_id IN 1..style_variants:
+    bash(mkdir -p {base_path}/style-consolidation/style-{style_id})
+    Write({base_path}/style-consolidation/style-{style_id}/design-tokens.json, proposed_tokens)
+
+# Load design space analysis (optional)
+IF exists({base_path}/style-extraction/design-space-analysis.json):
+    design_space_analysis = Read({base_path}/style-extraction/design-space-analysis.json)
+```
+
+**Output**: `token_sources{}`, `consolidated_count`, `proposed_count`, `design_space_analysis`
+
+### Step 3: Gather Layout Inspiration
+```bash
+bash(mkdir -p {base_path}/prototypes/_inspirations)
+
+# For each target: Research via MCP
+FOR target IN target_list:
+    search_query = "{target} {target_type} layout patterns variations"
+    mcp__exa__web_search_exa(query=search_query, numResults=5)
+
+    # Extract context from prompt for this target
+    target_requirements = extract_relevant_context_from_prompt(prompt_text, target)
+
+    # Write simple inspiration file
+    Write({base_path}/prototypes/_inspirations/{target}-layout-ideas.txt, inspiration_content)
+```
+
+**Output**: `T` inspiration text files
+
+## Phase 2: Target-Style-Centric Batch Generation (Agent)
+
+**Executor**: `Task(ui-design-agent)` × `T × S` tasks in **batched parallel** (max 6 concurrent)
+
+### Step 1: Calculate Batch Execution Plan
+```bash
+bash(mkdir -p {base_path}/prototypes)
+
+# Build task list: T × S combinations
+MAX_PARALLEL = 6
+total_tasks = T × S
+total_batches = ceil(total_tasks / MAX_PARALLEL)
+
+# Initialize batch tracking
+TodoWrite({todos: [
+  {content: "Batch 1/{batches}: Generate 6 tasks", status: "in_progress"},
+  {content: "Batch 2/{batches}: Generate 6 tasks", status: "pending"},
+  ...
+]})
+```
+
+### Step 2: Launch Batched Agent Tasks
+For each batch (up to 6 parallel tasks):
+```javascript
+Task(ui-design-agent): `
+  [TARGET_STYLE_UI_GENERATION_FROM_PROMPT]
+  🎯 ONE component: {target} × Style-{style_id} ({philosophy_name})
+  Generate: {layout_variants} × 2 files (HTML + CSS per layout)
+
+  PROMPT CONTEXT: {target_requirements}  # Extracted from original prompt
+  TARGET: {target} | TYPE: {target_type} | STYLE: {style_id}/{style_variants}
+  BASE_PATH: {base_path}
+  DEVICE: {device_type}
+  ${design_attributes ? "DESIGN_ATTRIBUTES: " + JSON.stringify(design_attributes) : ""}
+
+  ## Reference
+  - Layout inspiration: Read("{base_path}/prototypes/_inspirations/{target}-layout-ideas.txt")
+  - Design tokens: Read("{base_path}/style-consolidation/style-{style_id}/design-tokens.json")
+    Parse ALL token values (colors, typography, spacing, borders, shadows, breakpoints)
+  ${design_attributes ? "- Adapt DOM to: density, visual_weight, formality, organic_vs_geometric" : ""}
+
+  ## Generation
+  For EACH layout (1 to {layout_variants}):
+
+  1. HTML: {base_path}/prototypes/{target}-style-{style_id}-layout-N.html
+     - Complete HTML5: <!DOCTYPE>, <head>, <body>
+     - CSS ref: <link href="{target}-style-{style_id}-layout-N.css">
+     - Semantic: <header>, <nav>, <main>, <footer>
+     - A11y: ARIA labels, landmarks, responsive meta
+     - Viewport: <meta name="viewport" content="width=device-width, initial-scale=1.0">
+     - Follow user requirements from prompt
+     ${design_attributes ? `
+     - DOM adaptation:
+       * density='spacious' → flatter hierarchy
+       * density='compact' → deeper nesting
+       * visual_weight='heavy' → extra wrappers
+       * visual_weight='minimal' → direct structure` : ""}
+     - Device-specific: Optimize for {device_type}
+
+  2. CSS: {base_path}/prototypes/{target}-style-{style_id}-layout-N.css
+     - Self-contained: Direct token VALUES (no var())
+     - Use tokens: colors, fonts, spacing, borders, shadows
+     - Device-optimized: {device_type} styles
+     ${device_type === 'responsive' ? '- Responsive: Mobile-first @media' : '- Fixed: ' + device_type}
+     ${design_attributes ? `
+     - Token selection: density → spacing, visual_weight → shadows` : ""}
+
+  ## Notes
+  - ✅ Token VALUES directly from design-tokens.json
+  - ✅ Follow prompt requirements for {target}
+  - ✅ Optimize for {device_type}
+  - ❌ NO var() refs, NO external deps
+  - Layouts structurally DISTINCT
+  - Write files IMMEDIATELY (per layout)
+  - CSS filename MUST match HTML <link href>
+`
+
+# After each batch completes
+TodoWrite: Mark batch completed, next batch in_progress
+```
+
+## Phase 3: Verify & Generate Previews
+
+### Step 1: Verify Generated Files
+```bash
+# Count expected vs found
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+# Expected: S × L × T × 2
+
+# Validate samples
+Read({base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html)
+# Check: <!DOCTYPE html>, correct CSS href, sufficient CSS length
+```
+
+**Output**: `S × L × T × 2` files verified
+
+### Step 2: Run Preview Generation Script
+```bash
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+**Script generates**:
+- `compare.html` (interactive matrix)
+- `index.html` (navigation)
+- `PREVIEW.md` (instructions)
+
+### Step 3: Verify Preview Files
+```bash
+bash(ls {base_path}/prototypes/compare.html {base_path}/prototypes/index.html {base_path}/prototypes/PREVIEW.md)
+```
+
+**Output**: 3 preview files
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and parse prompt", status: "completed", activeForm: "Parsing prompt"},
+  {content: "Detect token sources", status: "completed", activeForm: "Loading design systems"},
+  {content: "Gather layout inspiration", status: "completed", activeForm: "Researching layouts"},
+  {content: "Batch 1/{batches}: Generate 6 tasks", status: "completed", activeForm: "Generating batch 1"},
+  ... (all batches completed)
+  {content: "Verify files & generate previews", status: "completed", activeForm: "Creating previews"}
+]});
+```
+
+### Output Message
+```
+✅ Prompt-driven batch UI generation complete!
+
+Prompt: {prompt_text}
+
+Configuration:
+- Style Variants: {style_variants}
+- Layout Variants: {layout_variants}
+- Target Type: {target_type}
+- Device Type: {device_type}
+- Targets: {target_list} ({T} targets)
+- Total Prototypes: {S × L × T}
+
+Batch Execution:
+- Total tasks: {T × S} (targets × styles)
+- Batches: {batches} (max 6 parallel per batch)
+- Agent scope: {L} layouts per target×style
+- Component isolation: Complete task independence
+- Device-specific: All layouts optimized for {device_type}
+
+Quality:
+- Style-aware: {design_space_analysis ? 'HTML adapts to design_attributes' : 'Standard structure'}
+- CSS: Self-contained (direct token values, no var())
+- Device-optimized: {device_type} layouts
+- Tokens: {consolidated_count} consolidated, {proposed_count} proposed
+{IF proposed_count > 0: '  💡 For production: /workflow:ui-design:consolidate'}
+
+Generated Files:
+{base_path}/prototypes/
+├── _inspirations/ ({T} text files)
+├── {target}-style-{s}-layout-{l}.html ({S×L×T} prototypes)
+├── {target}-style-{s}-layout-{l}.css
+├── compare.html (interactive matrix)
+├── index.html (navigation)
+└── PREVIEW.md (instructions)
+
+Preview:
+1. Open compare.html (recommended)
+2. Open index.html
+3. Read PREVIEW.md
+
+Next: /workflow:ui-design:update
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+
+# Count style variants
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+
+# Check token sources
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "consolidated")
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "proposed")
+```
+
+### Validation Commands
+```bash
+# Count generated files
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+
+# Verify preview
+bash(test -f {base_path}/prototypes/compare.html && echo "exists")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/prototypes/_inspirations)
+
+# Run preview script
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+## Output Structure
+
+```
+{base_path}/
+├── prototypes/
+│   ├── _inspirations/
+│   │   └── {target}-layout-ideas.txt  # Layout inspiration
+│   ├── {target}-style-{s}-layout-{l}.html  # Final prototypes
+│   ├── {target}-style-{s}-layout-{l}.css
+│   ├── compare.html
+│   ├── index.html
+│   └── PREVIEW.md
+└── style-consolidation/
+    └── style-{s}/
+        ├── design-tokens.json
+        └── style-guide.md
+```
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No token sources found
+→ Run /workflow:ui-design:extract or /workflow:ui-design:consolidate
+
+ERROR: No targets extracted from prompt
+→ Use --targets explicitly or rephrase prompt
+
+ERROR: MCP search failed
+→ Check network, retry
+
+ERROR: Batch {N} agent tasks failed
+→ Check agent output, retry specific target×style combinations
+
+ERROR: Script permission denied
+→ chmod +x ~/.claude/scripts/ui-generate-preview.sh
+```
+
+### Recovery Strategies
+- **Partial success**: Keep successful target×style combinations
+- **Missing design_attributes**: Works without (less style-aware)
+- **Invalid tokens**: Validate design-tokens.json structure
+- **Failed batch**: Re-run command, only failed combinations will retry
+
+## Quality Checklist
+
+- [ ] Prompt clearly describes targets
+- [ ] CSS uses direct token values (no var())
+- [ ] HTML adapts to design_attributes (if available)
+- [ ] Semantic HTML5 structure
+- [ ] ARIA attributes present
+- [ ] Device-optimized layouts
+- [ ] Layouts structurally distinct
+- [ ] compare.html works
+
+## Key Features
+
+- **Prompt-Driven**: Describe what to build, command extracts targets
+- **Target-Style-Centric**: `T×S` agents, each handles `L` layouts
+- **Parallel Batching**: Max 6 concurrent agents with progress tracking
+- **Component Isolation**: Complete task independence
+- **Style-Aware**: HTML adapts to design_attributes
+- **Self-Contained CSS**: Direct token values (no var())
+- **Device-Specific**: Optimized for desktop/mobile/tablet/responsive
+- **Inspiration-Based**: MCP-powered layout research
+- **Production-Ready**: Semantic, accessible, responsive
+
+## Integration
+
+**Input**: Prompt, design-tokens.json, design-space-analysis.json (optional)
+**Output**: S×L×T prototypes for `/workflow:ui-design:update`
+**Compatible**: extract, consolidate, explore-auto, imitate-auto outputs
+
+## Usage Examples
+
+### Basic: Auto-detection
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Dashboard with metric cards and charts"
+
+# Auto: latest design run, extracts "dashboard" target
+# Output: S × L × 1 prototypes
+```
+
+### With Session
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Auth pages: login, signup, password reset" \
+  --session WFS-auth
+
+# Uses WFS-auth's design run
+# Extracts: ["login", "signup", "password-reset"]
+# Batches: 2 (if S=3: 9 tasks = 6+3)
+# Output: S × L × 3 prototypes
+```
+
+### Components with Device Type
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Mobile UI components: navbar, card, footer" \
+  --target-type component \
+  --device-type mobile
+
+# Mobile-optimized component generation
+# Output: S × L × 3 prototypes
+```
+
+### Large Scale (Multi-batch)
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "E-commerce site" \
+  --targets "home,shop,product,cart,checkout" \
+  --style-variants 4 \
+  --layout-variants 2
+
+# Tasks: 5 × 4 = 20 (4 batches: 6+6+6+2)
+# Output: 4 × 2 × 5 = 40 prototypes
+```
+
+## Helper Functions Reference
+
+### Target Extraction
+```python
+# extract_targets_from_prompt(prompt_text)
+# Patterns: "Create X and Y", "Generate X, Y, Z pages", "Build X"
+# Returns: ["x", "y", "z"] (normalized lowercase with hyphens)
+
+# detect_target_type(target_list)
+# Keywords: page (home, dashboard, login) vs component (navbar, card, button)
+# Returns: "page" or "component"
+
+# extract_relevant_context_from_prompt(prompt_text, target)
+# Extracts sentences mentioning specific target
+# Returns: Relevant context string
+```
+
+## Batch Execution Details
+
+### Parallel Control
+- **Max concurrent**: 6 agents per batch
+- **Task distribution**: T × S tasks = ceil(T×S/6) batches
+- **Progress tracking**: TodoWrite per-batch status
+- **Examples**:
+  - 3 tasks → 1 batch
+  - 9 tasks → 2 batches (6+3)
+  - 20 tasks → 4 batches (6+6+6+2)
+
+### Performance
+| Tasks | Batches | Est. Time | Efficiency |
+|-------|---------|-----------|------------|
+| 1-6   | 1       | 3-5 min   | 100%       |
+| 7-12  | 2       | 6-10 min  | ~85%       |
+| 13-18 | 3       | 9-15 min  | ~80%       |
+| 19-30 | 4-5     | 12-25 min | ~75%       |
+
+### Optimization Tips
+1. **Reduce tasks**: Fewer targets or styles
+2. **Adjust layouts**: L=2 instead of L=3 for faster iteration
+3. **Stage generation**: Core pages first, secondary pages later
+
+## Notes
+
+- **Prompt quality**: Clear descriptions improve target extraction
+- **Token sources**: Consolidated (production) or proposed (fast-track)
+- **Batch parallelism**: Max 6 concurrent for stability
+- **Scalability**: Tested up to 30+ tasks (5+ batches)
+- **Dependencies**: MCP web search, ui-generate-preview.sh script

.claude/commands/workflow/ui-design/capture.md

@@ -0,0 +1,366 @@
+---
+name: capture
+description: Batch screenshot capture for UI design workflows using MCP or local fallback
+usage: /workflow:ui-design:capture --url-map "<map>" [--base-path <path>] [--session <id>]
+argument-hint: --url-map "target:url,..." [--base-path path] [--session id]
+examples:
+  - /workflow:ui-design:capture --url-map "home:https://linear.app, pricing:https://linear.app/pricing"
+  - /workflow:ui-design:capture --session WFS-auth --url-map "dashboard:https://app.com/dash"
+  - /workflow:ui-design:capture --base-path ".workflow/.design/run-20250110" --url-map "hero:https://example.com#hero"
+allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*), ListMcpResourcesTool(*), mcp__chrome-devtools__*, mcp__playwright__*
+---
+
+# Batch Screenshot Capture (/workflow:ui-design:capture)
+
+## Overview
+Batch screenshot tool with MCP-first strategy and multi-tier fallback. Processes multiple URLs in parallel.
+
+**Strategy**: MCP → Playwright → Chrome → Manual
+**Output**: Flat structure `screenshots/{target}.png`
+
+## Phase 1: Initialize & Parse
+
+### Step 1: Determine Base Path
+```bash
+# Priority: --base-path > session > standalone
+bash(if [ -n "$BASE_PATH" ]; then
+  echo "$BASE_PATH"
+elif [ -n "$SESSION_ID" ]; then
+  find .workflow/WFS-$SESSION_ID/design-* -type d | head -1 || \
+  echo ".workflow/WFS-$SESSION_ID/design-run-$(date +%Y%m%d-%H%M%S)"
+else
+  echo ".workflow/.design/run-$(date +%Y%m%d-%H%M%S)"
+fi)
+
+bash(mkdir -p $BASE_PATH/screenshots)
+```
+
+### Step 2: Parse URL Map
+```javascript
+// Input: "home:https://linear.app, pricing:https://linear.app/pricing"
+url_entries = []
+
+FOR pair IN split(params["--url-map"], ","):
+  parts = pair.split(":", 1)
+
+  IF len(parts) != 2:
+    ERROR: "Invalid format: {pair}. Expected: 'target:url'"
+    EXIT 1
+
+  target = parts[0].strip().lower().replace(" ", "-")
+  url = parts[1].strip()
+
+  // Validate target name
+  IF NOT regex_match(target, r"^[a-z0-9][a-z0-9_-]*$"):
+    ERROR: "Invalid target: {target}"
+    EXIT 1
+
+  // Add https:// if missing
+  IF NOT url.startswith("http"):
+    url = f"https://{url}"
+
+  url_entries.append({target, url})
+```
+
+**Output**: `base_path`, `url_entries[]`
+
+### Step 3: Initialize Todos
+```javascript
+TodoWrite({todos: [
+  {content: "Parse url-map", status: "completed", activeForm: "Parsing"},
+  {content: "Detect MCP tools", status: "in_progress", activeForm: "Detecting"},
+  {content: "Capture screenshots", status: "pending", activeForm: "Capturing"},
+  {content: "Verify results", status: "pending", activeForm: "Verifying"}
+]})
+```
+
+## Phase 2: Detect Screenshot Tools
+
+### Step 1: Check MCP Availability
+```javascript
+// List available MCP servers
+all_resources = ListMcpResourcesTool()
+available_servers = unique([r.server for r in all_resources])
+
+// Check Chrome DevTools MCP
+chrome_devtools = "chrome-devtools" IN available_servers
+chrome_screenshot = check_tool_exists("mcp__chrome-devtools__take_screenshot")
+
+// Check Playwright MCP
+playwright_mcp = "playwright" IN available_servers
+playwright_screenshot = check_tool_exists("mcp__playwright__screenshot")
+
+// Determine primary tool
+IF chrome_devtools AND chrome_screenshot:
+  tool = "chrome-devtools"
+ELSE IF playwright_mcp AND playwright_screenshot:
+  tool = "playwright"
+ELSE:
+  tool = null
+```
+
+**Output**: `tool` (chrome-devtools | playwright | null)
+
+### Step 2: Check Local Fallback
+```bash
+# Only if MCP unavailable
+bash(which playwright 2>/dev/null || echo "")
+bash(which google-chrome || which chrome || which chromium 2>/dev/null || echo "")
+```
+
+**Output**: `local_tools[]`
+
+## Phase 3: Capture Screenshots
+
+### Screenshot Format Options
+
+**PNG Format** (default, lossless):
+- **Pros**: Lossless quality, best for detailed UI screenshots
+- **Cons**: Larger file sizes (typically 200-500 KB per screenshot)
+- **Parameters**: `format: "png"` (no quality parameter)
+- **Use case**: High-fidelity UI replication, design system extraction
+
+**WebP Format** (optional, lossy/lossless):
+- **Pros**: Smaller file sizes with good quality (50-70% smaller than PNG)
+- **Cons**: Requires quality parameter, slight quality loss at high compression
+- **Parameters**: `format: "webp", quality: 90` (80-100 recommended)
+- **Use case**: Batch captures, network-constrained environments
+
+**JPEG Format** (optional, lossy):
+- **Pros**: Smallest file sizes
+- **Cons**: Lossy compression, not recommended for UI screenshots
+- **Parameters**: `format: "jpeg", quality: 90`
+- **Use case**: Photo-heavy pages, not recommended for UI design
+
+### Step 1: MCP Capture (If Available)
+```javascript
+IF tool == "chrome-devtools":
+  // Get or create page
+  pages = mcp__chrome-devtools__list_pages()
+
+  IF pages.length == 0:
+    mcp__chrome-devtools__new_page({url: url_entries[0].url})
+    page_idx = 0
+  ELSE:
+    page_idx = 0
+
+  mcp__chrome-devtools__select_page({pageIdx: page_idx})
+
+  // Capture each URL
+  FOR entry IN url_entries:
+    mcp__chrome-devtools__navigate_page({url: entry.url, timeout: 30000})
+    bash(sleep 2)
+
+    // PNG format doesn't support quality parameter
+    // Use PNG for lossless quality (larger files)
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: true,
+      format: "png",
+      filePath: f"{base_path}/screenshots/{entry.target}.png"
+    })
+
+    // Alternative: Use WebP with quality for smaller files
+    // mcp__chrome-devtools__take_screenshot({
+    //   fullPage: true,
+    //   format: "webp",
+    //   quality: 90,
+    //   filePath: f"{base_path}/screenshots/{entry.target}.webp"
+    // })
+
+ELSE IF tool == "playwright":
+  FOR entry IN url_entries:
+    mcp__playwright__screenshot({
+      url: entry.url,
+      output_path: f"{base_path}/screenshots/{entry.target}.png",
+      full_page: true,
+      timeout: 30000
+    })
+```
+
+### Step 2: Local Fallback (If MCP Failed)
+```bash
+# Try Playwright CLI
+bash(playwright screenshot "$url" "$output_file" --full-page --timeout 30000)
+
+# Try Chrome headless
+bash($chrome --headless --screenshot="$output_file" --window-size=1920,1080 "$url")
+```
+
+### Step 3: Manual Mode (If All Failed)
+```
+⚠️ Manual Screenshot Required
+
+Failed URLs:
+  home: https://linear.app
+  Save to: .workflow/.design/run-20250110/screenshots/home.png
+
+Steps:
+  1. Visit URL in browser
+  2. Take full-page screenshot
+  3. Save to path above
+  4. Type 'ready' to continue
+
+Options: ready | skip | abort
+```
+
+## Phase 4: Verification
+
+### Step 1: Scan Captured Files
+```bash
+bash(ls -1 $base_path/screenshots/*.{png,jpg,jpeg,webp} 2>/dev/null)
+bash(du -h $base_path/screenshots/*.png 2>/dev/null)
+```
+
+### Step 2: Generate Metadata
+```javascript
+captured_files = Glob(f"{base_path}/screenshots/*.{{png,jpg,jpeg,webp}}")
+captured_targets = [basename_no_ext(f) for f in captured_files]
+
+metadata = {
+  "timestamp": current_timestamp(),
+  "total_requested": len(url_entries),
+  "total_captured": len(captured_targets),
+  "screenshots": []
+}
+
+FOR entry IN url_entries:
+  is_captured = entry.target IN captured_targets
+
+  metadata.screenshots.append({
+    "target": entry.target,
+    "url": entry.url,
+    "captured": is_captured,
+    "path": f"{base_path}/screenshots/{entry.target}.png" IF is_captured ELSE null,
+    "size_kb": file_size_kb IF is_captured ELSE null
+  })
+
+Write(f"{base_path}/screenshots/capture-metadata.json", JSON.stringify(metadata))
+```
+
+**Output**: `capture-metadata.json`
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Parse url-map", status: "completed", activeForm: "Parsing"},
+  {content: "Detect MCP tools", status: "completed", activeForm: "Detecting"},
+  {content: "Capture screenshots", status: "completed", activeForm: "Capturing"},
+  {content: "Verify results", status: "completed", activeForm: "Verifying"}
+]})
+```
+
+### Output Message
+```
+✅ Batch screenshot capture complete!
+
+Summary:
+- Requested: {total_requested}
+- Captured: {total_captured}
+- Success rate: {success_rate}%
+- Method: {tool || "Local fallback"}
+
+Output:
+{base_path}/screenshots/
+├── home.png (245.3 KB)
+├── pricing.png (198.7 KB)
+└── capture-metadata.json
+
+Next: /workflow:ui-design:extract --images "screenshots/*.png"
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Create screenshot directory
+bash(mkdir -p $BASE_PATH/screenshots)
+```
+
+### Tool Detection
+```bash
+# Check MCP
+all_resources = ListMcpResourcesTool()
+
+# Check local tools
+bash(which playwright 2>/dev/null)
+bash(which google-chrome 2>/dev/null)
+```
+
+### Verification
+```bash
+# List captures
+bash(ls -1 $base_path/screenshots/*.png 2>/dev/null)
+
+# File sizes
+bash(du -h $base_path/screenshots/*.png)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── screenshots/
+    ├── home.png
+    ├── pricing.png
+    ├── about.png
+    └── capture-metadata.json
+```
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: Invalid url-map format
+→ Use: "target:url, target2:url2"
+
+ERROR: png screenshots do not support 'quality'
+→ PNG format is lossless, no quality parameter needed
+→ Remove quality parameter OR switch to webp/jpeg format
+
+ERROR: MCP unavailable
+→ Using local fallback
+
+ERROR: All tools failed
+→ Manual mode activated
+```
+
+### Format-Specific Errors
+```
+❌ Wrong: format: "png", quality: 90
+✅ Right: format: "png"
+
+✅ Or use: format: "webp", quality: 90
+✅ Or use: format: "jpeg", quality: 90
+```
+
+### Recovery
+- **Partial success**: Keep successful captures
+- **Retry**: Re-run with failed targets only
+- **Manual**: Follow interactive guidance
+
+## Quality Checklist
+
+- [ ] All requested URLs processed
+- [ ] File sizes > 1KB (valid images)
+- [ ] Metadata JSON generated
+- [ ] No missing targets (or documented)
+
+## Key Features
+
+- **MCP-first**: Prioritize managed tools
+- **Multi-tier fallback**: 4 layers (MCP → Local → Manual)
+- **Batch processing**: Parallel capture
+- **Error tolerance**: Partial failures handled
+- **Structured output**: Flat, predictable
+
+## Integration
+
+**Input**: `--url-map` (multiple target:url pairs)
+**Output**: `screenshots/*.png` + `capture-metadata.json`
+**Called by**: `/workflow:ui-design:imitate-auto`, `/workflow:ui-design:explore-auto`
+**Next**: `/workflow:ui-design:extract` or `/workflow:ui-design:explore-layers`

.claude/commands/workflow/ui-design/consolidate.md

@@ -13,198 +13,215 @@ allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Task(*)
 # Design System Consolidation Command
 
 ## Overview
-Consolidate user-selected style variants into **independent production-ready design systems**. This command serves as the **Style Planning Phase**, focusing exclusively on design tokens and style guides for the subsequent generation phase.
+Consolidate style variants into independent production-ready design systems. Refines raw token proposals from `style-extract` into finalized design tokens and style guides.
 
-## Core Philosophy
-- **Style System Focus**: Exclusively handles design system consolidation
-- **Agent-Driven**: Uses ui-design-agent for multi-file generation efficiency
-- **Separate Design Systems**: Generates N independent design systems (one per variant)
-- **Token Refinement**: Refines `proposed_tokens` from each variant into complete systems
-- **Intelligent Synthesis**: Ensures completeness and consistency
-- **Production-Ready**: Complete design system(s) with documentation
-- **Matrix-Ready**: Provides style variants for style × layout matrix exploration in generate phase
+**Strategy**: Philosophy-Driven Refinement
+- **Agent-Driven**: Uses ui-design-agent for N variant generation
+- **Token Refinement**: Transforms proposed_tokens into complete systems
+- **Production-Ready**: design-tokens.json + style-guide.md per variant
+- **Matrix-Ready**: Provides style variants for generate phase
 
-## Execution Protocol
-
-### Phase 1: Path Resolution & Variant Loading
+## Phase 1: Setup & Validation
 
+### Step 1: Resolve Base Path & Load Style Cards
 ```bash
 # Determine base path
-IF --base-path: base_path = {provided_base_path}
-ELSE IF --session: base_path = find_latest_path_matching(".workflow/WFS-{session}/design-*")
-ELSE: base_path = find_latest_path_matching(".workflow/.design/*")
-
-# Verify extraction output exists
-style_cards_path = "{base_path}/style-extraction/style-cards.json"
-VERIFY: exists(style_cards_path)
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
 
 # Load style cards
-style_cards = Read(style_cards_path)
-total_variants = len(style_cards.style_cards)
+bash(cat {base_path}/style-extraction/style-cards.json)
 ```
 
-### Phase 2: Variant Selection
-
+### Step 2: Memory Check (Skip if Already Done)
 ```bash
-# Determine how many variants to consolidate
-IF --variants:
-    variants_count = {provided_count}
-    VALIDATE: 1 <= variants_count <= total_variants
-ELSE:
-    variants_count = total_variants
-
-# Select first N variants
-selected_variants = style_cards.style_cards[0:variants_count]
-VERIFY: selected_variants.length > 0
-
-REPORT: "📦 Generating {variants_count} independent design systems"
+# Check if already consolidated
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "exists")
 ```
 
-### Phase 3: Load Design Context (Optional)
+**If exists**: Skip to completion message
 
+### Step 3: Select Variants
 ```bash
-# Load brainstorming context if available
-design_context = ""
-IF exists({base_path}/.brainstorming/synthesis-specification.md):
-    design_context = Read(synthesis-specification.md)
-ELSE IF exists({base_path}/.brainstorming/ui-designer/analysis.md):
-    design_context = Read(ui-designer/analysis.md)
+# Determine variant count (default: all from style-cards.json)
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
 
-# Load design space analysis from extraction phase
-design_space_analysis = {}
-design_space_path = "{base_path}/style-extraction/design-space-analysis.json"
-IF exists(design_space_path):
-    design_space_analysis = Read(design_space_path)
-    REPORT: "📊 Loaded design space analysis with {len(design_space_analysis.divergent_directions)} variant directions"
-ELSE:
-    REPORT: "⚠️ No design space analysis found - will refine tokens from proposed_tokens only"
+# Validate variant count
+# Priority: --variants parameter → total_variants from style-cards.json
 ```
 
-### Phase 4: Design System Synthesis (Agent Execution)
+**Output**: `variants_count`, `selected_variants[]`
 
+### Step 4: Load Design Context (Optional)
 ```bash
-REPORT: "🤖 Using agent for separate design system generation..."
+# Load brainstorming context
+bash(test -f {base_path}/.brainstorming/synthesis-specification.md && cat it)
 
-# Create output directories
-Bash(mkdir -p "{base_path}/style-consolidation/style-{{1..{variants_count}}}")
+# Load design space analysis
+bash(test -f {base_path}/style-extraction/design-space-analysis.json && cat it)
+```
 
-# Prepare agent task prompt with clear task identifier
-agent_task_prompt = """
-[DESIGN_TOKEN_GENERATION_TASK]
+**Output**: `design_context`, `design_space_analysis`
 
-CRITICAL: You MUST use Write() tool to create files. DO NOT return file contents as text.
+## Phase 2: Design System Synthesis (Agent)
 
-## Task Summary
-Generate {variants_count} independent design systems using philosophy-driven refinement and WRITE files directly (NO MCP calls).
+**Executor**: `Task(ui-design-agent)` for all variants
 
-## Context
-SESSION: {session_id}
-MODE: Separate design system generation with philosophy-driven refinement (NO MCP)
-BASE_PATH: {base_path}
-VARIANTS TO PROCESS: {variants_count}
+### Step 1: Create Output Directories
+```bash
+bash(mkdir -p {base_path}/style-consolidation/style-{{1..{variants_count}}})
+```
 
-## Variant Data
+### Step 2: Launch Agent Task
+For all variants (1 to {variants_count}):
+```javascript
+Task(ui-design-agent): `
+  [DESIGN_TOKEN_GENERATION_TASK]
+  Generate {variants_count} independent design systems using philosophy-driven refinement
 
-CRITICAL PATH MAPPING:
-- Variant 1 (id: {variant.id}) → Output directory: style-1/
-- Variant 2 (id: {variant.id}) → Output directory: style-2/
-- Variant N (id: {variant.id}) → Output directory: style-N/
+  SESSION: {session_id} | MODE: Philosophy-driven refinement | BASE_PATH: {base_path}
 
-Use loop index (1-based) for directory names, NOT variant.id.
+  CRITICAL PATH: Use loop index (N) for directories: style-1/, style-2/, ..., style-N/
 
-{FOR each variant IN selected_variants with index N (1-based):
-  ---
-  VARIANT INDEX: {N} (use this for directory: style-{N}/)
-  Variant ID: {variant.id} (metadata only, DO NOT use in paths)
-  Name: {variant.name}
-  Description: {variant.description}
-  Design Philosophy: {variant.design_philosophy}
-  Proposed Tokens: {JSON.stringify(variant.proposed_tokens, null, 2)}
-  ---
-}
+  VARIANT DATA:
+  {FOR each variant with index N:
+    VARIANT INDEX: {N} | ID: {variant.id} | NAME: {variant.name}
+    Design Philosophy: {variant.design_philosophy}
+    Proposed Tokens: {variant.proposed_tokens}
+    {IF design_space_analysis: Design Attributes: {attributes}, Anti-keywords: {anti_keywords}}
+  }
 
-{IF design_context: DESIGN CONTEXT (from brainstorming): {design_context}}
+  ## 参考
+  - Style cards: Each variant's proposed_tokens and design_philosophy
+  - Design space analysis: design_attributes (saturation, weight, formality, organic/geometric, innovation, density)
+  - Anti-keywords: Explicit constraints to avoid
+  - WCAG AA: 4.5:1 text, 3:1 UI (use built-in AI knowledge)
 
-{IF design_space_analysis:
-## Design Space Analysis (for Philosophy-Driven Refinement)
-{JSON.stringify(design_space_analysis, null, 2)}
+  ## 生成
+  For EACH variant (use loop index N for paths):
+  1. {base_path}/style-consolidation/style-{N}/design-tokens.json
+     - Complete token structure: colors, typography, spacing, border_radius, shadows, breakpoints
+     - All colors in OKLCH format
+     - Apply design_attributes to token values (saturation→chroma, density→spacing, etc.)
 
-Note: Each variant has design_attributes and anti_keywords for token refinement.
-Use philosophy_name and design_attributes to guide token generation WITHOUT external research.
-}
+  2. {base_path}/style-consolidation/style-{N}/style-guide.md
+     - Expanded design philosophy
+     - Complete color system with accessibility notes
+     - Typography documentation
+     - Usage guidelines
 
-## Task
-For EACH variant (1 to {variants_count}):
-1. **Load variant's design philosophy and attributes** (from design_space_analysis)
-2. **Refine design tokens** using philosophy-driven strategy (NO external research)
-3. **Generate and WRITE 2 files** to the file system
+  ## 注意
+  - ✅ Use Write() tool immediately for each file
+  - ✅ Use loop index N for directory names: style-1/, style-2/, etc.
+  - ❌ DO NOT use variant.id in paths (metadata only)
+  - ❌ NO external research or MCP calls (pure AI refinement)
+  - Apply philosophy-driven refinement: design_attributes guide token values
+  - Maintain divergence: Use anti_keywords to prevent variant convergence
+  - Complete each variant's files before moving to next variant
+`
+```
 
-## Step 1: Load Design Philosophy (No MCP Calls)
+**Output**: Agent generates `variants_count × 2` files
 
-IF design_space_analysis is provided:
-  FOR EACH variant:
-    1. **Extract Design Direction**: Load philosophy_name, design_attributes, search_keywords, anti_keywords
-    2. **Use as Refinement Guide**: Apply philosophy and attributes to token generation
-    3. **Enforce Constraints**: Avoid characteristics listed in anti_keywords
-    4. **Maintain Divergence**: Ensure tokens differ from other variants based on attributes
+## Phase 3: Verify Output
 
-ELSE:
-  Refine tokens based solely on variant's proposed_tokens and design_philosophy from style-cards.json
+### Step 1: Check Files Created
+```bash
+# Verify all design systems created
+bash(ls {base_path}/style-consolidation/style-*/design-tokens.json | wc -l)
 
-## Philosophy-Driven Refinement Strategy
+# Validate structure
+bash(cat {base_path}/style-consolidation/style-1/design-tokens.json | grep -q "colors" && echo "valid")
+```
 
-**Core Principles**:
-- Use variant's design_attributes as primary guide (color saturation, visual weight, formality, organic/geometric, innovation, density)
-- Apply anti_keywords as explicit constraints during token selection
-- Ensure WCAG AA accessibility using built-in AI knowledge (4.5:1 text, 3:1 UI)
-- Preserve maximum contrast between variants from extraction phase
+### Step 2: Verify File Sizes
+```bash
+bash(ls -lh {base_path}/style-consolidation/style-1/)
+```
 
-**Refinement Process** (Apply to each variant):
-1. **Colors**: Generate palette based on saturation attribute
-   - "monochrome" → low chroma values (oklch L 0.00-0.02 H)
-   - "vibrant" → high chroma values (oklch L 0.20-0.30 H)
-2. **Typography**: Select font families matching formality level
-   - "playful" → rounded, friendly fonts
-   - "luxury" → serif, elegant fonts
-3. **Spacing**: Apply density attribute
-   - "spacious" → larger spacing scale (e.g., "4": "1.5rem")
-   - "compact" → smaller spacing scale (e.g., "4": "0.75rem")
-4. **Shadows**: Match visual weight
-   - "minimal" → subtle shadows with low opacity
-   - "bold" → strong shadows with higher spread
-5. **Border Radius**: Align with organic/geometric attribute
-   - "organic" → larger radius values (xl: "1.5rem")
-   - "brutalist" → minimal radius (xl: "0.125rem")
-6. **Innovation**: Influence overall token adventurousness
-   - "timeless" → conservative, proven values
-   - "experimental" → unconventional token combinations
+**Output**: `variants_count × 2` files verified
 
-## Step 2: Refinement Rules (apply to each variant)
-1. **Complete Token Coverage**: Ensure all categories present (colors, typography, spacing, etc.)
-2. **Fill Gaps**: Generate missing tokens based on variant's philosophy and design_attributes
-3. **Maintain Style Identity**: Preserve unique characteristics from proposed tokens
-4. **Semantic Naming**: Use clear names (e.g., "brand-primary" not "color-1")
-5. **Accessibility**: Validate WCAG AA contrast using built-in AI knowledge (4.5:1 text, 3:1 UI)
-6. **OKLCH Format**: All colors use oklch(L C H / A) format
-7. **Design Philosophy**: Expand variant's design philosophy based on its attributes
-8. **Divergence Preservation**: Apply anti_keywords to prevent convergence with other variants
+## Completion
 
-## Step 3: FILE WRITE OPERATIONS (CRITICAL)
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and load style cards", status: "completed", activeForm: "Loading style cards"},
+  {content: "Select variants and load context", status: "completed", activeForm: "Loading context"},
+  {content: "Generate design systems (agent)", status: "completed", activeForm: "Generating systems"},
+  {content: "Verify output files", status: "completed", activeForm: "Verifying files"}
+]});
+```
 
-**EXECUTION MODEL**: For EACH variant (1 to {variants_count}):
-1. Load design philosophy and attributes
-2. Refine tokens using philosophy-driven strategy
-3. **IMMEDIATELY Write() files - DO NOT accumulate, DO NOT return as text**
+### Output Message
+```
+✅ Design system consolidation complete!
 
-### Required Write Operations Per Variant
+Configuration:
+- Session: {session_id}
+- Variants: {variants_count}
+- Philosophy-driven refinement (zero MCP calls)
 
-For variant with loop index {N} (e.g., 1st variant = N=1, 2nd variant = N=2), execute these Write() operations:
+Generated Files:
+{base_path}/style-consolidation/
+├── style-1/ (design-tokens.json, style-guide.md)
+├── style-2/ (same structure)
+└── style-{variants_count}/ (same structure)
+
+Next: /workflow:ui-design:generate --session {session_id} --style-variants {variants_count} --targets "dashboard,auth"
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Load style cards
+bash(cat {base_path}/style-extraction/style-cards.json)
+
+# Count variants
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
+```
+
+### Validation Commands
+```bash
+# Check if already consolidated
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "exists")
+
+# Verify output
+bash(ls {base_path}/style-consolidation/style-*/design-tokens.json | wc -l)
+
+# Validate structure
+bash(cat design-tokens.json | grep -q "colors" && echo "valid")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/style-consolidation/style-{{1..3}})
+
+# Check file sizes
+bash(ls -lh {base_path}/style-consolidation/style-1/)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── style-consolidation/
+    ├── style-1/
+    │   ├── design-tokens.json
+    │   └── style-guide.md
+    ├── style-2/
+    │   ├── design-tokens.json
+    │   └── style-guide.md
+    └── style-N/ (same structure)
+```
+
+## design-tokens.json Format
 
-#### Write Operation 1: Design Tokens
-**Path**: `{base_path}/style-consolidation/style-{N}/design-tokens.json`
-**Method**: `Write(path, JSON.stringify(tokens, null, 2))`
-**Example**: For 1st variant → `{base_path}/style-consolidation/style-1/design-tokens.json`
-**Content Structure**:
 ```json
 {
   "colors": {
@@ -222,229 +239,34 @@ For variant with loop index {N} (e.g., 1st variant = N=1, 2nd variant = N=2), ex
 }
 ```
 
-#### Write Operation 2: Style Guide
-**Path**: `{base_path}/style-consolidation/style-{N}/style-guide.md`
-**Method**: `Write(path, guide_markdown_content)`
-**Example**: For 2nd variant → `{base_path}/style-consolidation/style-2/style-guide.md`
-**Content Structure**:
-```markdown
-# Design System Style Guide - {variant.name}
-
-## Design Philosophy
-{Expanded variant philosophy}
-
-## Color System
-### Brand Colors, Surface Colors, Semantic Colors, Text Colors, Border Colors
-{List all with usage and accessibility notes}
-
-## Typography
-### Font Families, Type Scale, Usage Examples
-{Complete typography documentation}
-
-## Spacing System, Component Guidelines
-{Spacing patterns and component token examples}
-
-## Accessibility
-- All text meets WCAG AA (4.5:1 minimum)
-- UI components meet WCAG AA (3:1 minimum)
-- Focus indicators are clearly visible
-```
-
-### Execution Checklist (Per Variant)
-
-For each variant from 1 to {variants_count} (use loop index N):
-- [ ] Extract variant's philosophy, design_attributes, and anti_keywords
-- [ ] Apply philosophy-driven refinement strategy to proposed_tokens
-- [ ] Generate complete token set following refinement rules
-- [ ] **EXECUTE**: `Write("{base_path}/style-consolidation/style-{N}/design-tokens.json", tokens_json)`
-  - Example: 1st variant → `style-1/design-tokens.json`
-- [ ] **EXECUTE**: `Write("{base_path}/style-consolidation/style-{N}/style-guide.md", guide_content)`
-  - Example: 1st variant → `style-1/style-guide.md`
-- [ ] Verify both files written successfully
-
-### Verification After Each Write
-```javascript
-// Immediately after Write() for each file (use loop index N):
-Bash(`ls -lh "{base_path}/style-consolidation/style-{N}/"`)
-// Example: For 1st variant → ls -lh ".../style-1/"
-// Confirm file exists and has reasonable size (>1KB)
-
-## Expected Final Report
-
-After completing all {variants_count} variants, report:
-```
-✅ Variant 1 ({variant_name}):
-   - design-tokens.json: 12.5 KB | {token_count} tokens
-   - style-guide.md: 8.3 KB
-✅ Variant 2 ({variant_name}):
-   - design-tokens.json: 11.8 KB | {token_count} tokens
-   - style-guide.md: 7.9 KB
-... (for all variants)
-
-Summary: {variants_count} design systems generated with philosophy-driven refinement (zero MCP calls)
-```
-
-## KEY REMINDERS (CRITICAL)
-
-**ALWAYS:**
-- Use Write() tool for EVERY file - this is your PRIMARY responsibility
-- Write files immediately after generating content for each variant
-- Verify each Write() operation succeeds before proceeding
-- Use loop index (N) for directory names: `{base_path}/style-consolidation/style-{N}/...`
-  - 1st variant → `style-1/`, 2nd variant → `style-2/`, etc.
-  - DO NOT use variant.id in paths (metadata only)
-- Apply philosophy-driven refinement strategy for each variant
-- Maintain variant divergence using design_attributes and anti_keywords
-- Report completion with file paths and sizes
-
-**NEVER:**
-- Return file contents as text with labeled sections
-- Accumulate all content and try to output at once
-- Skip Write() operations and expect orchestrator to write files
-- Use relative paths or modify provided paths
-- Use external research or MCP calls (pure AI refinement only)
-- Generate variant N+1 before completing variant N writes
-"""
-
-# Dispatch to ui-design-agent with task prompt
-Task(subagent_type="ui-design-agent", description="Generate {variants_count} separate design systems", prompt=agent_task_prompt)
-
-REPORT: "✅ Agent task dispatched for {variants_count} design systems"
-```
-
-### Phase 5: Verify Agent File Creation
-```bash
-REPORT: "📝 Verifying agent file creation for {variants_count} design systems..."
-
-# Verify each variant's files were created by agent (use numeric index)
-FOR N IN range(1, variants_count + 1):
-    tokens_path = "{base_path}/style-consolidation/style-{N}/design-tokens.json"
-    guide_path = "{base_path}/style-consolidation/style-{N}/style-guide.md"
-
-    # Verify files exist
-    VERIFY: exists(tokens_path), "Design tokens not created by agent for style-{N}"
-    VERIFY: exists(guide_path), "Style guide not created by agent for style-{N}"
-
-    # Optional: Validate JSON structure
-    TRY:
-        tokens = Read(tokens_path)
-        tokens_json = parse_json(tokens)
-        VALIDATE: tokens_json.colors exists, "Missing colors in design-tokens.json"
-        VALIDATE: tokens_json.typography exists, "Missing typography in design-tokens.json"
-        VALIDATE: tokens_json.spacing exists, "Missing spacing in design-tokens.json"
-
-        tokens_size = get_file_size(tokens_path)
-        guide_size = get_file_size(guide_path)
-        REPORT: "  ✅ style-{N}/ verified ({tokens_size} KB tokens, {guide_size} KB guide)"
-    CATCH error:
-        ERROR: "Validation failed for style-{N}: {error}"
-        REPORT: "  ⚠️ Files exist but validation failed - review agent output"
-
-REPORT: "✅ All {variants_count} design systems verified"
-```
-
-**Output Structure**:
-```
-{base_path}/style-consolidation/
-├── style-1/ (design-tokens.json, style-guide.md)
-├── style-2/ (same structure)
-└── style-N/ (same structure)
-```
-
-### Phase 6: Completion & Reporting
-
-```javascript
-TodoWrite({todos: [
-  {content: "Load session and style cards", status: "completed", activeForm: "Loading style cards"},
-  {content: "Select variants for consolidation", status: "completed", activeForm: "Selecting variants"},
-  {content: "Load design context and space analysis", status: "completed", activeForm: "Loading context"},
-  {content: "Apply philosophy-driven refinement", status: "completed", activeForm: "Refining design tokens"},
-  {content: "Generate design systems via agent", status: "completed", activeForm: "Generating design systems"},
-  {content: "Process agent results and write files", status: "completed", activeForm: "Writing output files"}
-]});
-```
-
-**Completion Message**:
-```
-✅ Design system consolidation complete for session: {session_id}
-
-{IF design_space_analysis:
-🎨 Philosophy-Driven Refinement:
-- {variants_count} design systems generated from AI-analyzed philosophies
-- Zero MCP calls (pure AI token refinement)
-- Divergence preserved from extraction phase design_attributes
-- Each variant maintains unique style identity via anti_keywords
-}
-
-Generated {variants_count} independent design systems:
-{FOR each variant: - {variant.name} ({variant.id})}
-
-📂 Output: {base_path}/style-consolidation/
-├── style-1/ (design-tokens.json, style-guide.md)
-├── style-2/ (same structure)
-└── style-{variants_count}/ (same structure)
-
-Next: /workflow:ui-design:generate --session {session_id} --style-variants {variants_count} --targets "dashboard,auth" --layout-variants N
-
-Note: When called from /workflow:ui-design:explore-auto, UI generation is triggered automatically.
-Layout planning is now handled in the generate phase for each specific target.
-```
-
-## design-tokens.json Format
-
-**Token structure** (all variants follow identical structure with different values):
-
-```json
-{
-  "colors": {
-    "brand": {"primary": "oklch(...)", "secondary": "oklch(...)", "accent": "oklch(...)"},
-    "surface": {"background": "oklch(...)", "elevated": "oklch(...)", "overlay": "oklch(...)"},
-    "semantic": {"success": "oklch(...)", "warning": "oklch(...)", "error": "oklch(...)", "info": "oklch(...)"},
-    "text": {"primary": "oklch(...)", "secondary": "oklch(...)", "tertiary": "oklch(...)", "inverse": "oklch(...)"},
-    "border": {"default": "oklch(...)", "strong": "oklch(...)", "subtle": "oklch(...)"}
-  },
-  "typography": {
-    "font_family": {"heading": "...", "body": "...", "mono": "..."},
-    "font_size": {"xs": "...", "sm": "...", "base": "...", "lg": "...", "xl": "...", "2xl": "...", "3xl": "...", "4xl": "..."},
-    "font_weight": {"normal": "400", "medium": "500", "semibold": "600", "bold": "700"},
-    "line_height": {"tight": "1.25", "normal": "1.5", "relaxed": "1.75"},
-    "letter_spacing": {"tight": "-0.025em", "normal": "0", "wide": "0.025em"}
-  },
-  "spacing": {"0": "0", "1": "0.25rem", ..., "24": "6rem"},
-  "border_radius": {"none": "0", "sm": "0.25rem", ..., "full": "9999px"},
-  "shadows": {"sm": "...", "md": "...", "lg": "...", "xl": "..."},
-  "breakpoints": {"sm": "640px", "md": "768px", "lg": "1024px", "xl": "1280px", "2xl": "1536px"}
-}
-```
-
-**Requirements**: All colors in OKLCH format, complete token coverage, semantic naming
+**Requirements**: OKLCH colors, complete coverage, semantic naming
 
 ## Error Handling
 
-- **No style cards found**: Report error, suggest running `/workflow:ui-design:extract` first
-- **Invalid variant count**: List available count, auto-select all if called from auto workflow
-- **Parsing errors**: Retry with stricter format instructions
-- **Validation warnings**: Report but continue (non-blocking)
-- **Missing categories**: Claude will fill gaps based on design philosophy
+### Common Errors
+```
+ERROR: No style cards found
+→ Run /workflow:ui-design:style-extract first
+
+ERROR: Invalid variant count
+→ List available count, auto-select all
+
+ERROR: Agent file creation failed
+→ Check agent output, verify Write() operations
+```
 
 ## Key Features
 
-1. **Philosophy-Driven Refinement** - Pure AI token refinement based on design_space_analysis from extraction phase; Uses variant-specific philosophies and design_attributes as refinement rules; Preserves maximum contrast without external trend pollution; Zero MCP calls = faster execution + better divergence preservation
-2. **Agent-Driven Architecture** - Uses ui-design-agent for multi-file generation; Processes N variants with philosophy-guided synthesis; Structured output with deterministic token generation; Agent applies design attributes directly to token values
-3. **Separate Design Systems (Matrix-Ready)** - Generates N independent design systems (one per variant); Each variant maintains unique style identity from extraction phase; Provides style foundation for style × layout matrix exploration in generate phase
-4. **Token Refinement with AI Guidance** - Reads `proposed_tokens` from style cards; Loads design_space_analysis for philosophy and attributes; Applies attributes to token generation (saturation → chroma, density → spacing, etc.); Refines tokens while maintaining variant divergence through anti_keywords
-5. **Complete Design System Output** - design-tokens.json (CSS tokens per variant); style-guide.md (documentation per variant with philosophy explanation)
-6. **Production-Ready Quality** - WCAG AA accessibility validation using built-in AI knowledge (4.5:1 text, 3:1 UI); OKLCH color format for perceptual uniformity; Semantic token naming; Complete token coverage
-7. **Streamlined Workflow** - Sequential phases with clear responsibilities; Agent handles philosophy-driven token refinement and file generation; Reproducible with deterministic structure; Context-aware (integrates brainstorming and design space analysis); ~30-60s faster without MCP overhead
-8. **Divergence Preservation** - Strictly follows design_space_analysis constraints from extraction; Applies anti_keywords to prevent variant convergence; Maintains maximum variant contrast through attribute-driven generation; No external research = pure philosophical consistency
+- **Philosophy-Driven Refinement** - Pure AI token refinement using design_attributes
+- **Agent-Driven** - Uses ui-design-agent for multi-file generation
+- **Separate Design Systems** - N independent systems (one per variant)
+- **Production-Ready** - WCAG AA compliant, OKLCH colors, semantic naming
+- **Zero MCP Calls** - Faster execution, better divergence preservation
 
-## Integration Points
+## Integration
 
-- **Input**:
-  - `style-cards.json` from `/workflow:ui-design:extract` (with `proposed_tokens`)
-  - `design-space-analysis.json` from extraction phase (with philosophy and design_attributes)
-  - `--variants` parameter (default: all variants)
-- **Output**: Style Systems: `style-consolidation/style-{N}/design-tokens.json` and `style-guide.md` for each variant (refined with philosophy-driven approach), where N is the variant index (1, 2, 3...)
-- **Context**: Optional `synthesis-specification.md` or `ui-designer/analysis.md`
-- **Auto Integration**: Automatically triggered by `/workflow:ui-design:explore-auto` workflow
-- **Next Command**: `/workflow:ui-design:generate --style-variants N --targets "..." --layout-variants M` performs target-specific layout planning
+**Input**: `style-cards.json` from `/workflow:ui-design:style-extract`
+**Output**: `style-consolidation/style-{N}/` for each variant
+**Next**: `/workflow:ui-design:generate --style-variants N`
+
+**Note**: After consolidate, use `/workflow:ui-design:layout-extract` to generate layout templates before running generate.

.claude/commands/workflow/ui-design/explore-auto-v2.md

@@ -1,390 +0,0 @@
----
-name: explore-auto-v2
-description: Exploratory UI design workflow with style-centric batch generation
-usage: /workflow:ui-design:explore-auto-v2 [--prompt "<desc>"] [--images "<glob>"] [--targets "<list>"] [--target-type "page|component"] [--session <id>] [--style-variants <count>] [--layout-variants <count>] [--batch-plan]
-examples:
-  - /workflow:ui-design:explore-auto-v2 --prompt "Generate 3 style variants for modern blog: home, article, author"
-  - /workflow:ui-design:explore-auto-v2 --prompt "SaaS dashboard and settings with 2 layout options"
-  - /workflow:ui-design:explore-auto-v2 --images "refs/*.png" --prompt "E-commerce: home, product, cart" --style-variants 3 --layout-variants 3
-  - /workflow:ui-design:explore-auto-v2 --session WFS-auth --images "refs/*.png"
-  - /workflow:ui-design:explore-auto-v2 --targets "navbar,hero" --target-type "component" --style-variants 3 --layout-variants 2
-allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*), Task(conceptual-planning-agent)
----
-
-# UI Design Auto Workflow Command
-
-## Overview & Execution Model
-
-**Fully autonomous orchestrator**: Executes all design phases sequentially from style extraction to design integration, with optional batch planning.
-
-**Unified Target System**: Generates `style_variants × layout_variants × targets` prototypes, where targets can be:
-- **Pages** (full-page layouts): home, dashboard, settings, etc.
-- **Components** (isolated UI elements): navbar, card, hero, form, etc.
-- **Mixed**: Can combine both in a single workflow
-
-**Autonomous Flow** (⚠️ CONTINUOUS EXECUTION - DO NOT STOP):
-1. User triggers: `/workflow:ui-design:explore-auto-v2 [params]`
-2. Phase 0c: Target confirmation → User confirms → **IMMEDIATELY triggers Phase 1**
-3. Phase 1 (style-extract) → **WAIT for completion** → Auto-continues
-4. Phase 2 (style-consolidate) → **WAIT for completion** → Auto-continues
-5. **Phase 3 (ui-generate-v2)** → **WAIT for completion** → Auto-continues
-6. Phase 4 (design-update) → **WAIT for completion** → Auto-continues
-7. Phase 5 (batch-plan, optional) → Reports completion
-
-**Phase Transition Mechanism**:
-- **Phase 0c (User Interaction)**: User confirms targets → IMMEDIATELY triggers Phase 1
-- **Phase 1-5 (Autonomous)**: `SlashCommand` is BLOCKING - execution pauses until completion
-- Upon each phase completion: Automatically process output and execute next phase
-- No additional user interaction after Phase 0c confirmation
-
-**Auto-Continue Mechanism**: TodoWrite tracks phase status. Upon each phase completion, you MUST immediately construct and execute the next phase command. No user intervention required. The workflow is NOT complete until reaching Phase 4 (or Phase 5 if --batch-plan).
-
-**Target Type Detection**: Automatically inferred from prompt/targets, or explicitly set via `--target-type`.
-
-## Core Rules
-
-1. **Start Immediately**: TodoWrite initialization → Phase 1 execution
-2. **No Preliminary Validation**: Sub-commands handle their own validation
-3. **Parse & Pass**: Extract data from each output for next phase
-4. **Default to All**: When selecting variants/prototypes, use ALL generated items
-5. **Track Progress**: Update TodoWrite after each phase
-6. **⚠️ CRITICAL: DO NOT STOP** - This is a continuous multi-phase workflow. After each SlashCommand completes, you MUST wait for completion, then immediately execute the next phase. Workflow is NOT complete until Phase 4 (or Phase 5 if --batch-plan).
-
-## Parameter Requirements
-
-**Optional Parameters** (all have smart defaults):
-- `--targets "<list>"`: Comma-separated targets (pages/components) to generate (inferred from prompt/session if omitted)
-- `--target-type "page|component|auto"`: Explicitly set target type (default: `auto` - intelligent detection)
-- `--session <id>`: Workflow session ID (standalone mode if omitted)
-- `--images "<glob>"`: Reference image paths (default: `design-refs/*`)
-- `--prompt "<description>"`: Design style and target description
-- `--style-variants <count>`: Style variants (default: inferred from prompt or 3, range: 1-5)
-- `--layout-variants <count>`: Layout variants per style (default: inferred or 3, range: 1-5)
-- `--batch-plan`: Auto-generate implementation tasks after design-update
-
-**Legacy Parameters** (maintained for backward compatibility):
-- `--pages "<list>"`: Alias for `--targets` with `--target-type page`
-- `--components "<list>"`: Alias for `--targets` with `--target-type component`
-
-**Input Rules**:
-- Must provide at least one: `--images` or `--prompt` or `--targets`
-- Multiple parameters can be combined for guided analysis
-- If `--targets` not provided, intelligently inferred from prompt/session
-
-**Supported Target Types**:
-- **Pages** (full layouts): home, dashboard, settings, profile, login, etc.
-- **Components** (UI elements):
-  - Navigation: navbar, header, menu, breadcrumb, tabs, sidebar
-  - Content: hero, card, list, table, grid, timeline
-  - Input: form, search, filter, input-group
-  - Feedback: modal, alert, toast, badge, progress
-  - Media: gallery, carousel, video-player, image-card
-  - Other: footer, pagination, dropdown, tooltip, avatar
-
-**Intelligent Prompt Parsing**: Extracts variant counts from natural language:
-- "Generate **3 style variants**" → `--style-variants 3`
-- "**2 layout options**" → `--layout-variants 2`
-- "Create **4 styles** with **2 layouts each**" → `--style-variants 4 --layout-variants 2`
-- Explicit flags override prompt inference
-
-## Execution Modes
-
-**Matrix Mode** (style-centric):
-- Generates `style_variants × layout_variants × targets` prototypes
-- **Phase 1**: `style_variants` style options with design_attributes (extract)
-- **Phase 2**: `style_variants` independent design systems (consolidate)
-- **Phase 3**: Style-centric batch generation (generate-v2)
-  - Sub-phase 1: `targets × layout_variants` target-specific layout plans
-  - **Sub-phase 2**: `S` style-centric agents (each handles `L×T` combinations)
-  - Sub-phase 3: `style_variants × layout_variants × targets` final prototypes
-  - Performance: Efficient parallel execution with S agents
-  - Quality: HTML structure adapts to design_attributes
-  - Pages: Full-page layouts with complete structure
-  - Components: Isolated elements with minimal wrapper
-
-**Integrated vs. Standalone**:
-- `--session` flag determines session integration or standalone execution
-
-## 6-Phase Execution
-
-### Phase 0a: Intelligent Prompt Parsing
-```bash
-# Parse variant counts from prompt or use explicit/default values
-IF --prompt AND (NOT --style-variants OR NOT --layout-variants):
-    style_variants = regex_extract(prompt, r"(\d+)\s*style") OR --style-variants OR 3
-    layout_variants = regex_extract(prompt, r"(\d+)\s*layout") OR --layout-variants OR 3
-ELSE:
-    style_variants = --style-variants OR 3
-    layout_variants = --layout-variants OR 3
-
-VALIDATE: 1 <= style_variants <= 5, 1 <= layout_variants <= 5
-```
-
-### Phase 0b: Run Initialization & Directory Setup
-```bash
-run_id = "run-$(date +%Y%m%d-%H%M%S)"
-base_path = --session ? ".workflow/WFS-{session}/design-${run_id}" : ".workflow/.design/${run_id}"
-
-Bash(mkdir -p "${base_path}/{style-extraction,style-consolidation,prototypes}")
-
-Write({base_path}/.run-metadata.json): {
-  "run_id": "${run_id}", "session_id": "${session_id}", "timestamp": "...",
-  "workflow": "ui-design:auto-v2",
-  "version": "2.0",
-  "architecture": "style-centric-batch-generation",
-  "parameters": { "style_variants": ${style_variants}, "layout_variants": ${layout_variants},
-                  "targets": "${inferred_target_list}", "target_type": "${target_type}",
-                  "prompt": "${prompt_text}", "images": "${images_pattern}" },
-  "status": "in_progress",
-  "performance_mode": "optimized"
-}
-```
-
-### Phase 0c: Unified Target Inference with Intelligent Type Detection
-```bash
-# Priority: --pages/--components (legacy) → --targets → --prompt analysis → synthesis → default
-target_list = []; target_type = "auto"; target_source = "none"
-
-# Step 1-2: Explicit parameters (legacy or unified)
-IF --pages: target_list = split(--pages); target_type = "page"; target_source = "explicit_legacy"
-ELSE IF --components: target_list = split(--components); target_type = "component"; target_source = "explicit_legacy"
-ELSE IF --targets:
-    target_list = split(--targets); target_source = "explicit"
-    target_type = --target-type != "auto" ? --target-type : detect_target_type(target_list)
-
-# Step 3: Prompt analysis (Claude internal analysis)
-ELSE IF --prompt:
-    analysis_result = analyze_prompt("{prompt_text}")  # Extract targets, types, purpose
-    target_list = analysis_result.targets
-    target_type = analysis_result.primary_type OR detect_target_type(target_list)
-    target_source = "prompt_analysis"
-
-# Step 4: Session synthesis
-ELSE IF --session AND exists(synthesis-specification.md):
-    target_list = extract_targets_from_synthesis(); target_type = "page"; target_source = "synthesis"
-
-# Step 5: Fallback
-IF NOT target_list: target_list = ["home"]; target_type = "page"; target_source = "default"
-
-# Validate and clean
-validated_targets = [normalize(t) for t in target_list if is_valid(t)]
-IF NOT validated_targets: validated_targets = ["home"]; target_type = "page"
-IF --target-type != "auto": target_type = --target-type
-
-# Interactive confirmation
-DISPLAY_CONFIRMATION(target_type, target_source, validated_targets):
-  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-  "{emoji} {LABEL} CONFIRMATION (v2.0 Style-Centric)"
-  "Type: {target_type} | Source: {target_source}"
-  "Targets ({count}): {', '.join(validated_targets)}"
-  "Performance: {style_variants} agent calls (vs {layout_variants * len(validated_targets)} in v1.0)"
-  "Options: 'continue/yes' | 'targets: a,b' | 'skip: x' | 'add: y' | 'type: page|component'"
-  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-
-user_input = WAIT_FOR_USER_INPUT()
-
-# Process user modifications
-MATCH user_input:
-  "continue|yes|ok" → proceed
-  "targets: ..." → validated_targets = parse_new_list()
-  "skip: ..." → validated_targets = remove_items()
-  "add: ..." → validated_targets = add_items()
-  "type: ..." → target_type = extract_type()
-  default → proceed with current list
-
-STORE: inferred_target_list, target_type, target_inference_source
-
-# ⚠️ CRITICAL: User confirmation complete, IMMEDIATELY initialize TodoWrite and execute Phase 1
-# This is the only user interaction point in the workflow
-# After this point, all subsequent phases execute automatically without user intervention
-```
-
-**Helper Function: detect_target_type()**
-```bash
-detect_target_type(target_list):
-    page_keywords = ["home", "dashboard", "settings", "profile", "login", "signup", "auth", ...]
-    component_keywords = ["navbar", "header", "footer", "hero", "card", "button", "form", ...]
-
-    page_matches = count_matches(target_list, page_keywords + ["page", "screen", "view"])
-    component_matches = count_matches(target_list, component_keywords + ["component", "widget"])
-
-    RETURN "component" IF component_matches > page_matches ELSE "page"
-```
-
-### Phase 1: Style Extraction
-```bash
-command = "/workflow:ui-design:extract --base-path \"{base_path}\" " +
-          (--images ? "--images \"{images}\" " : "") +
-          (--prompt ? "--prompt \"{prompt}\" " : "") +
-          "--variants {style_variants} --mode explore"
-SlashCommand(command)
-
-# Output: {style_variants} style cards with design_attributes
-# SlashCommand blocks until phase complete
-# Upon completion, IMMEDIATELY execute Phase 2 (auto-continue)
-```
-
-### Phase 2: Style Consolidation
-```bash
-command = "/workflow:ui-design:consolidate --base-path \"{base_path}\" " +
-          "--variants {style_variants}"
-SlashCommand(command)
-
-# Output: {style_variants} independent design systems with tokens.css
-# SlashCommand blocks until phase complete
-# Upon completion, IMMEDIATELY execute Phase 3 (auto-continue)
-```
-
-### Phase 3: Style-Centric Matrix UI Generation
-```bash
-targets_string = ",".join(inferred_target_list)
-command = "/workflow:ui-design:generate-v2 --base-path \"{base_path}\" " +
-          "--targets \"{targets_string}\" --target-type \"{target_type}\" " +
-          "--style-variants {style_variants} --layout-variants {layout_variants}"
-
-total = style_variants × layout_variants × len(inferred_target_list)
-agent_calls = style_variants
-
-REPORT: "🚀 Phase 3: {type_icon} {targets_string} | Matrix: {s}×{l}×{n} = {total} prototypes"
-REPORT: "   → Agent calls: {agent_calls} style-centric agents"
-REPORT: "   → Layout planning: {len(inferred_target_list)}×{layout_variants} target-specific layouts"
-REPORT: "   → Style-centric generation: Each of {style_variants} agents handles {layout_variants}×{len(inferred_target_list)} combinations"
-
-SlashCommand(command)
-
-# SlashCommand blocks until phase complete
-# Upon completion, IMMEDIATELY execute Phase 4 (auto-continue)
-# Output:
-# - {target}-layout-{l}.json (target-specific layout plans)
-# - {target}-style-{s}-layout-{l}.html (final prototypes with style-aware structure)
-# - compare.html (interactive matrix view)
-# - PREVIEW.md (usage instructions)
-```
-
-### Phase 4: Design System Integration
-```bash
-command = "/workflow:ui-design:update" + (--session ? " --session {session_id}" : "")
-SlashCommand(command)
-
-# SlashCommand blocks until phase complete
-# Upon completion:
-#   - If --batch-plan flag present: IMMEDIATELY execute Phase 5 (auto-continue)
-#   - If no --batch-plan: Workflow complete, display final report
-```
-
-### Phase 5: Batch Task Generation (Optional)
-```bash
-IF --batch-plan:
-    FOR target IN inferred_target_list:
-        task_desc = "Implement {target} {target_type} based on design system"
-        SlashCommand("/workflow:plan --agent \"{task_desc}\"")
-```
-
-## TodoWrite Pattern
-```javascript
-// Initialize IMMEDIATELY after Phase 0c user confirmation to track multi-phase execution
-TodoWrite({todos: [
-  {"content": "Execute style extraction", "status": "in_progress", "activeForm": "Executing..."},
-  {"content": "Execute style consolidation", "status": "pending", "activeForm": "Executing..."},
-  {"content": "Execute style-centric UI generation", "status": "pending", "activeForm": "Executing..."},
-  {"content": "Execute design integration", "status": "pending", "activeForm": "Executing..."}
-]})
-
-// ⚠️ CRITICAL: After EACH SlashCommand completion (Phase 1-5), you MUST:
-// 1. SlashCommand blocks and returns when phase is complete
-// 2. Update current phase: status → "completed"
-// 3. Update next phase: status → "in_progress"
-// 4. IMMEDIATELY execute next phase SlashCommand (auto-continue)
-// This ensures continuous workflow tracking and prevents premature stopping
-```
-
-## Key Features
-
-- **🚀 Performance**: Style-centric batch generation with S agent calls
-- **🎨 Style-Aware**: HTML structure adapts to design_attributes
-- **✅ Perfect Consistency**: Each style by single agent
-- **📦 Autonomous**: No user intervention required between phases
-- **🧠 Intelligent**: Parses natural language, infers targets/types
-- **🔄 Reproducible**: Deterministic flow with isolated run directories
-- **🎯 Flexible**: Supports pages, components, or mixed targets
-
-## Examples
-
-### 1. Page Mode (Prompt Inference)
-```bash
-/workflow:ui-design:explore-auto-v2 --prompt "Modern blog: home, article, author"
-# Result: 27 prototypes (3×3×3)
-```
-
-### 2. Custom Matrix with Session
-```bash
-/workflow:ui-design:explore-auto-v2 --session WFS-ecommerce --images "refs/*.png" --style-variants 2 --layout-variants 2
-# Result: 2×2×N prototypes
-```
-
-### 3. Component Mode
-```bash
-/workflow:ui-design:explore-auto-v2 --targets "navbar,hero" --target-type "component" --style-variants 3 --layout-variants 2
-# Result: 12 prototypes (3×2×2) - components with minimal wrapper
-```
-
-### 4. Intelligent Parsing + Batch Planning
-```bash
-/workflow:ui-design:explore-auto-v2 --prompt "Create 4 styles with 2 layouts for dashboard and settings" --batch-plan
-# Result: 16 prototypes (4×2×2) + auto-generated tasks
-```
-
-### 5. Large Scale
-```bash
-/workflow:ui-design:explore-auto-v2 --targets "home,dashboard,settings,profile" --style-variants 3 --layout-variants 3
-# Result: 36 prototypes (3×3×4)
-```
-
-## Completion Output
-```
-✅ UI Design Explore-Auto Workflow Complete!
-
-Architecture: Style-Centric Batch Generation
-Run ID: {run_id} | Session: {session_id or "standalone"}
-Type: {icon} {target_type} | Matrix: {s}×{l}×{n} = {total} prototypes
-
-Phase 1: {s} style variants with design_attributes (extract)
-Phase 2: {s} design systems with tokens.css (consolidate)
-Phase 3: Style-centric batch generation (generate-v2)
-  - {n}×{l} target-specific layout plans
-  - {s} style-centric agents (each handled {l}×{n} combinations)
-  - {s}×{l}×{n} = {total} final prototypes with style-aware structure
-Phase 4: Brainstorming artifacts updated
-[Phase 5: {n} implementation tasks created]  # if --batch-plan
-
-Agent Execution:
-✅ Style-centric agents: {s} agents total
-✅ Each agent handles: {l}×{n} combinations
-
-Design Quality:
-✅ Style-Aware Structure: HTML adapts to design_attributes
-✅ Style Consistency: PERFECT (each style by single agent)
-✅ Token-Driven Styling: 100% var() usage
-
-📂 {base_path}/
-  ├── style-extraction/       ({s} style cards + design-space-analysis.json)
-  ├── style-consolidation/    ({s} design systems with tokens.css)
-  ├── prototypes/
-  │   ├── _templates/         ({n}×{l} layout JSON files)
-  │   └── ...                 ({total} final prototypes)
-  └── .run-metadata.json
-
-🌐 Preview: {base_path}/prototypes/compare.html
-  - Interactive {s}×{l} matrix view
-  - Side-by-side comparison
-  - Target-specific layouts with style-aware structure
-  - Toggle between {n} targets
-
-{icon} Targets: {', '.join(targets)} (type: {target_type})
-  - Each target has {l} custom-designed layouts
-  - Each style × target × layout has unique HTML structure (not just CSS!)
-  - Layout plans stored as structured JSON
-
-Next: [/workflow:execute] OR [Open compare.html → Select → /workflow:plan]
-```
-

.claude/commands/workflow/ui-design/explore-auto.md

@@ -1,15 +1,13 @@
 ---
 name: explore-auto
-description: Exploratory UI design workflow - Generate and compare multiple style × layout combinations (3×3 matrix exploration)
+description: Exploratory UI design workflow with style-centric batch generation
 usage: /workflow:ui-design:explore-auto [--prompt "<desc>"] [--images "<glob>"] [--targets "<list>"] [--target-type "page|component"] [--session <id>] [--style-variants <count>] [--layout-variants <count>] [--batch-plan]
 examples:
   - /workflow:ui-design:explore-auto --prompt "Generate 3 style variants for modern blog: home, article, author"
   - /workflow:ui-design:explore-auto --prompt "SaaS dashboard and settings with 2 layout options"
   - /workflow:ui-design:explore-auto --images "refs/*.png" --prompt "E-commerce: home, product, cart" --style-variants 3 --layout-variants 3
   - /workflow:ui-design:explore-auto --session WFS-auth --images "refs/*.png"
-  - /workflow:ui-design:explore-auto --targets "navbar,hero" --target-type "component" --prompt "Compare 3 navigation bar designs" --style-variants 3 --layout-variants 2
-  - /workflow:ui-design:explore-auto --targets "card,form,button" --images "refs/*.png" --style-variants 2 --layout-variants 3
-  - /workflow:ui-design:explore-auto --targets "home,dashboard" --target-type "page"
+  - /workflow:ui-design:explore-auto --targets "navbar,hero" --target-type "component" --style-variants 3 --layout-variants 2
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*), Task(conceptual-planning-agent)
 ---
 
@@ -26,11 +24,19 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*
 
 **Autonomous Flow** (⚠️ CONTINUOUS EXECUTION - DO NOT STOP):
 1. User triggers: `/workflow:ui-design:explore-auto [params]`
-2. Phase 1 (style-extract) → **WAIT for completion** → Auto-continues
-3. Phase 2 (style-consolidate) → **WAIT for completion** → Auto-continues
-4. Phase 3 (ui-generate) → **WAIT for completion** → Auto-continues with unified target list
-5. Phase 4 (design-update) → **WAIT for completion** → Auto-continues
-6. Phase 5 (batch-plan, optional) → Reports completion
+2. Phase 0c: Target confirmation → User confirms → **IMMEDIATELY triggers Phase 1**
+3. Phase 1 (style-extract) → **WAIT for completion** → Auto-continues
+4. Phase 2 (style-consolidate) → **WAIT for completion** → Auto-continues
+5. Phase 2.5 (layout-extract) → **WAIT for completion** → Auto-continues
+6. **Phase 3 (ui-assembly)** → **WAIT for completion** → Auto-continues
+7. Phase 4 (design-update) → **WAIT for completion** → Auto-continues
+8. Phase 5 (batch-plan, optional) → Reports completion
+
+**Phase Transition Mechanism**:
+- **Phase 0c (User Interaction)**: User confirms targets → IMMEDIATELY triggers Phase 1
+- **Phase 1-5 (Autonomous)**: `SlashCommand` is BLOCKING - execution pauses until completion
+- Upon each phase completion: Automatically process output and execute next phase
+- No additional user interaction after Phase 0c confirmation
 
 **Auto-Continue Mechanism**: TodoWrite tracks phase status. Upon each phase completion, you MUST immediately construct and execute the next phase command. No user intervention required. The workflow is NOT complete until reaching Phase 4 (or Phase 5 if --batch-plan).
 
@@ -50,6 +56,11 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*
 **Optional Parameters** (all have smart defaults):
 - `--targets "<list>"`: Comma-separated targets (pages/components) to generate (inferred from prompt/session if omitted)
 - `--target-type "page|component|auto"`: Explicitly set target type (default: `auto` - intelligent detection)
+- `--device-type "desktop|mobile|tablet|responsive|auto"`: Device type for layout optimization (default: `auto` - intelligent detection)
+  - **Desktop**: 1920×1080px - Mouse-driven, spacious layouts
+  - **Mobile**: 375×812px - Touch-friendly, compact layouts
+  - **Tablet**: 768×1024px - Hybrid touch/mouse layouts
+  - **Responsive**: 1920×1080px base with mobile-first breakpoints
 - `--session <id>`: Workflow session ID (standalone mode if omitted)
 - `--images "<glob>"`: Reference image paths (default: `design-refs/*`)
 - `--prompt "<description>"`: Design style and target description
@@ -84,17 +95,18 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*
 
 ## Execution Modes
 
-**Matrix Mode** (unified):
+**Matrix Mode** (style-centric):
 - Generates `style_variants × layout_variants × targets` prototypes
-- **Phase 1**: `style_variants` style options (extract)
+- **Phase 1**: `style_variants` style options with design_attributes (extract)
 - **Phase 2**: `style_variants` independent design systems (consolidate)
-- **Phase 3**: Layout planning + UI generation (generate)
+- **Phase 3**: Style-centric batch generation (generate)
   - Sub-phase 1: `targets × layout_variants` target-specific layout plans
-  - Sub-phase 2: `layout_variants × targets` HTML/CSS templates
+  - **Sub-phase 2**: `S` style-centric agents (each handles `L×T` combinations)
   - Sub-phase 3: `style_variants × layout_variants × targets` final prototypes
+  - Performance: Efficient parallel execution with S agents
+  - Quality: HTML structure adapts to design_attributes
   - Pages: Full-page layouts with complete structure
   - Components: Isolated elements with minimal wrapper
-  - Mixed: Combination based on intelligent detection
 
 **Integrated vs. Standalone**:
 - `--session` flag determines session integration or standalone execution
@@ -114,6 +126,51 @@ ELSE:
 VALIDATE: 1 <= style_variants <= 5, 1 <= layout_variants <= 5
 ```
 
+### Phase 0a-2: Device Type Inference
+```bash
+# Device type inference
+device_type = "auto"
+
+# Step 1: Explicit parameter (highest priority)
+IF --device-type AND --device-type != "auto":
+    device_type = --device-type
+    device_source = "explicit"
+ELSE:
+    # Step 2: Prompt analysis
+    IF --prompt:
+        device_keywords = {
+            "desktop": ["desktop", "web", "laptop", "widescreen", "large screen"],
+            "mobile": ["mobile", "phone", "smartphone", "ios", "android"],
+            "tablet": ["tablet", "ipad", "medium screen"],
+            "responsive": ["responsive", "adaptive", "multi-device", "cross-platform"]
+        }
+        detected_device = detect_device_from_prompt(--prompt, device_keywords)
+        IF detected_device:
+            device_type = detected_device
+            device_source = "prompt_inference"
+
+    # Step 3: Target type inference
+    IF device_type == "auto":
+        # Components are typically desktop-first, pages can vary
+        device_type = target_type == "component" ? "desktop" : "responsive"
+        device_source = "target_type_inference"
+
+STORE: device_type, device_source
+```
+
+**Device Type Presets**:
+- **Desktop**: 1920×1080px - Mouse-driven, spacious layouts
+- **Mobile**: 375×812px - Touch-friendly, compact layouts
+- **Tablet**: 768×1024px - Hybrid touch/mouse layouts
+- **Responsive**: 1920×1080px base with mobile-first breakpoints
+
+**Detection Keywords**:
+- Prompt contains "mobile", "phone", "smartphone" → mobile
+- Prompt contains "tablet", "ipad" → tablet
+- Prompt contains "desktop", "web", "laptop" → desktop
+- Prompt contains "responsive", "adaptive" → responsive
+- Otherwise: Inferred from target type (components→desktop, pages→responsive)
+
 ### Phase 0b: Run Initialization & Directory Setup
 ```bash
 run_id = "run-$(date +%Y%m%d-%H%M%S)"
@@ -124,10 +181,13 @@ Bash(mkdir -p "${base_path}/{style-extraction,style-consolidation,prototypes}")
 Write({base_path}/.run-metadata.json): {
   "run_id": "${run_id}", "session_id": "${session_id}", "timestamp": "...",
   "workflow": "ui-design:auto",
+  "architecture": "style-centric-batch-generation",
   "parameters": { "style_variants": ${style_variants}, "layout_variants": ${layout_variants},
                   "targets": "${inferred_target_list}", "target_type": "${target_type}",
-                  "prompt": "${prompt_text}", "images": "${images_pattern}" },
-  "status": "in_progress"
+                  "prompt": "${prompt_text}", "images": "${images_pattern}",
+                  "device_type": "${device_type}", "device_source": "${device_source}" },
+  "status": "in_progress",
+  "performance_mode": "optimized"
 }
 ```
 
@@ -163,13 +223,24 @@ IF NOT validated_targets: validated_targets = ["home"]; target_type = "page"
 IF --target-type != "auto": target_type = --target-type
 
 # Interactive confirmation
-DISPLAY_CONFIRMATION(target_type, target_source, validated_targets):
-  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-  "{emoji} {LABEL} CONFIRMATION"
+DISPLAY_CONFIRMATION(target_type, target_source, validated_targets, device_type, device_source):
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "{emoji} {LABEL} CONFIRMATION (Style-Centric)"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
   "Type: {target_type} | Source: {target_source}"
   "Targets ({count}): {', '.join(validated_targets)}"
-  "Options: 'continue/yes' | 'targets: a,b' | 'skip: x' | 'add: y' | 'type: page|component'"
-  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Device: {device_type} | Source: {device_source}"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Performance: {style_variants} agent calls"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Modification Options:"
+  "  • 'continue/yes/ok' - Proceed with current configuration"
+  "  • 'targets: a,b,c' - Replace target list"
+  "  • 'skip: x,y' - Remove specific targets"
+  "  • 'add: z' - Add new targets"
+  "  • 'type: page|component' - Change target type"
+  "  • 'device: desktop|mobile|tablet|responsive' - Change device type"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
 
 user_input = WAIT_FOR_USER_INPUT()
 
@@ -180,9 +251,14 @@ MATCH user_input:
   "skip: ..." → validated_targets = remove_items()
   "add: ..." → validated_targets = add_items()
   "type: ..." → target_type = extract_type()
+  "device: ..." → device_type = extract_device()
   default → proceed with current list
 
 STORE: inferred_target_list, target_type, target_inference_source
+
+# ⚠️ CRITICAL: User confirmation complete, IMMEDIATELY initialize TodoWrite and execute Phase 1
+# This is the only user interaction point in the workflow
+# After this point, all subsequent phases execute automatically without user intervention
 ```
 
 **Helper Function: detect_target_type()**
@@ -199,14 +275,15 @@ detect_target_type(target_list):
 
 ### Phase 1: Style Extraction
 ```bash
-command = "/workflow:ui-design:extract --base-path \"{base_path}\" " +
+command = "/workflow:ui-design:style-extract --base-path \"{base_path}\" " +
           (--images ? "--images \"{images}\" " : "") +
           (--prompt ? "--prompt \"{prompt}\" " : "") +
-          "--variants {style_variants} --mode explore"
+          "--mode explore --variants {style_variants}"
 SlashCommand(command)
 
-# WAIT for extract command to complete, then IMMEDIATELY continue to Phase 2
-# DO NOT STOP - Phase 2 must execute automatically
+# Output: {style_variants} style cards with design_attributes
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 2 (auto-continue)
 ```
 
 ### Phase 2: Style Consolidation
@@ -215,30 +292,54 @@ command = "/workflow:ui-design:consolidate --base-path \"{base_path}\" " +
           "--variants {style_variants}"
 SlashCommand(command)
 
-# WAIT for consolidate command to complete, then IMMEDIATELY continue to Phase 3
-# DO NOT STOP - Phase 3 must execute automatically
-# Output: style_variants independent design systems (design tokens and style guides)
+# Output: {style_variants} independent design systems with tokens.css
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 2.5 (auto-continue)
 ```
 
-### Phase 3: Matrix UI Generation (with Layout Planning)
+### Phase 2.5: Layout Extraction
 ```bash
 targets_string = ",".join(inferred_target_list)
-command = "/workflow:ui-design:generate --base-path \"{base_path}\" " +
-          "--targets \"{targets_string}\" --target-type \"{target_type}\" " +
-          "--style-variants {style_variants} --layout-variants {layout_variants}"
+command = "/workflow:ui-design:layout-extract --base-path \"{base_path}\" " +
+          (--images ? "--images \"{images}\" " : "") +
+          (--prompt ? "--prompt \"{prompt}\" " : "") +
+          "--targets \"{targets_string}\" " +
+          "--mode explore --variants {layout_variants} " +
+          "--device-type \"{device_type}\""
 
-total = style_variants × layout_variants × len(inferred_target_list)
-REPORT: "🚀 Phase 3: {type_icon} {targets_string} | Matrix: {s}×{l}×{n} = {total} prototypes"
-REPORT: "   → Layout planning: {len(inferred_target_list)}×{layout_variants} target-specific layouts"
+REPORT: "🚀 Phase 2.5: Layout Extraction (explore mode)"
+REPORT: "   → Targets: {targets_string}"
+REPORT: "   → Layout variants: {layout_variants}"
+REPORT: "   → Device: {device_type}"
 
 SlashCommand(command)
 
-# WAIT for generate command to complete, then IMMEDIATELY continue to Phase 4
-# DO NOT STOP - Phase 4 must execute automatically
+# Output: layout-templates.json with {targets × layout_variants} layout structures
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 3 (auto-continue)
+```
+
+### Phase 3: UI Assembly
+```bash
+command = "/workflow:ui-design:generate --base-path \"{base_path}\" " +
+          "--style-variants {style_variants} --layout-variants {layout_variants}"
+
+total = style_variants × layout_variants × len(inferred_target_list)
+
+REPORT: "🚀 Phase 3: UI Assembly | Matrix: {s}×{l}×{n} = {total} prototypes"
+REPORT: "   → Pure assembly: Combining layout templates + design tokens"
+REPORT: "   → Device: {device_type} (from layout templates)"
+REPORT: "   → Assembly tasks: {total} combinations"
+
+SlashCommand(command)
+
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 4 (auto-continue)
 # Output:
-# - {target}-layout-{l}.json (target-specific layout plans)
-# - {target}-style-{s}-layout-{l}.html (final prototypes)
-# - compare.html (matrix view)
+# - {target}-style-{s}-layout-{l}.html (assembled prototypes)
+# - {target}-style-{s}-layout-{l}.css
+# - compare.html (interactive matrix view)
+# - PREVIEW.md (usage instructions)
 ```
 
 ### Phase 4: Design System Integration
@@ -246,9 +347,10 @@ SlashCommand(command)
 command = "/workflow:ui-design:update" + (--session ? " --session {session_id}" : "")
 SlashCommand(command)
 
-# WAIT for update command to complete
-# If --batch-plan flag present: IMMEDIATELY continue to Phase 5
-# If no --batch-plan: Workflow complete, display final report
+# SlashCommand blocks until phase complete
+# Upon completion:
+#   - If --batch-plan flag present: IMMEDIATELY execute Phase 5 (auto-continue)
+#   - If no --batch-plan: Workflow complete, display final report
 ```
 
 ### Phase 5: Batch Task Generation (Optional)
@@ -261,90 +363,133 @@ IF --batch-plan:
 
 ## TodoWrite Pattern
 ```javascript
-// Initialize at workflow start to track multi-phase execution
+// Initialize IMMEDIATELY after Phase 0c user confirmation to track multi-phase execution
 TodoWrite({todos: [
   {"content": "Execute style extraction", "status": "in_progress", "activeForm": "Executing..."},
   {"content": "Execute style consolidation", "status": "pending", "activeForm": "Executing..."},
-  {"content": "Execute UI generation", "status": "pending", "activeForm": "Executing..."},
+  {"content": "Execute layout extraction", "status": "pending", "activeForm": "Executing..."},
+  {"content": "Execute UI assembly", "status": "pending", "activeForm": "Executing..."},
   {"content": "Execute design integration", "status": "pending", "activeForm": "Executing..."}
 ]})
 
-// ⚠️ CRITICAL: After EACH phase completion, you MUST:
-// 1. Update current phase: status → "completed"
-// 2. Update next phase: status → "in_progress"
-// 3. Continue to execute next phase immediately
+// ⚠️ CRITICAL: After EACH SlashCommand completion (Phase 1-5), you MUST:
+// 1. SlashCommand blocks and returns when phase is complete
+// 2. Update current phase: status → "completed"
+// 3. Update next phase: status → "in_progress"
+// 4. IMMEDIATELY execute next phase SlashCommand (auto-continue)
 // This ensures continuous workflow tracking and prevents premature stopping
 ```
 
 ## Key Features
-- **Autonomous**: No user intervention required between phases
-- **Intelligent**: Parses natural language, infers targets/types
-- **Reproducible**: Deterministic flow with isolated run directories
-- **Flexible**: Supports pages, components, or mixed targets
+
+- **🚀 Performance**: Style-centric batch generation with S agent calls
+- **🎨 Style-Aware**: HTML structure adapts to design_attributes
+- **✅ Perfect Consistency**: Each style by single agent
+- **📦 Autonomous**: No user intervention required between phases
+- **🧠 Intelligent**: Parses natural language, infers targets/types
+- **🔄 Reproducible**: Deterministic flow with isolated run directories
+- **🎯 Flexible**: Supports pages, components, or mixed targets
 
 ## Examples
 
 ### 1. Page Mode (Prompt Inference)
 ```bash
 /workflow:ui-design:explore-auto --prompt "Modern blog: home, article, author"
-# Result: 27 prototypes (3×3×3 - inferred defaults)
+# Result: 27 prototypes (3×3×3) - responsive layouts (default)
 ```
 
-### 2. Custom Matrix with Session
+### 2. Mobile-First Design
+```bash
+/workflow:ui-design:explore-auto --prompt "Mobile shopping app: home, product, cart" --device-type mobile
+# Result: 27 prototypes (3×3×3) - mobile layouts (375×812px)
+```
+
+### 3. Desktop Application
+```bash
+/workflow:ui-design:explore-auto --targets "dashboard,analytics,settings" --device-type desktop --style-variants 2 --layout-variants 2
+# Result: 12 prototypes (2×2×3) - desktop layouts (1920×1080px)
+```
+
+### 4. Tablet Interface
+```bash
+/workflow:ui-design:explore-auto --prompt "Educational app for tablets" --device-type tablet --targets "courses,lessons,profile"
+# Result: 27 prototypes (3×3×3) - tablet layouts (768×1024px)
+```
+
+### 5. Custom Matrix with Session
 ```bash
 /workflow:ui-design:explore-auto --session WFS-ecommerce --images "refs/*.png" --style-variants 2 --layout-variants 2
-# Result: 2×2×N prototypes (targets from synthesis)
+# Result: 2×2×N prototypes - device type inferred from session
 ```
 
-### 3. Component Mode
+### 6. Component Mode (Desktop)
 ```bash
-/workflow:ui-design:explore-auto --targets "navbar,hero" --target-type "component" --style-variants 3 --layout-variants 2
-# Result: 12 prototypes (3×2×2 components with minimal wrapper)
+/workflow:ui-design:explore-auto --targets "navbar,hero" --target-type "component" --device-type desktop --style-variants 3 --layout-variants 2
+# Result: 12 prototypes (3×2×2) - desktop components
 ```
 
-### 4. Intelligent Parsing + Batch Planning
+### 7. Intelligent Parsing + Batch Planning
 ```bash
-/workflow:ui-design:explore-auto --prompt "Create 4 styles with 2 layouts for dashboard and settings" --batch-plan
-# Result: 16 prototypes (4×2×2) + auto-generated implementation tasks
+/workflow:ui-design:explore-auto --prompt "Create 4 styles with 2 layouts for mobile dashboard and settings" --batch-plan
+# Result: 16 prototypes (4×2×2) + auto-generated tasks - mobile-optimized (inferred from prompt)
 ```
 
-### 5. Legacy Support
+### 8. Large Scale Responsive
 ```bash
-/workflow:ui-design:explore-auto --pages "home,dashboard,settings"
-# Equivalent to: --targets "home,dashboard,settings" --target-type "page"
+/workflow:ui-design:explore-auto --targets "home,dashboard,settings,profile" --device-type responsive --style-variants 3 --layout-variants 3
+# Result: 36 prototypes (3×3×4) - responsive layouts
 ```
 
 ## Completion Output
 ```
 ✅ UI Design Explore-Auto Workflow Complete!
 
+Architecture: Style-Centric Batch Generation
 Run ID: {run_id} | Session: {session_id or "standalone"}
-Type: {icon} {target_type} | Matrix: {s}×{l}×{n} = {total} prototypes
+Type: {icon} {target_type} | Device: {device_type} | Matrix: {s}×{l}×{n} = {total} prototypes
 
-Phase 1: {s} style variants (extract)
-Phase 2: {s} design systems (consolidate)
-Phase 3: Layout planning + generation (generate)
-  - {n}×{l} target-specific layout plans
-  - {l}×{n} HTML/CSS templates
+Phase 1: {s} style variants with design_attributes (style-extract)
+Phase 2: {s} design systems with tokens.css (consolidate)
+Phase 2.5: {n×l} layout templates (layout-extract explore mode)
+  - Device: {device_type} layouts
+  - {n} targets × {l} layout variants = {n×l} structural templates
+Phase 3: UI Assembly (generate)
+  - Pure assembly: layout templates + design tokens
   - {s}×{l}×{n} = {total} final prototypes
 Phase 4: Brainstorming artifacts updated
 [Phase 5: {n} implementation tasks created]  # if --batch-plan
 
+Assembly Process:
+✅ Separation of Concerns: Layout (structure) + Style (tokens) kept separate
+✅ Layout Extraction: {n×l} reusable structural templates
+✅ Pure Assembly: No design decisions in generate phase
+✅ Device-Optimized: Layouts designed for {device_type}
+
+Design Quality:
+✅ Token-Driven Styling: 100% var() usage
+✅ Structural Variety: {l} distinct layouts per target
+✅ Style Variety: {s} independent design systems
+✅ Device-Optimized: Layouts designed for {device_type}
+
 📂 {base_path}/
-  ├── style-consolidation/  ({s} design systems)
-  ├── prototypes/
-  │   ├── _templates/       ({n}×{l} layout JSON + {l}×{n} HTML/CSS)
-  │   └── ...               ({total} final prototypes)
-  └── .run-metadata.json
+  ├── style-extraction/       ({s} style cards + design-space-analysis.json)
+  ├── style-consolidation/    ({s} design systems with tokens.css)
+  ├── layout-extraction/      ({n×l} layout templates + layout-space-analysis.json)
+  ├── prototypes/             ({total} assembled prototypes)
+  └── .run-metadata.json      (includes device type)
 
 🌐 Preview: {base_path}/prototypes/compare.html
   - Interactive {s}×{l} matrix view
   - Side-by-side comparison
-  - Target-specific layouts per prototype
+  - Target-specific layouts with style-aware structure
+  - Toggle between {n} targets
 
 {icon} Targets: {', '.join(targets)} (type: {target_type})
   - Each target has {l} custom-designed layouts
+  - Each style × target × layout has unique HTML structure (not just CSS!)
   - Layout plans stored as structured JSON
+  - Optimized for {device_type} viewing
 
 Next: [/workflow:execute] OR [Open compare.html → Select → /workflow:plan]
 ```
+

.claude/commands/workflow/ui-design/explore-layers.md

@@ -0,0 +1,594 @@
+---
+name: explore-layers
+description: Interactive deep UI capture with depth-controlled layer exploration
+usage: /workflow:ui-design:explore-layers --url <url> --depth <1-5> [--session <id>] [--base-path <path>]
+argument-hint: --url <url> --depth <1-5> [--session id] [--base-path path]
+examples:
+  - /workflow:ui-design:explore-layers --url "https://app.linear.app" --depth 3
+  - /workflow:ui-design:explore-layers --url "https://notion.so" --depth 2 --session WFS-notion-ui
+  - /workflow:ui-design:explore-layers --url "https://app.com/dashboard" --depth 4
+allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*), mcp__chrome-devtools__*
+---
+
+# Interactive Layer Exploration (/workflow:ui-design:explore-layers)
+
+## Overview
+Single-URL depth-controlled interactive capture. Progressively explores UI layers from pages to Shadow DOM.
+
+**Depth Levels**:
+- `1` = Page (full-page screenshot)
+- `2` = Elements (key components)
+- `3` = Interactions (modals, dropdowns)
+- `4` = Embedded (iframes, widgets)
+- `5` = Shadow DOM (web components)
+
+**Requirements**: Chrome DevTools MCP
+
+## Phase 1: Setup & Validation
+
+### Step 1: Parse Parameters
+```javascript
+url = params["--url"]
+depth = int(params["--depth"])
+
+// Validate URL
+IF NOT url.startswith("http"):
+  url = f"https://{url}"
+
+// Validate depth
+IF depth NOT IN [1, 2, 3, 4, 5]:
+  ERROR: "Invalid depth: {depth}. Use 1-5"
+  EXIT 1
+```
+
+### Step 2: Determine Base Path
+```bash
+bash(if [ -n "$BASE_PATH" ]; then
+  echo "$BASE_PATH"
+elif [ -n "$SESSION_ID" ]; then
+  find .workflow/WFS-$SESSION_ID/design-* -type d | head -1 || \
+  echo ".workflow/WFS-$SESSION_ID/design-layers-$(date +%Y%m%d-%H%M%S)"
+else
+  echo ".workflow/.design/layers-$(date +%Y%m%d-%H%M%S)"
+fi)
+
+# Create depth directories
+bash(for i in $(seq 1 $depth); do mkdir -p $BASE_PATH/screenshots/depth-$i; done)
+```
+
+**Output**: `url`, `depth`, `base_path`
+
+### Step 3: Validate MCP Availability
+```javascript
+all_resources = ListMcpResourcesTool()
+chrome_devtools = "chrome-devtools" IN [r.server for r in all_resources]
+
+IF NOT chrome_devtools:
+  ERROR: "explore-layers requires Chrome DevTools MCP"
+  ERROR: "Install: npm i -g @modelcontextprotocol/server-chrome-devtools"
+  EXIT 1
+```
+
+### Step 4: Initialize Todos
+```javascript
+todos = [
+  {content: "Setup and validation", status: "completed", activeForm: "Setting up"}
+]
+
+FOR level IN range(1, depth + 1):
+  todos.append({
+    content: f"Depth {level}: {DEPTH_NAMES[level]}",
+    status: "pending",
+    activeForm: f"Capturing depth {level}"
+  })
+
+todos.append({content: "Generate layer map", status: "pending", activeForm: "Mapping"})
+
+TodoWrite({todos})
+```
+
+## Phase 2: Navigate & Load Page
+
+### Step 1: Get or Create Browser Page
+```javascript
+pages = mcp__chrome-devtools__list_pages()
+
+IF pages.length == 0:
+  mcp__chrome-devtools__new_page({url: url, timeout: 30000})
+  page_idx = 0
+ELSE:
+  page_idx = 0
+  mcp__chrome-devtools__select_page({pageIdx: page_idx})
+  mcp__chrome-devtools__navigate_page({url: url, timeout: 30000})
+
+bash(sleep 3)  // Wait for page load
+```
+
+**Output**: `page_idx`
+
+## Phase 3: Depth 1 - Page Level
+
+### Step 1: Capture Full Page
+```javascript
+TodoWrite(mark_in_progress: "Depth 1: Page")
+
+output_file = f"{base_path}/screenshots/depth-1/full-page.png"
+
+mcp__chrome-devtools__take_screenshot({
+  fullPage: true,
+  format: "png",
+  quality: 90,
+  filePath: output_file
+})
+
+layer_map = {
+  "url": url,
+  "depth": depth,
+  "layers": {
+    "depth-1": {
+      "type": "page",
+      "captures": [{
+        "name": "full-page",
+        "path": output_file,
+        "size_kb": file_size_kb(output_file)
+      }]
+    }
+  }
+}
+
+TodoWrite(mark_completed: "Depth 1: Page")
+```
+
+**Output**: `depth-1/full-page.png`
+
+## Phase 4: Depth 2 - Element Level (If depth >= 2)
+
+### Step 1: Analyze Page Structure
+```javascript
+IF depth < 2: SKIP
+
+TodoWrite(mark_in_progress: "Depth 2: Elements")
+
+snapshot = mcp__chrome-devtools__take_snapshot()
+
+// Filter key elements
+key_types = ["nav", "header", "footer", "aside", "button", "form", "article"]
+key_elements = [
+  el for el in snapshot.interactiveElements
+  if el.type IN key_types OR el.role IN ["navigation", "banner", "main"]
+][:10]  // Limit to top 10
+```
+
+### Step 2: Capture Element Screenshots
+```javascript
+depth_2_captures = []
+
+FOR idx, element IN enumerate(key_elements):
+  element_name = sanitize(element.text[:20] or element.type) or f"element-{idx}"
+  output_file = f"{base_path}/screenshots/depth-2/{element_name}.png"
+
+  TRY:
+    mcp__chrome-devtools__take_screenshot({
+      uid: element.uid,
+      format: "png",
+      quality: 85,
+      filePath: output_file
+    })
+
+    depth_2_captures.append({
+      "name": element_name,
+      "type": element.type,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+  CATCH error:
+    REPORT: f"Skip {element_name}: {error}"
+
+layer_map.layers["depth-2"] = {
+  "type": "elements",
+  "captures": depth_2_captures
+}
+
+TodoWrite(mark_completed: "Depth 2: Elements")
+```
+
+**Output**: `depth-2/{element}.png` × N
+
+## Phase 5: Depth 3 - Interaction Level (If depth >= 3)
+
+### Step 1: Analyze Interactive Triggers
+```javascript
+IF depth < 3: SKIP
+
+TodoWrite(mark_in_progress: "Depth 3: Interactions")
+
+// Detect structure
+structure = mcp__chrome-devtools__evaluate_script({
+  function: `() => ({
+    modals: document.querySelectorAll('[role="dialog"], .modal').length,
+    dropdowns: document.querySelectorAll('[role="menu"], .dropdown').length,
+    tooltips: document.querySelectorAll('[role="tooltip"], [title]').length
+  })`
+})
+
+// Identify triggers
+triggers = []
+FOR element IN snapshot.interactiveElements:
+  IF element.attributes CONTAINS ("data-toggle", "aria-haspopup"):
+    triggers.append({
+      uid: element.uid,
+      type: "modal" IF "modal" IN element.classes ELSE "dropdown",
+      trigger: "click",
+      text: element.text
+    })
+  ELSE IF element.attributes CONTAINS ("title", "data-tooltip"):
+    triggers.append({
+      uid: element.uid,
+      type: "tooltip",
+      trigger: "hover",
+      text: element.text
+    })
+
+triggers = triggers[:10]  // Limit
+```
+
+### Step 2: Trigger Interactions & Capture
+```javascript
+depth_3_captures = []
+
+FOR idx, trigger IN enumerate(triggers):
+  layer_name = f"{trigger.type}-{sanitize(trigger.text[:15]) or idx}"
+  output_file = f"{base_path}/screenshots/depth-3/{layer_name}.png"
+
+  TRY:
+    // Trigger interaction
+    IF trigger.trigger == "click":
+      mcp__chrome-devtools__click({uid: trigger.uid})
+    ELSE:
+      mcp__chrome-devtools__hover({uid: trigger.uid})
+
+    bash(sleep 1)
+
+    // Capture
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: false,  // Viewport only
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_3_captures.append({
+      "name": layer_name,
+      "type": trigger.type,
+      "trigger_method": trigger.trigger,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+    // Dismiss (ESC key)
+    mcp__chrome-devtools__evaluate_script({
+      function: `() => {
+        document.dispatchEvent(new KeyboardEvent('keydown', {key: 'Escape'}));
+      }`
+    })
+    bash(sleep 0.5)
+
+  CATCH error:
+    REPORT: f"Skip {layer_name}: {error}"
+
+layer_map.layers["depth-3"] = {
+  "type": "interactions",
+  "triggers": structure,
+  "captures": depth_3_captures
+}
+
+TodoWrite(mark_completed: "Depth 3: Interactions")
+```
+
+**Output**: `depth-3/{interaction}.png` × N
+
+## Phase 6: Depth 4 - Embedded Level (If depth >= 4)
+
+### Step 1: Detect Iframes
+```javascript
+IF depth < 4: SKIP
+
+TodoWrite(mark_in_progress: "Depth 4: Embedded")
+
+iframes = mcp__chrome-devtools__evaluate_script({
+  function: `() => {
+    return Array.from(document.querySelectorAll('iframe')).map(iframe => ({
+      src: iframe.src,
+      id: iframe.id || 'iframe',
+      title: iframe.title || 'untitled'
+    })).filter(i => i.src && i.src.startsWith('http'));
+  }`
+})
+```
+
+### Step 2: Capture Iframe Content
+```javascript
+depth_4_captures = []
+
+FOR idx, iframe IN enumerate(iframes):
+  iframe_name = f"iframe-{sanitize(iframe.title or iframe.id)}-{idx}"
+  output_file = f"{base_path}/screenshots/depth-4/{iframe_name}.png"
+
+  TRY:
+    // Navigate to iframe URL in new tab
+    mcp__chrome-devtools__new_page({url: iframe.src, timeout: 30000})
+    bash(sleep 2)
+
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: true,
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_4_captures.append({
+      "name": iframe_name,
+      "url": iframe.src,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+    // Close iframe tab
+    current_pages = mcp__chrome-devtools__list_pages()
+    mcp__chrome-devtools__close_page({pageIdx: current_pages.length - 1})
+
+  CATCH error:
+    REPORT: f"Skip {iframe_name}: {error}"
+
+layer_map.layers["depth-4"] = {
+  "type": "embedded",
+  "captures": depth_4_captures
+}
+
+TodoWrite(mark_completed: "Depth 4: Embedded")
+```
+
+**Output**: `depth-4/iframe-*.png` × N
+
+## Phase 7: Depth 5 - Shadow DOM (If depth = 5)
+
+### Step 1: Detect Shadow Roots
+```javascript
+IF depth < 5: SKIP
+
+TodoWrite(mark_in_progress: "Depth 5: Shadow DOM")
+
+shadow_elements = mcp__chrome-devtools__evaluate_script({
+  function: `() => {
+    const elements = Array.from(document.querySelectorAll('*'));
+    return elements
+      .filter(el => el.shadowRoot)
+      .map((el, idx) => ({
+        tag: el.tagName.toLowerCase(),
+        id: el.id || \`shadow-\${idx}\`,
+        innerHTML: el.shadowRoot.innerHTML.substring(0, 100)
+      }));
+  }`
+})
+```
+
+### Step 2: Capture Shadow DOM Components
+```javascript
+depth_5_captures = []
+
+FOR idx, shadow IN enumerate(shadow_elements):
+  shadow_name = f"shadow-{sanitize(shadow.id)}"
+  output_file = f"{base_path}/screenshots/depth-5/{shadow_name}.png"
+
+  TRY:
+    // Inject highlight script
+    mcp__chrome-devtools__evaluate_script({
+      function: `() => {
+        const el = document.querySelector('${shadow.tag}${shadow.id ? "#" + shadow.id : ""}');
+        if (el) {
+          el.scrollIntoView({behavior: 'smooth', block: 'center'});
+          el.style.outline = '3px solid red';
+        }
+      }`
+    })
+
+    bash(sleep 0.5)
+
+    // Full-page screenshot (component highlighted)
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: false,
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_5_captures.append({
+      "name": shadow_name,
+      "tag": shadow.tag,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+  CATCH error:
+    REPORT: f"Skip {shadow_name}: {error}"
+
+layer_map.layers["depth-5"] = {
+  "type": "shadow-dom",
+  "captures": depth_5_captures
+}
+
+TodoWrite(mark_completed: "Depth 5: Shadow DOM")
+```
+
+**Output**: `depth-5/shadow-*.png` × N
+
+## Phase 8: Generate Layer Map
+
+### Step 1: Compile Metadata
+```javascript
+TodoWrite(mark_in_progress: "Generate layer map")
+
+// Calculate totals
+total_captures = sum(len(layer.captures) for layer in layer_map.layers.values())
+total_size_kb = sum(
+  sum(c.size_kb for c in layer.captures)
+  for layer in layer_map.layers.values()
+)
+
+layer_map["summary"] = {
+  "timestamp": current_timestamp(),
+  "total_depth": depth,
+  "total_captures": total_captures,
+  "total_size_kb": total_size_kb
+}
+
+Write(f"{base_path}/screenshots/layer-map.json", JSON.stringify(layer_map, indent=2))
+
+TodoWrite(mark_completed: "Generate layer map")
+```
+
+**Output**: `layer-map.json`
+
+## Completion
+
+### Todo Update
+```javascript
+all_todos_completed = true
+TodoWrite({todos: all_completed_todos})
+```
+
+### Output Message
+```
+✅ Interactive layer exploration complete!
+
+Configuration:
+- URL: {url}
+- Max depth: {depth}
+- Layers explored: {len(layer_map.layers)}
+
+Capture Summary:
+  Depth 1 (Page):        {depth_1_count} screenshot(s)
+  Depth 2 (Elements):    {depth_2_count} screenshot(s)
+  Depth 3 (Interactions): {depth_3_count} screenshot(s)
+  Depth 4 (Embedded):    {depth_4_count} screenshot(s)
+  Depth 5 (Shadow DOM):  {depth_5_count} screenshot(s)
+
+Total: {total_captures} captures ({total_size_kb:.1f} KB)
+
+Output Structure:
+{base_path}/screenshots/
+├── depth-1/
+│   └── full-page.png
+├── depth-2/
+│   ├── navbar.png
+│   └── footer.png
+├── depth-3/
+│   ├── modal-login.png
+│   └── dropdown-menu.png
+├── depth-4/
+│   └── iframe-analytics.png
+├── depth-5/
+│   └── shadow-button.png
+└── layer-map.json
+
+Next: /workflow:ui-design:extract --images "screenshots/**/*.png"
+```
+
+## Simple Bash Commands
+
+### Directory Setup
+```bash
+# Create depth directories
+bash(for i in $(seq 1 $depth); do mkdir -p $BASE_PATH/screenshots/depth-$i; done)
+```
+
+### Validation
+```bash
+# Check MCP
+all_resources = ListMcpResourcesTool()
+
+# Count captures per depth
+bash(ls $base_path/screenshots/depth-{1..5}/*.png 2>/dev/null | wc -l)
+```
+
+### File Operations
+```bash
+# List all captures
+bash(find $base_path/screenshots -name "*.png" -type f)
+
+# Total size
+bash(du -sh $base_path/screenshots)
+```
+
+## Output Structure
+
+```
+{base_path}/screenshots/
+├── depth-1/
+│   └── full-page.png
+├── depth-2/
+│   ├── {element}.png
+│   └── ...
+├── depth-3/
+│   ├── {interaction}.png
+│   └── ...
+├── depth-4/
+│   ├── iframe-*.png
+│   └── ...
+├── depth-5/
+│   ├── shadow-*.png
+│   └── ...
+└── layer-map.json
+```
+
+## Depth Level Details
+
+| Depth | Name | Captures | Time | Use Case |
+|-------|------|----------|------|----------|
+| 1 | Page | Full page | 30s | Quick preview |
+| 2 | Elements | Key components | 1-2min | Component library |
+| 3 | Interactions | Modals, dropdowns | 2-4min | UI flows |
+| 4 | Embedded | Iframes | 3-6min | Complete context |
+| 5 | Shadow DOM | Web components | 4-8min | Full coverage |
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: Chrome DevTools MCP required
+→ Install: npm i -g @modelcontextprotocol/server-chrome-devtools
+
+ERROR: Invalid depth
+→ Use: 1-5
+
+ERROR: Interaction trigger failed
+→ Some modals may be skipped, check layer-map.json
+```
+
+### Recovery
+- **Partial success**: Lower depth captures preserved
+- **Trigger failures**: Interaction layer may be incomplete
+- **Iframe restrictions**: Cross-origin iframes skipped
+
+## Quality Checklist
+
+- [ ] All depths up to specified level captured
+- [ ] layer-map.json generated with metadata
+- [ ] File sizes valid (> 500 bytes)
+- [ ] Interaction triggers executed
+- [ ] Shadow DOM elements highlighted
+
+## Key Features
+
+- **Depth-controlled**: Progressive capture 1-5 levels
+- **Interactive triggers**: Click/hover for hidden layers
+- **Iframe support**: Embedded content captured
+- **Shadow DOM**: Web component internals
+- **Structured output**: Organized by depth
+
+## Integration
+
+**Input**: Single URL + depth level (1-5)
+**Output**: Hierarchical screenshots + layer-map.json
+**Complements**: `/workflow:ui-design:capture` (multi-URL batch)
+**Next**: `/workflow:ui-design:extract` for design analysis

.claude/commands/workflow/ui-design/extract.md

@@ -1,425 +0,0 @@
----
-name: extract
-description: Extract design style from reference images or text prompts using Claude's analysis
-usage: /workflow:ui-design:extract [--base-path <path>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--variants <count>]
-examples:
-  - /workflow:ui-design:extract --images "design-refs/*.png" --variants 3
-  - /workflow:ui-design:extract --prompt "Modern minimalist blog, dark theme" --variants 3
-  - /workflow:ui-design:extract --session WFS-auth --images "refs/*.png" --prompt "Linear.app style" --variants 2
-  - /workflow:ui-design:extract --base-path ".workflow/WFS-auth/design-run-20250109-143022" --images "refs/*.png" --variants 3
-  - /workflow:ui-design:extract --prompt "Bold vibrant" --variants 1  # Single variant (default)
-allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*)
----
-
-# Style Extraction Command
-
-## Overview
-Extract design style elements from reference images or text prompts using Claude's built-in analysis capabilities. Generates a single, comprehensive `style-cards.json` file containing multiple design variants with complete token proposals.
-
-## Core Philosophy
-- **Claude-Native**: 100% Claude-driven analysis, no external tools
-- **Single Output**: Only `style-cards.json` with embedded token proposals
-- **Sequential Execution**: Generate multiple style variants in one pass
-- **Flexible Input**: Images, text prompts, or both (hybrid mode)
-- **Reproducible**: Deterministic output structure
-
-## Execution Protocol
-
-### Phase 0: Parameter Detection & Validation
-
-```bash
-# Detect input source
-IF --images AND --prompt: input_mode = "hybrid"  # Text guides image analysis
-ELSE IF --images: input_mode = "image"
-ELSE IF --prompt: input_mode = "text"
-ELSE: ERROR: "Must provide --images or --prompt"
-
-# Determine base path (PRIORITY: --base-path > --session > standalone)
-IF --base-path:
-    base_path = {provided_base_path}; session_mode = "integrated"
-    session_id = base_path matches ".workflow/WFS-*/design-*" ? extract_session_id(base_path) : "standalone"
-ELSE:
-    run_id = "run-" + timestamp()
-    IF --session:
-        session_mode = "integrated"; session_id = {provided_session}
-        base_path = ".workflow/WFS-{session_id}/design-{run_id}/"
-    ELSE:
-        session_mode = "standalone"; base_path = ".workflow/.design/{run_id}/"
-
-# Set variant count
-variants_count = --variants OR 1; VALIDATE: 1 <= variants_count <= 5
-```
-
-### Phase 1: Input Loading & Validation
-
-```bash
-# Expand and validate inputs
-IF input_mode IN ["image", "hybrid"]:
-    expanded_images = Glob({--images pattern}); VERIFY: expanded_images.length > 0
-    FOR each image: image_data[i] = Read({image_path})
-
-IF input_mode IN ["text", "hybrid"]:
-    VALIDATE: --prompt is non-empty; prompt_guidance = {--prompt value}
-
-CREATE: {base_path}/style-extraction/
-```
-
-### Phase 0.5: AI-Driven Design Space Divergence
-
-```bash
-# Determine extraction mode
-extraction_mode = --mode OR "auto"
-IF extraction_mode == "auto":
-    extraction_mode = (variants_count == 1) ? "imitate" : "explore"
-    REPORT: "🔍 Auto-detected mode: {extraction_mode} (variants_count={variants_count})"
-
-# Branch: Skip or Execute divergence analysis
-IF extraction_mode == "imitate":
-    REPORT: "🎯 IMITATE MODE: High-fidelity single style extraction"
-    REPORT: "   → Skipping design space divergence analysis"
-    REPORT: "   → Proceeding to Phase 2 for direct style synthesis"
-    design_space_analysis = null
-    # Skip to Phase 2
-    GOTO Phase 2
-
-# ELSE: REQUIRED execution path for explore mode
-# ⚠️ CRITICAL: The following steps (Step 1-3) MUST be executed when extraction_mode == "explore"
-# Step 1: Load project context (explore mode only)
-project_context = ""
-IF exists({base_path}/.brainstorming/synthesis-specification.md):
-    project_context = Read(synthesis-specification.md)
-ELSE IF exists({base_path}/.brainstorming/ui-designer/analysis.md):
-    project_context = Read(ui-designer/analysis.md)
-
-REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-REPORT: "🎨 EXPLORE MODE: Analyzing design space (REQUIRED)"
-REPORT: "   → Generating {variants_count} maximally contrasting directions"
-REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
-
-# Step 2: AI-driven divergent direction generation (REQUIRED)
-divergence_prompt = """
-Analyze user requirements and generate {variants_count} MAXIMALLY CONTRASTING design directions.
-
-USER INPUT:
-{IF prompt_guidance: Prompt: "{prompt_guidance}"}
-{IF project_context: Project Context Summary: {extract_key_points(project_context, max_lines=10)}}
-{IF images: Reference Images: {image_count} images will be analyzed in next phase}
-
-DESIGN ATTRIBUTE SPACE (maximize contrast):
-- Color Saturation: [monochrome, muted, moderate, vibrant, hypersaturated]
-- Visual Weight: [minimal, light, balanced, bold, heavy]
-- Formality: [playful, casual, professional, formal, luxury]
-- Organic vs Geometric: [organic/fluid, soft, balanced, geometric, brutalist]
-- Innovation: [timeless, modern, contemporary, trendy, experimental]
-- Density: [spacious, airy, balanced, compact, dense]
-
-TASK:
-1. Identify design space center point from user requirements
-2. Generate {variants_count} directions that:
-   - Are MAXIMALLY DISTANT from each other in attribute space
-   - Each occupies a distinct region/quadrant of the design spectrum
-   - Together provide diverse aesthetic options
-   - Are contextually appropriate for project type
-   - Have clear, memorable philosophical differences
-3. For each direction, generate:
-   - Specific search keywords for MCP research (3-5 keywords)
-   - Anti-keywords to avoid (2-3 keywords)
-   - Clear rationale explaining contrast with other variants
-
-OUTPUT FORMAT: Valid JSON only, no markdown:
-{"design_space_center": {attributes}, "divergent_directions": [
-  {"id": "variant-1", "philosophy_name": "Brief name 2-3 words",
-   "design_attributes": {attribute_scores}, "search_keywords": [...],
-   "anti_keywords": [...], "rationale": "..."}
-], "contrast_verification": {"min_pairwise_distance": "0.75", "strategy": "..."}}
-
-RULES: Output ONLY valid JSON, maximize inter-variant distance, ensure each variant
-occupies distinct aesthetic region, avoid overlapping attributes
-"""
-
-# Execute AI analysis (REQUIRED in explore mode)
-divergent_directions = parse_json(Claude_Native_Analysis(divergence_prompt))
-
-REPORT: "✅ Generated {variants_count} contrasting design directions:"
-FOR direction IN divergent_directions.divergent_directions:
-    REPORT: "  - {direction.philosophy_name}: {direction.rationale}"
-
-design_space_analysis = divergent_directions
-
-# Step 3: Save design space analysis for consolidation phase (REQUIRED)
-# ⚠️ CRITICAL: This file MUST be generated in explore mode for downstream consolidation
-output_file_path = "{base_path}/style-extraction/design-space-analysis.json"
-Write({file_path: output_file_path,
-       content: JSON.stringify(design_space_analysis, null, 2)})
-
-REPORT: "💾 Saved design space analysis to design-space-analysis.json"
-
-# Verification step (REQUIRED)
-VERIFY: file_exists(output_file_path) == true
-REPORT: "✅ Verified: design-space-analysis.json exists ({file_size(output_file_path)} bytes)"
-```
-
-### Phase 2: Variant-Specific Style Synthesis & Direct File Write
-
-**Analysis Prompt Template**:
-```
-Generate {variants_count} design style proposals{IF extraction_mode == "explore": , each guided by its pre-analyzed design direction}.
-
-INPUT MODE: {input_mode}
-{IF input_mode IN ["image", "hybrid"]: VISUAL REFERENCES: {list of loaded images}}
-{IF input_mode IN ["text", "hybrid"]: TEXT GUIDANCE: "{prompt_guidance}"}
-
-{IF extraction_mode == "explore":
-DESIGN SPACE ANALYSIS: {design_space_analysis summary}
-
-VARIANT-SPECIFIC DESIGN DIRECTIONS:
-{FOR each direction IN design_space_analysis.divergent_directions:
----
-VARIANT: {direction.id} | PHILOSOPHY: {direction.philosophy_name}
-DESIGN ATTRIBUTES: {direction.design_attributes}
-SEARCH KEYWORDS: {direction.search_keywords}
-ANTI-PATTERNS (avoid): {direction.anti_keywords}
-RATIONALE: {direction.rationale}
----}
-}
-
-TASK: Generate {variants_count} design style variant{IF variants_count > 1: s} where {IF extraction_mode == "explore": EACH variant}:
-{IF extraction_mode == "explore":
-1. Strictly follows its pre-defined design philosophy and attributes
-2. Maintains maximum contrast with other variants' attributes
-3. Incorporates its design direction and avoids its anti-patterns
-}
-{IF extraction_mode == "imitate":
-1. Provides high-fidelity replication of reference design
-2. Focuses on accurate extraction of visual characteristics
-}
-4. Uses OKLCH color space for all color values
-5. Includes complete, production-ready design token proposals
-6. Applies WCAG AA accessibility guidelines (4.5:1 text, 3:1 UI)
-
-{IF extraction_mode == "explore":
-CRITICAL RULES FOR CONTRAST:
-- Variant-1 should feel completely different from Variant-2/3
-- Use each variant's specific attribute scores (e.g., "monochrome" vs "vibrant")
-- Each variant should embody its unique design direction
-- If Variant-1 is "minimal/geometric", Variant-2 must be "bold/organic" or similar contrast
-}
-
-OUTPUT FORMAT: JSON matching this structure:
-{"extraction_metadata": {"session_id": "...", "input_mode": "...", "timestamp": "...", "variants_count": N},
- "style_cards": [
-   {"id": "variant-1", "name": "Concise Style Name (2-3 words)", "description": "2-3 sentences",
-    "design_philosophy": "Core design principles",
-    "preview": {"primary": "oklch(...)", "background": "oklch(...)", "font_heading": "...", "border_radius": "..."},
-    "proposed_tokens": {
-      "colors": {"brand": {...}, "surface": {...}, "semantic": {...}, "text": {...}, "border": {...}},
-      "typography": {"font_family": {...}, "font_size": {...}, "font_weight": {...}, "line_height": {...}, "letter_spacing": {...}},
-      "spacing": {"0": "0", ..., "24": "6rem"},
-      "border_radius": {"none": "0", ..., "full": "9999px"},
-      "shadows": {"sm": "...", ..., "xl": "..."},
-      "breakpoints": {"sm": "640px", ..., "2xl": "1536px"}
-    }}
-   // Repeat for ALL {variants_count} variants
- ]}
-
-RULES: {IF extraction_mode == "explore": Each variant must strictly adhere to pre-defined attributes; maximize visual contrast;}
-{IF extraction_mode == "imitate": Focus on high-fidelity replication;}
-all colors in OKLCH format; complete token structures; semantic naming;
-WCAG AA accessibility (4.5:1 text, 3:1 UI)
-```
-
-**Execution & File Write**:
-```bash
-# Execute Claude Native Analysis (internal processing, no context output)
-style_cards_json = Claude_Native_Analysis(synthesis_prompt)
-
-# Write directly to file
-Write({file_path: "{base_path}/style-extraction/style-cards.json", content: style_cards_json})
-REPORT: "💾 Saved {variants_count} style variants to style-cards.json"
-```
-
-### Phase 3: Completion
-
-```javascript
-TodoWrite({todos: [
-  {content: "Validate inputs and create directories", status: "completed", activeForm: "Validating inputs"},
-  {content: extraction_mode == "explore" ? "Analyze design space for maximum contrast" : "Skip design space analysis (imitate mode)", status: "completed", activeForm: extraction_mode == "explore" ? "Analyzing design space" : "Skipping analysis"},
-  {content: extraction_mode == "explore" ? `Generate ${variants_count} divergent design directions (REQUIRED)` : "Prepare for high-fidelity extraction", status: "completed", activeForm: extraction_mode == "explore" ? "Generating directions" : "Preparing extraction"},
-  {content: extraction_mode == "explore" ? `Write and verify design-space-analysis.json (REQUIRED)` : "Skip design space output", status: "completed", activeForm: extraction_mode == "explore" ? "Writing and verifying file" : "Skipping output"},
-  {content: `Generate and write ${variants_count} ${extraction_mode == "explore" ? "contrasting" : "high-fidelity"} style variant${variants_count > 1 ? "s" : ""} to file`, status: "completed", activeForm: "Generating and writing variants"}
-]});
-```
-
-**Completion Message**:
-```
-✅ Style extraction complete for session: {session_id}
-
-Mode: {extraction_mode == "imitate" ? "🎯 IMITATE (high-fidelity)" : "🎨 EXPLORE (contrast analysis)"}
-Input mode: {input_mode}
-{IF image mode: Images analyzed: {count}}
-{IF prompt mode: Prompt: "{truncated_prompt}"}
-
-{IF extraction_mode == "explore":
-🎨 Design Space Analysis:
-- Generated {variants_count} MAXIMALLY CONTRASTING design directions
-- Min pairwise contrast distance: {design_space_analysis.contrast_verification.min_pairwise_distance}
-- Strategy: {design_space_analysis.contrast_verification.strategy}
-}
-{IF extraction_mode == "imitate":
-🎯 Imitation Mode:
-- High-fidelity single style extraction
-- Design space divergence skipped for faster execution
-}
-
-Generated {variants_count} style variant{variants_count > 1 ? "s" : ""}:
-{FOR each card: - {card.name} ({card.id}) - {card.design_philosophy}}
-
-📂 Outputs:
-- {base_path}/style-extraction/style-cards.json
-{IF extraction_mode == "explore": - {base_path}/style-extraction/design-space-analysis.json}
-
-Next: /workflow:ui-design:consolidate --session {session_id} --variants {variants_count} [--layout-variants <count>]
-
-Note: When called from /workflow:ui-design:{extraction_mode == "imitate" ? "imitate" : "explore"}-auto, consolidation is triggered automatically.
-```
-
-## Output Structure
-
-```
-.workflow/WFS-{session}/design-{run_id}/style-extraction/
-├── style-cards.json              # Complete style variants with token proposals
-└── design-space-analysis.json    # Design directions (explore mode only)
-
-OR (standalone mode):
-
-.workflow/.design/{run_id}/style-extraction/
-├── style-cards.json
-└── design-space-analysis.json    # Only in explore mode
-```
-
-### style-cards.json Format
-
-**Schema Structure**:
-
-```json
-{
-  "extraction_metadata": {"session_id": "string", "input_mode": "image|text|hybrid",
-                           "timestamp": "ISO 8601", "variants_count": "number"},
-  "style_cards": [
-    {
-      "id": "variant-{n}", "name": "Concise Style Name (2-3 words)",
-      "description": "2-3 sentence description of visual language and UX",
-      "design_philosophy": "Core design principles for this variant",
-      "preview": {"primary": "oklch(...)", "background": "oklch(...)",
-                  "font_heading": "Font family, fallbacks", "border_radius": "value"},
-      "proposed_tokens": {
-        "colors": {
-          "brand": {"primary": "oklch(...)", "secondary": "oklch(...)", "accent": "oklch(...)"},
-          "surface": {"background": "oklch(...)", "elevated": "oklch(...)", "overlay": "oklch(...)"},
-          "semantic": {"success": "oklch(...)", "warning": "oklch(...)", "error": "oklch(...)", "info": "oklch(...)"},
-          "text": {"primary": "oklch(...)", "secondary": "oklch(...)", "tertiary": "oklch(...)", "inverse": "oklch(...)"},
-          "border": {"default": "oklch(...)", "strong": "oklch(...)", "subtle": "oklch(...)"}
-        },
-        "typography": {
-          "font_family": {"heading": "...", "body": "...", "mono": "..."},
-          "font_size": {"xs": "...", "sm": "...", "base": "...", "lg": "...", "xl": "...", "2xl": "...", "3xl": "...", "4xl": "..."},
-          "font_weight": {"normal": "400", "medium": "500", "semibold": "600", "bold": "700"},
-          "line_height": {"tight": "1.25", "normal": "1.5", "relaxed": "1.75"},
-          "letter_spacing": {"tight": "-0.025em", "normal": "0", "wide": "0.025em"}
-        },
-        "spacing": {"0": "0", "1": "0.25rem", "2": "0.5rem", "3": "0.75rem", "4": "1rem",
-                    "5": "1.25rem", "6": "1.5rem", "8": "2rem", "10": "2.5rem", "12": "3rem",
-                    "16": "4rem", "20": "5rem", "24": "6rem"},
-        "border_radius": {"none": "0", "sm": "0.25rem", "md": "0.5rem", "lg": "0.75rem",
-                          "xl": "1rem", "full": "9999px"},
-        "shadows": {"sm": "0 1px 2px oklch(0.00 0.00 0 / 0.05)",
-                    "md": "0 4px 6px oklch(0.00 0.00 0 / 0.07)",
-                    "lg": "0 10px 15px oklch(0.00 0.00 0 / 0.10)",
-                    "xl": "0 20px 25px oklch(0.00 0.00 0 / 0.15)"},
-        "breakpoints": {"sm": "640px", "md": "768px", "lg": "1024px", "xl": "1280px", "2xl": "1536px"}
-      }
-    }
-    // Repeat structure for variants_count total (variant-1, variant-2, ..., variant-n)
-  ]
-}
-```
-
-**Key Structural Requirements**:
-- Each variant MUST have complete, independent token proposals (all categories present)
-- All colors MUST use OKLCH format: `oklch(L C H / A)`
-- Token keys MUST match exactly across all variants for consistency
-- Variants differ in VALUES, not structure
-- Production-ready: no placeholders or incomplete sections
-
-## Error Handling
-
-- **No images found**: Report glob pattern and suggest corrections
-- **Invalid prompt**: Require non-empty string for text mode
-- **Claude JSON parsing error**: Retry with stricter format instructions
-- **Invalid session**: Create standalone session automatically in `.workflow/.scratchpad/`
-- **Invalid variant count**: Clamp to 1-5 range and warn user
-
-## Key Features
-
-1. **🚀 AI-Driven Design Space Exploration** 🆕
-   - Phase 0.5: AI analyzes requirements and generates MAXIMALLY CONTRASTING design directions
-   - Uses 6-dimensional design attribute space (color saturation, visual weight, formality, organic/geometric, innovation, density)
-   - Ensures each variant occupies a distinct region of the design spectrum
-   - Generates search keywords and anti-patterns for each variant
-   - Provides contrast verification with minimum pairwise distance metrics
-
-2. **🎯 Variant-Specific Design Directions** 🆕
-   - AI generates search keywords and anti-patterns for each variant
-   - Each variant has distinct design philosophy (e.g., "minimal brutalist" vs "bold vibrant")
-   - Philosophy-specific keywords guide synthesis
-   - Design space analysis saved for consolidation phase
-   - Trend research deferred to consolidation for better integration
-
-3. **🔒 Maximum Contrast Guarantee**
-   - AI-driven divergence ensures variants are maximally distant in attribute space
-   - Each variant has distinct: philosophy, color saturation, visual weight, formality, etc.
-   - Explicit anti-patterns prevent variants from borrowing each other's characteristics
-   - Contrast verification built into design space analysis
-
-4. **100% Claude-Native Analysis**
-   - No external tools (gemini-wrapper, codex, or MCP) - pure Claude
-   - Single-pass comprehensive analysis guided by design space analysis
-   - Fast, deterministic style synthesis without external dependencies
-
-5. **Streamlined Output**
-   - Single file (`style-cards.json`) vs. multiple scattered files
-   - Eliminates `semantic_style_analysis.json`, `design-tokens.json`, `tailwind-tokens.js` clutter
-   - Each variant contains complete token proposals embedded
-
-6. **Flexible Input Modes**
-   - Image-only: Analyze visual references through each variant's philosophical lens
-   - Text-only: Generate from descriptions with maximum divergence
-   - Hybrid: Text guides image analysis while maintaining variant independence
-   - All modes enhanced with AI-driven design space analysis
-
-7. **Context-Aware & Dynamic**
-   - Extracts design keywords from user prompts (e.g., "minimalist", "Linear.app")
-   - Considers project type from brainstorming artifacts
-   - Dynamically generates design directions based on project context
-   - No hardcoded design philosophies - fully adaptive
-
-8. **Production-Ready Token Proposals**
-   - Complete design system proposals per variant
-   - OKLCH color format for perceptual uniformity and accessibility
-   - Semantic naming conventions
-   - WCAG AA accessibility considerations built-in
-   - Variant-specific token sets (not generic)
-
-9. **Workflow Integration**
-   - Integrated mode: Works within existing workflow sessions
-   - Standalone mode: Auto-creates session in scratchpad
-   - Context-aware: Can reference synthesis-specification.md or ui-designer/analysis.md
-   - Contrast metrics included in completion report
-
-## Integration Points
-
-- **Input**: Reference images (PNG, JPG, WebP) via glob patterns, or text prompts
-- **Output**: `style-cards.json` for `/workflow:ui-design:consolidate`
-- **Context**: Optional brainstorming artifacts (`synthesis-specification.md`, `ui-designer/analysis.md`)
-- **Auto Integration**: Automatically triggered by `/workflow:ui-design:auto` workflow
-- **Next Step**: `/workflow:ui-design:consolidate --session {session_id} --variants {count} [--layout-variants <count>]` (add `--keep-separate` for matrix mode)

.claude/commands/workflow/ui-design/generate-v2.md

@@ -1,546 +0,0 @@
----
-name: generate-v2
-description: Generate UI prototypes using target-style-centric batch generation
-usage: /workflow:ui-design:generate-v2 [--targets "<list>"] [--target-type "page|component"] [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
-examples:
-  - /workflow:ui-design:generate-v2 --session WFS-auth --targets "dashboard,settings" --style-variants 3 --layout-variants 3
-  - /workflow:ui-design:generate-v2 --base-path ".workflow/WFS-auth/design-run-20250109-143022" --targets "home,pricing"
-  - /workflow:ui-design:generate-v2 --targets "navbar,hero,card" --target-type "component" --style-variants 2 --layout-variants 2
-allowed-tools: TodoWrite(*), Read(*), Write(*), Task(ui-design-agent), Bash(*)
----
-
-# UI Generation Command (Target-Style-Centric Architecture)
-
-**Executor**: → @ui-design-agent
-**Parallel Generation**: Phase 2 → @ui-design-agent (T×S tasks, each handling L layouts)
-
-## Overview
-Generate production-ready UI prototypes (HTML/CSS) using **target-style-centric batch generation**. Each agent handles all layout variants for one target × one style combination, ensuring component isolation and focused generation.
-
-## Core Philosophy
-- **Target-Style-Centric**: Each of T×S agents generates L layouts for one target × one style
-- **Component Isolation**: Tasks completely independent, preventing cross-component interference
-- **Style-Aware Structure**: HTML DOM adapts based on design_attributes (density, visual_weight, etc.)
-- **Performance Optimized**: T×S agent calls with highly focused scope per agent
-- **Layout Inspiration**: Simple text-based research replaces complex JSON planning
-- **Self-Contained CSS**: Agent reads design-tokens.json and creates independent CSS (no token.css reference)
-- **Production-Ready**: Semantic HTML5, ARIA attributes, responsive design
-
-## Execution Protocol
-
-### Phase 1: Path Resolution & Context Loading
-```bash
-# 1. Determine base path
-IF --base-path: base_path = {provided_base_path}
-ELSE IF --session: base_path = find_latest_path_matching(".workflow/WFS-{session}/design-*")
-ELSE: base_path = find_latest_path_matching(".workflow/.design/*")
-
-# 2. Determine style variant count and layout variant count
-style_variants = --style-variants OR auto_detect_from_consolidation()
-layout_variants = --layout-variants OR 3
-VALIDATE: 1 <= style_variants <= 5
-VALIDATE: 1 <= layout_variants <= 5
-
-# Validate against actual style directories
-actual_style_count = count_directories({base_path}/style-consolidation/style-*)
-
-IF actual_style_count == 0:
-    ERROR: "No style directories found"; SUGGEST: "Run /workflow:ui-design:consolidate first"; EXIT 1
-
-IF style_variants > actual_style_count:
-    WARN: "⚠️ Requested {style_variants}, but only {actual_style_count} exist"
-    REPORT: "   Available styles: {list_directories}"; style_variants = actual_style_count
-
-REPORT: "✅ Validated style variants: {style_variants}"
-
-# 3. Enhanced target list parsing with type detection
-target_list = []; target_type = "page"  # Default
-
-# Priority 1: Unified --targets parameter
-IF --targets:
-    raw_targets = {--targets value}
-    target_list = split_and_clean(raw_targets, delimiters=[",", ";", "、"])
-    target_list = [t.strip().lower().replace(" ", "-") for t in target_list if t.strip()]
-
-    target_type = --target-type provided ? {--target-type} : detect_target_type(target_list)
-    REPORT: "🎯 Using provided targets ({target_type}): {', '.join(target_list)}"
-
-# Priority 2: Legacy --pages parameter
-ELSE IF --pages:
-    raw_targets = {--pages value}
-    target_list = split_and_clean(raw_targets, delimiters=[",", ";", "、"])
-    target_list = [t.strip().lower().replace(" ", "-") for t in target_list if t.strip()]
-    target_type = "page"
-    REPORT: "📋 Using provided pages (legacy): {', '.join(target_list)}"
-
-# Priority 3: Extract from synthesis-specification.md
-ELSE IF --session:
-    synthesis_spec = Read(.workflow/WFS-{session}/.brainstorming/synthesis-specification.md)
-    target_list = extract_targets_from_synthesis(synthesis_spec); target_type = "page"
-    REPORT: "📋 Extracted from synthesis: {', '.join(target_list)}"
-
-# Priority 4: Detect from existing prototypes or default
-ELSE:
-    target_list = detect_from_prototypes({base_path}/prototypes/) OR ["home"]; target_type = "page"
-    REPORT: "📋 Detected/default targets: {', '.join(target_list)}"
-
-# 4. Validate target names
-validated_targets = [t for t in target_list if regex_match(t, r"^[a-z0-9][a-z0-9_-]*$")]
-invalid_targets = [t for t in target_list if t not in validated_targets]
-
-IF invalid_targets: REPORT: "⚠️ Skipped invalid target names: {', '.join(invalid_targets)}"
-VALIDATE: validated_targets not empty, "No valid targets found"
-target_list = validated_targets
-
-STORE: target_list, target_type
-
-# 5. Verify design systems exist
-FOR style_id IN range(1, style_variants + 1):
-    VERIFY: exists({base_path}/style-consolidation/style-{style_id}/design-tokens.json)
-
-# 6. Load design space analysis (for style-aware generation)
-design_space_path = "{base_path}/style-extraction/design-space-analysis.json"
-IF exists(design_space_path):
-    design_space_analysis = Read(design_space_path)
-    REPORT: "📊 Loaded design space analysis with style attributes"
-ELSE:
-    WARN: "⚠️ No design space analysis found - will use basic style generation"
-    design_space_analysis = null
-
-# 7. Load requirements (if integrated mode)
-IF --session:
-    synthesis_spec = Read(.workflow/WFS-{session}/.brainstorming/synthesis-specification.md)
-ELSE:
-    synthesis_spec = null
-```
-
-### Phase 1.5: Target Layout Inspiration
-```bash
-REPORT: "💡 Gathering layout inspiration for {len(target_list)} targets..."
-
-CREATE: {base_path}/prototypes/_inspirations/
-
-# For each target, gather layout inspiration via MCP search
-FOR target IN target_list:
-    REPORT: "  Researching '{target}' ({target_type}) layout patterns..."
-
-    # MCP search for layout patterns
-    search_query = f"common {target} {target_type} layout patterns variations best practices"
-    search_results = mcp__exa__web_search_exa(
-        query=search_query,
-        numResults=5
-    )
-
-    # Extract key layout patterns from search results
-    inspiration_content = f"""Layout Inspiration for '{target}' ({target_type})
-Generated: {current_timestamp()}
-Search Query: {search_query}
-
-## Layout Patterns Identified
-
-From web research, {layout_variants} distinct layout approaches:
-
-Layout 1: [First structural pattern identified from search]
-- Key characteristics: ...
-- Structure approach: ...
-
-Layout 2: [Second structural pattern]
-- Key characteristics: ...
-- Structure approach: ...
-
-Layout 3: [Third structural pattern]
-- Key characteristics: ...
-- Structure approach: ...
-
-## Reference Links
-{format_search_results_urls(search_results)}
-
-## Implementation Notes
-- Each layout should be STRUCTURALLY DIFFERENT (not just CSS variations)
-- Consider {target_type}-specific patterns (navigation, content areas, interactions)
-- Adapt structure based on design_attributes in Phase 2
-"""
-
-    # Write simple inspiration file
-    inspiration_file = f"{base_path}/prototypes/_inspirations/{target}-layout-ideas.txt"
-    Write(inspiration_file, inspiration_content)
-
-    REPORT: f"   ✓ Created: {target}-layout-ideas.txt"
-
-REPORT: f"✅ Phase 1.5 complete: Gathered inspiration for {len(target_list)} targets"
-```
-
-### Phase 2: Target-Style-Centric Batch Generation
-
-**Strategy**: T×S target-style-centric agents, each generating L layouts for one target × one style.
-**Performance**: T×S agent calls with component isolation
-
-```bash
-REPORT: "🎨 Phase 2: Launching {len(target_list)}×{style_variants}={len(target_list) * style_variants} target-style agents..."
-REPORT: "   Each agent generates {layout_variants} layouts for one component"
-
-CREATE: {base_path}/prototypes/
-
-# Launch ONE agent task PER TARGET × STYLE combination (parallel execution)
-FOR target IN target_list:
-    # Load layout inspiration for this target
-    inspiration_path = f"{base_path}/prototypes/_inspirations/{target}-layout-ideas.txt"
-
-    FOR style_id IN range(1, style_variants + 1):
-        # Load style-specific context
-        style_tokens_path = f"{base_path}/style-consolidation/style-{style_id}/design-tokens.json"
-        style_guide_path = f"{base_path}/style-consolidation/style-{style_id}/style-guide.md"
-
-        # Extract design attributes for this style (if available)
-        IF design_space_analysis AND style_id <= len(design_space_analysis.divergent_directions):
-            design_attributes = design_space_analysis.divergent_directions[style_id - 1]
-            philosophy_name = design_attributes.philosophy_name
-            attributes_summary = JSON.stringify({
-                density: design_attributes.design_attributes.density,
-                visual_weight: design_attributes.design_attributes.visual_weight,
-                formality: design_attributes.design_attributes.formality,
-                organic_vs_geometric: design_attributes.design_attributes.organic_vs_geometric,
-                innovation: design_attributes.design_attributes.innovation
-            })
-        ELSE:
-            design_attributes = null
-            philosophy_name = f"Style {style_id}"
-            attributes_summary = "No design attributes available"
-
-        Task(ui-design-agent): """
-          [TARGET_STYLE_UI_GENERATION]
-
-          ## 🎯 Mission
-          Generate {layout_variants} layout variants for: {target} × Style-{style_id} ({philosophy_name})
-          Output: {layout_variants × 2} files ({layout_variants} HTML + {layout_variants} CSS)
-
-          ## 🎨 Style Context
-          PHILOSOPHY: {philosophy_name}
-          {IF design_attributes:
-          DESIGN_ATTRIBUTES: {attributes_summary}
-          Key impacts:
-          - density → DOM nesting depth, whitespace scale
-          - visual_weight → wrapper layers, border/shadow strength
-          - formality → semantic structure choices
-          - organic_vs_geometric → alignment, edge treatment
-          - innovation → layout adventurousness
-          }
-
-          ## 📂 Input Resources
-          **Design System**:
-          - Design Tokens (JSON): {style_tokens_path}
-          - Style Guide: {style_guide_path}
-
-          **Layout Inspiration**: {inspiration_path}
-          Contains {layout_variants} distinct structural patterns
-
-          **Target**: {target} ({target_type})
-
-          ## 🔄 Generation Steps (for each layout 1..{layout_variants})
-
-          **1. Read Inspiration**
-          - Load: {inspiration_path}
-          - Apply layout N pattern
-
-          **2. Read Design Tokens**
-          - Load: {style_tokens_path}
-          - Parse JSON structure and extract all design token values
-          - Understand token categories: colors, typography, spacing, shadows, borders, etc.
-
-          **3. Generate HTML Structure**
-          - Complete HTML5 document (<!DOCTYPE>, <html>, <head>, <body>)
-          - Semantic elements: <header>, <nav>, <main>, <section>, <article>, <footer>
-          - ARIA attributes: aria-label, role, aria-labelledby
-          - Responsive meta: <meta name="viewport" content="width=device-width, initial-scale=1">
-          - Include CSS reference: <link rel="stylesheet" href="{target}-style-{style_id}-layout-N.css">
-          - Example: For dashboard-style-1-layout-2.html, use <link rel="stylesheet" href="dashboard-style-1-layout-2.css">
-
-          {IF design_attributes:
-          **⚠️ Adapt DOM based on design_attributes:**
-          - density='spacious' → Flatter hierarchy
-            Example: <main><section class="card"></section></main>
-          - density='compact' → Deeper nesting
-            Example: <main><div class="grid"><div class="card-wrapper"><section></section></div></div></main>
-          - visual_weight='heavy' → Extra wrapper divs for layered effects
-            Example: <div class="border-container"><div class="content-wrapper">...</div></div>
-          - visual_weight='minimal' → Direct structure, minimal wrappers
-            Example: <section class="card">...</section>
-          - organic_vs_geometric → Affects alignment patterns and edge structure
-          }
-
-          **4. Generate Self-Contained CSS**
-          ⚠️ Use design token values DIRECTLY from step 2 - create complete, independent CSS
-
-          **Required Token Usage** (from design-tokens.json):
-          - Colors: Use color values for backgrounds, text, borders
-          - Typography: Use font-family, font-size, font-weight, line-height values
-          - Spacing: Use spacing scale for margins, padding, gaps
-          - Borders: Use border-radius, border-width values
-          - Shadows: Use box-shadow values
-          - Breakpoints: Use breakpoint values for @media queries
-
-          {IF design_attributes:
-          **Apply design_attributes to token selection:**
-          - density='spacious' → Select larger spacing tokens
-          - density='compact' → Select smaller spacing tokens
-          - visual_weight='heavy' → Use stronger shadows, add borders
-          - visual_weight='minimal' → Use subtle/no shadows
-          - formality → Affects typography choices and structure
-          - organic_vs_geometric → Affects border-radius and alignment
-          }
-
-          **CSS Structure**:
-          - Complete styling: colors, typography, layout, spacing, effects
-          - Responsive design: Mobile-first with breakpoint-based @media
-          - Self-contained: No external dependencies or var() references
-
-          **5. Write Files IMMEDIATELY**
-          - Output paths:
-            - HTML: {base_path}/prototypes/{target}-style-{style_id}-layout-N.html
-            - CSS: {base_path}/prototypes/{target}-style-{style_id}-layout-N.css
-          - Write after generating each layout (do NOT accumulate)
-          - Do NOT return content as text
-
-          ## ✅ Success Criteria
-          - [ ] Generated exactly {layout_variants × 2} files
-          - [ ] All HTML includes correct CSS file reference (matching filename pattern)
-          - [ ] All CSS uses design token values directly (self-contained, no var() references)
-          - [ ] CSS fully embodies the style's design tokens (colors, typography, spacing, effects)
-          - [ ] {IF design_attributes: 'HTML structure adapts to design_attributes' ELSE: 'HTML follows layout inspiration'}
-          - [ ] Layouts are structurally distinct (different grids/regions, not just CSS tweaks)
-          - [ ] Files written to filesystem (not returned as text)
-
-          ## 📋 Completion
-          Report: "✅ {target} × Style-{style_id} ({philosophy_name}): {layout_variants × 2} files created"
-        """
-
-REPORT: "⏳ Phase 2: Waiting for {len(target_list) * style_variants} target-style agents to complete..."
-REPORT: "   Expected total files: {style_variants × layout_variants × len(target_list) × 2}"
-```
-
-### Phase 2.5: Verify Agent File Creation
-```bash
-REPORT: "📝 Phase 2.5: Verifying target-style generation..."
-
-total_expected = style_variants × layout_variants × len(target_list) × 2
-total_found = 0
-
-FOR target IN target_list:
-    FOR style_id IN range(1, style_variants + 1):
-        agent_files_found = 0
-
-        FOR layout_id IN range(1, layout_variants + 1):
-            html_file = f"{target}-style-{style_id}-layout-{layout_id}.html"
-            css_file = f"{target}-style-{style_id}-layout-{layout_id}.css"
-
-            html_path = f"{base_path}/prototypes/{html_file}"
-            css_path = f"{base_path}/prototypes/{css_file}"
-
-            # Verify files exist
-            IF exists(html_path) AND exists(css_path):
-                # Validate content
-                html_content = Read(html_path)
-                css_content = Read(css_path)
-
-                # Basic validation
-                VALIDATE: "<!DOCTYPE html>" in html_content, f"Invalid HTML: {html_file}"
-                VALIDATE: f'href="{css_file}"' in html_content, f"Missing or incorrect CSS reference in: {html_file}"
-                VALIDATE: len(css_content) > 100, f"CSS file too small (likely incomplete): {css_file}"
-
-                html_size = get_file_size(html_path)
-                css_size = get_file_size(css_path)
-
-                agent_files_found += 2
-                total_found += 2
-
-                REPORT: f"   ✓ {html_file} ({html_size} KB) + {css_file} ({css_size} KB)"
-            ELSE:
-                ERROR: f"   ✗ Missing files: {target}-style-{style_id}-layout-{layout_id}.*"
-
-        REPORT: f"  {target} × style-{style_id}: {agent_files_found}/{layout_variants * 2} files verified"
-
-IF total_found == total_expected:
-    REPORT: f"✅ Phase 2.5 complete: Verified all {total_expected} files"
-ELSE:
-    ERROR: f"⚠️ Only {total_found}/{total_expected} files found - some agents may have failed"
-```
-
-### Phase 3: Generate Preview Files
-
-```bash
-REPORT: "🌐 Phase 3: Generating preview files..."
-
-prototypes_dir = f"{base_path}/prototypes"
-
-# Template-based preview generation script
-# - Uses: ~/.claude/workflows/_template-compare-matrix.html
-# - Auto-detects: S, L, T from file patterns
-# - Generates: compare.html, index.html, PREVIEW.md
-Bash(~/.claude/scripts/ui-generate-preview-v2.sh "{prototypes_dir}")
-
-# Verify preview files generated
-preview_files = [
-    f"{base_path}/prototypes/compare.html",
-    f"{base_path}/prototypes/index.html",
-    f"{base_path}/prototypes/PREVIEW.md"
-]
-
-all_present = True
-FOR file_path IN preview_files:
-    IF exists(file_path):
-        REPORT: f"   ✓ Generated: {basename(file_path)}"
-    ELSE:
-        WARN: f"   ✗ Missing: {basename(file_path)}"
-        all_present = False
-
-IF all_present:
-    REPORT: "✅ Phase 3 complete: All preview files generated"
-ELSE:
-    WARN: "⚠️ Some preview files missing - script may need attention"
-```
-
-### Phase 4: Completion
-
-```javascript
-TodoWrite({todos: [
-  {content: "Resolve paths and load design systems", status: "completed", activeForm: "Loading design systems"},
-  {content: `Gather layout inspiration for ${target_list.length} targets`, status: "completed", activeForm: "Gathering inspiration"},
-  {content: `Launch ${target_list.length}×${style_variants}=${target_list.length * style_variants} target-style agents (each handling ${layout_variants} layouts)`, status: "completed", activeForm: "Running target-style generation"},
-  {content: `Verify ${style_variants * layout_variants * target_list.length * 2} generated files`, status: "completed", activeForm: "Verifying files"},
-  {content: "Generate preview files (compare.html, index.html)", status: "completed", activeForm: "Generating previews"}
-]});
-```
-
-**Completion Message**:
-```
-✅ Target-Style-Centric UI Generation Complete!
-
-Architecture: Target-Style-Centric Batch Generation
-
-Configuration:
-- Style Variants: {style_variants}
-- Layout Variants: {layout_variants} (inspiration-based)
-- Target Type: {target_type_icon} {target_type}
-- Targets: {target_list}
-- Total Prototypes: {style_variants * layout_variants * len(target_list)}
-
-Agent Execution:
-✅ Target-style agents: T×S = {len(target_list)}×{style_variants} = {len(target_list) * style_variants} agents
-✅ Each agent handles: L = {layout_variants} layouts for one component
-✅ Component isolation: Tasks completely independent
-
-Design Quality:
-✅ Style-Aware Structure: {IF design_space_analysis: 'YES - HTML adapts to design_attributes' ELSE: 'Standard semantic structure'}
-✅ Focused generation: Each agent handles single target × single style
-✅ Self-Contained CSS: Direct design token usage (no var() dependencies)
-
-Output Files:
-- Layout Inspirations: {len(target_list)} simple text files
-- HTML Prototypes: {style_variants * layout_variants * len(target_list)} files
-- CSS Files: {style_variants * layout_variants * len(target_list)} files
-- Preview Files: compare.html, index.html, PREVIEW.md
-
-Generated Structure:
-📂 {base_path}/prototypes/
-├── _inspirations/
-│   └── {target}-layout-ideas.txt ({len(target_list)} inspiration files)
-├── {target}-style-{s}-layout-{l}.html ({style_variants * layout_variants * len(target_list)} prototypes)
-├── {target}-style-{s}-layout-{l}.css
-├── compare.html (interactive S×L×T matrix)
-├── index.html (quick navigation)
-└── PREVIEW.md (usage instructions)
-
-🌐 Interactive Preview:
-1. Matrix View: Open compare.html (recommended)
-2. Quick Index: Open index.html
-3. Instructions: See PREVIEW.md
-
-{IF design_space_analysis:
-🎨 Style-Aware Generation Active:
-Each style's prototypes use structure adapted to design_attributes:
-- Density affects container nesting and whitespace
-- Visual weight affects wrapper layers and border structure
-- Same layout × same target × different style = DIFFERENT HTML trees!
-}
-
-Next: /workflow:ui-design:update {--session flag if applicable}
-
-Note: When called from /workflow:ui-design:explore-auto, design-update is triggered automatically.
-
-**Dynamic Values**: target_type_icon: "📄" for page, "🧩" for component
-```
-
-## Output Structure
-
-```
-{base_path}/prototypes/
-├── _inspirations/                                 # Layout inspiration only
-│   └── {target}-layout-ideas.txt                 # Simple inspiration text
-├── {target}-style-{s}-layout-{l}.html            # Final prototypes (S×L×T)
-├── {target}-style-{s}-layout-{l}.css
-├── compare.html                                   # Interactive matrix
-├── index.html                                     # Navigation page
-└── PREVIEW.md                                     # Instructions
-
-{base_path}/style-consolidation/
-├── style-1/ (design-tokens.json, style-guide.md)
-├── style-2/ (same structure)
-└── style-{S}/ (same structure)
-```
-
-## Error Handling
-
-### Pre-execution Checks
-- **No design systems found**: Error - Run `/workflow:ui-design:consolidate` first
-- **Invalid target names**: Extract from synthesis-specification.md or error with validation message
-- **Missing design-space-analysis.json**: WARN only - generation continues with basic structure
-- **Unsupported target type**: Error if target_type not in ["page", "component"]
-
-### Phase-Specific Errors
-- **Agent execution errors (Phase 2)**: Report details, identify which target × style agent failed
-- **Invalid design-tokens.json**: Check JSON format and structure
-- **Missing files (Phase 2.5)**: Indicates agent failed to write - review agent output logs
-- **MCP search errors (Phase 1.5)**: Check network connectivity, retry search
-- **Preview generation errors (Phase 3)**: Check script exists, permissions
-
-### Recovery Strategies
-- **Partial generation**: If some target-style agents succeed, you still have those prototypes
-- **Retry single combination**: Can re-run targeting failed target × style combination
-- **Missing design_attributes**: Generation works without them - just less style-aware
-- **Permission errors**: Run `chmod +x ~/.claude/scripts/ui-generate-preview-v2.sh`
-
-## Key Features
-
-1. **🚀 Target-Style-Centric Batch Generation**
-   Each agent handles L layouts for one target × one style with component isolation
-
-2. **🎯 Component Isolation**
-   Tasks completely independent, preventing cross-component interference
-
-3. **🎨 Style-Aware Structure Adaptation**
-   HTML DOM adapts based on design_attributes (density, visual_weight, organic_vs_geometric)
-
-4. **⚡ Performance Optimized**
-   Parallel execution of T×S agents with highly focused scope per agent
-
-5. **💡 Simplified Layout Inspiration**
-   Simple text-based research replaces complex JSON planning
-
-6. **🔧 Focused Agent Scope**
-   Each agent generates only L layouts, reducing complexity and improving quality
-
-7. **🎯 Self-Contained CSS Generation**
-   Agents read design-tokens.json and create independent CSS with direct token values (no var() references)
-
-8. **🌐 Interactive Visualization**
-   Full-featured compare.html with matrix grid
-
-9. **✅ Production-Ready Output**
-   Semantic HTML5, ARIA attributes, WCAG 2.2 compliant
-
-## Integration Points
-
-- **Input**: Per-style design-tokens.json; design-space-analysis.json (optional); targets + layout-variants
-- **Output**: S×L×T HTML/CSS prototypes with self-contained styling for `/workflow:ui-design:update`
-- **Auto Integration**: Triggered by `/workflow:ui-design:explore-auto`
-- **Backward Compatibility**: Works without design-space-analysis.json

.claude/commands/workflow/ui-design/generate.md

@@ -1,617 +1,309 @@
 ---
 name: generate
-description: Generate UI prototypes in matrix mode (style × layout combinations) for pages or components
-usage: /workflow:ui-design:generate [--targets "<list>"] [--target-type "page|component"] [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
+description: Assemble UI prototypes by combining layout templates with design tokens (pure assembler)
+usage: /workflow:ui-design:generate [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
 examples:
-  - /workflow:ui-design:generate --base-path ".workflow/WFS-auth/design-run-20250109-143022" --targets "dashboard,settings" --target-type "page" --style-variants 3 --layout-variants 3
-  - /workflow:ui-design:generate --session WFS-auth --targets "home,pricing" --target-type "page" --style-variants 2 --layout-variants 2
-  - /workflow:ui-design:generate --base-path "./.workflow/.design/run-20250109-150533"  # ✅ Recommended: auto-detect variants
-  - /workflow:ui-design:generate --targets "navbar,hero,card" --target-type "component" --style-variants 3 --layout-variants 2
-  - /workflow:ui-design:generate --pages "home,dashboard" --style-variants 2 --layout-variants 2  # Legacy syntax
+  - /workflow:ui-design:generate --session WFS-auth
+  - /workflow:ui-design:generate --style-variants 2 --layout-variants 2
+  - /workflow:ui-design:generate --base-path ".workflow/WFS-auth/design-run-20250109-143022"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Task(ui-design-agent), Bash(*)
 ---
 
-# UI Generation Command (Matrix Mode)
-
-**Executor**: → @ui-design-agent
-**Parallel Generation**: Phase 2a → @ui-design-agent (L×T tasks)
+# Generate UI Prototypes (/workflow:ui-design:generate)
 
 ## Overview
-Generate production-ready UI prototypes (HTML/CSS) in `style × layout` matrix mode, strictly adhering to consolidated design tokens from separate style design systems. Supports both full-page layouts and isolated component generation.
+Pure assembler that combines pre-extracted layout templates with design tokens to generate UI prototypes (`style × layout × targets`). No layout design logic - purely combines existing components.
 
-## Core Philosophy
-- **Unified Generation**: Single mode generating `style_variants × layout_variants × targets` prototypes
-- **Target Types**: Supports pages (full layouts) and components (isolated UI elements)
-- **Agent-Driven**: Uses `Task(ui-design-agent)` for parallel generation
-- **Token-Driven**: All styles reference per-style design-tokens.json; no hardcoded values
-- **Production-Ready**: Semantic HTML5, ARIA attributes, responsive design
-- **Template-Based**: Decouples HTML structure from CSS styling for optimal performance
-- **Adaptive Wrapper**: All templates use complete HTML5 documents; body content adapts (full page structure for pages, isolated component for components)
+**Strategy**: Pure Assembly
+- **Input**: `layout-templates.json` + `design-tokens.json`
+- **Process**: Combine structure (DOM) with style (tokens)
+- **Output**: Complete HTML/CSS prototypes
+- **No Design Logic**: All layout and style decisions already made
 
-## Execution Protocol
+**Prerequisite Commands**:
+- `/workflow:ui-design:style-extract` → Style tokens
+- `/workflow:ui-design:consolidate` → Final design tokens
+- `/workflow:ui-design:layout-extract` → Layout structure
 
-### Phase 1: Path Resolution & Context Loading
+## Phase 1: Setup & Validation
 
+### Step 1: Resolve Base Path & Parse Configuration
 ```bash
-# 1. Determine base path
-IF --base-path: base_path = {provided_base_path}
-ELSE IF --session: base_path = find_latest_path_matching(".workflow/WFS-{session}/design-*")
-ELSE: base_path = find_latest_path_matching(".workflow/.design/*")
+# Determine working directory
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
 
-# 2. Determine style variant count and layout variant count
-style_variants = --style-variants OR 3; VALIDATE: 1 <= style_variants <= 5
-layout_variants = --layout-variants OR 3; VALIDATE: 1 <= layout_variants <= 5
-
-# Validate against actual style directories
-actual_style_count = count_directories({base_path}/style-consolidation/style-*)
-
-IF actual_style_count == 0:
-    ERROR: "No style directories found"; SUGGEST: "Run /workflow:ui-design:consolidate first"; EXIT 1
-
-IF style_variants > actual_style_count:
-    WARN: "⚠️ Requested {style_variants}, but only {actual_style_count} exist"
-    REPORT: "   Available styles: {list_directories}"; style_variants = actual_style_count
-
-REPORT: "✅ Validated style variants: {style_variants}"
-
-# 3. Enhanced target list parsing with type detection
-target_list = []; target_type = "page"  # Default
-
-# Priority 1: Unified --targets parameter
-IF --targets:
-    raw_targets = {--targets value}
-    target_list = split_and_clean(raw_targets, delimiters=[",", ";", "、"])
-    target_list = [t.strip().lower().replace(" ", "-") for t in target_list if t.strip()]
-
-    target_type = --target-type provided ? {--target-type} : detect_target_type(target_list)
-    REPORT: "🎯 Using provided targets ({target_type}): {', '.join(target_list)}"
-
-# Priority 2: Legacy --pages parameter
-ELSE IF --pages:
-    raw_targets = {--pages value}
-    target_list = split_and_clean(raw_targets, delimiters=[",", ";", "、"])
-    target_list = [t.strip().lower().replace(" ", "-") for t in target_list if t.strip()]
-    target_type = "page"
-    REPORT: "📋 Using provided pages (legacy): {', '.join(target_list)}"
-
-# Priority 3: Extract from synthesis-specification.md
-ELSE IF --session:
-    synthesis_spec = Read(.workflow/WFS-{session}/.brainstorming/synthesis-specification.md)
-    target_list = extract_targets_from_synthesis(synthesis_spec); target_type = "page"
-    REPORT: "📋 Extracted from synthesis: {', '.join(target_list)}"
-
-# Priority 4: Detect from existing prototypes or default
-ELSE:
-    target_list = detect_from_prototypes({base_path}/prototypes/) OR ["home"]; target_type = "page"
-    REPORT: "📋 Detected/default targets: {', '.join(target_list)}"
-
-# 4. Validate target names
-validated_targets = [t for t in target_list if regex_match(t, r"^[a-z0-9][a-z0-9_-]*$")]
-invalid_targets = [t for t in target_list if t not in validated_targets]
-
-IF invalid_targets: REPORT: "⚠️ Skipped invalid target names: {', '.join(invalid_targets)}"
-VALIDATE: validated_targets not empty, "No valid targets found"
-target_list = validated_targets
-
-STORE: target_list, target_type
-
-# 5. Verify design systems exist
-FOR style_id IN range(1, style_variants + 1):
-    VERIFY: exists({base_path}/style-consolidation/style-{style_id}/design-tokens.json)
-    VERIFY: exists({base_path}/style-consolidation/style-{style_id}/style-guide.md)
-
-# 6. Load requirements (if integrated mode)
-IF --session: synthesis_spec = Read(.workflow/WFS-{session}/.brainstorming/synthesis-specification.md)
+# Get style count
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
 ```
 
-### Phase 1.5: Target-Specific Layout Planning
-
+### Step 2: Load Layout Templates
 ```bash
-REPORT: "📐 Planning {layout_variants} layout strategies for each target..."
+# Check layout templates exist
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
 
-CREATE: {base_path}/prototypes/_templates/
-
-# For each target, plan its specific layouts
-FOR target IN target_list:
-    REPORT: "  Planning layouts for '{target}' ({target_type})..."
-
-    FOR layout_id IN range(1, layout_variants + 1):
-        Task(ui-design-agent): "
-          [TARGET_LAYOUT_PLANNING]
-
-          TARGET: {target} | TARGET_TYPE: {target_type} | LAYOUT_ID: {layout_id}/{layout_variants}
-          BASE_PATH: {base_path}
-          {IF --session: PROJECT_REQUIREMENTS: .workflow/WFS-{session}/.brainstorming/synthesis-specification.md}
-
-          ## Task
-          Research {target} {target_type} layout variations → Select approach #{layout_id} → Generate layout plan JSON
-
-          ## Research
-          mcp__exa__web_search_exa(
-            query=\"common {target} {target_type} layout patterns variations best practices 2024\",
-            numResults=5
-          )
-          Identify multiple structural patterns → Select DISTINCT approach #{layout_id}
-
-          ## Output
-          Write(\"{base_path}/prototypes/_templates/{target}-layout-{layout_id}.json\", layout_plan_json)
-
-          ## JSON Structure
-          ```json
-          {
-            "id": "layout-{layout_id}",
-            "target": "{target}",
-            "target_type": "{target_type}",
-            "name": "Descriptive name (2-4 words)",
-            "description": "2-3 sentences",
-            "structure": {
-              // IF page: type, regions, grid, sidebar, responsive
-              // IF component: arrangement, alignment, spacing, element_order
-            },
-            "semantic_hints": [...],
-            "accessibility_features": [...],
-            "research_references": [...]
-          }
-          ```
-
-          ## Requirements
-          - Research-informed, structurally DIFFERENT from other layout IDs
-          - Write file directly (not text output)
-        "
-
-# Wait for all agent tasks to complete
-REPORT: "⏳ Waiting for layout planning agents to complete..."
-
-# Verify agent created layout JSON files
-REPORT: "📝 Verifying agent file creation..."
-
-FOR target IN target_list:
-    FOR layout_id IN range(1, layout_variants + 1):
-        layout_json_label = f"{target}-layout-{layout_id}.json"
-        json_path = f"{base_path}/prototypes/_templates/{layout_json_label}"
-
-        # Verify file exists
-        VERIFY: exists(json_path), f"Layout JSON not created by agent: {layout_json_label}"
-
-        # Validate JSON structure
-        TRY:
-            layout_json_content = Read(json_path)
-            layout_plan = JSON.parse(layout_json_content)
-
-            # Validate required fields
-            VALIDATE: layout_plan.id == f"layout-{layout_id}", f"Invalid layout ID in {layout_json_label}"
-            VALIDATE: layout_plan.target == target, f"Invalid target in {layout_json_label}"
-            VALIDATE: layout_plan.target_type == target_type, f"Invalid target_type in {layout_json_label}"
-            VALIDATE: layout_plan.name exists, f"Missing 'name' field in {layout_json_label}"
-            VALIDATE: layout_plan.structure exists, f"Missing 'structure' field in {layout_json_label}"
-
-            file_size = get_file_size(json_path)
-            REPORT: f"   ✓ Verified: {layout_json_label} - {layout_plan.name} ({file_size} KB)"
-        CATCH error:
-            ERROR: f"Validation failed for {layout_json_label}: {error}"
-            REPORT: f"   ⚠️ File exists but validation failed - review agent output"
-
-REPORT: f"✅ Phase 1.5 complete: Verified {len(target_list) × layout_variants} target-specific layout files"
+# Load layout templates
+Read({base_path}/layout-extraction/layout-templates.json)
+# Extract: targets, layout_variants count, device_type, template structures
 ```
 
-### Phase 1.6: Convert Design Tokens to CSS
+**Output**: `base_path`, `style_variants`, `layout_templates[]`, `targets[]`, `device_type`
 
+### Step 3: Validate Design Tokens
 ```bash
-REPORT: "🎨 Converting design tokens to CSS variables..."
+# Check design tokens exist for all styles
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "valid")
 
-# Check for jq dependency
-IF NOT command_exists("jq"):
-    ERROR: "jq is not installed or not in PATH. The conversion script requires jq."
-    REPORT: "Please install jq: macOS: brew install jq | Linux: apt-get install jq | Windows: https://stedolan.github.io/jq/download/"
-    EXIT 1
-
-# Convert design tokens to CSS for each style variant
-FOR style_id IN range(1, style_variants + 1):
-    tokens_json_path = "{base_path}/style-consolidation/style-${style_id}/design-tokens.json"
-    tokens_css_path = "{base_path}/style-consolidation/style-${style_id}/tokens.css"
-    script_path = "~/.claude/scripts/convert_tokens_to_css.sh"
-
-    # Verify input file exists
-    VERIFY: exists(tokens_json_path), f"Design tokens not found for style-{style_id}"
-
-    # Execute conversion: cat input.json | script.sh > output.css
-    Bash(cat "${tokens_json_path}" | "${script_path}" > "${tokens_css_path}")
-
-    # Verify output was generated
-    IF exit_code == 0 AND exists(tokens_css_path):
-        file_size = get_file_size(tokens_css_path)
-        REPORT: f"   ✓ Generated tokens.css for style-{style_id} ({file_size} KB)"
-    ELSE:
-        ERROR: f"Failed to generate tokens.css for style-{style_id}"
-        EXIT 1
-
-REPORT: f"✅ Phase 1.6 complete: Converted {style_variants} design token files to CSS"
+# For each style variant: Load design tokens
+Read({base_path}/style-consolidation/style-{id}/design-tokens.json)
 ```
 
-### Phase 1.7: Extract Token Variable Names from CSS
+**Output**: `design_tokens[]` for all style variants
 
+## Phase 2: Assembly (Agent)
+
+**Executor**: `Task(ui-design-agent)` × `T × S × L` tasks (can be batched)
+
+### Step 1: Launch Assembly Tasks
 ```bash
-REPORT: "📋 Extracting actual CSS variable names from tokens.css..."
-tokens_css_path = "{base_path}/style-consolidation/style-1/tokens.css"
-VERIFY: exists(tokens_css_path), "tokens.css not found. Phase 1.6 may have failed."
-
-tokens_css_content = Read(tokens_css_path)
-
-# Extract all CSS variable names from the generated file
-# Pattern: --variable-name: value;
-all_token_vars = extract_css_variables(tokens_css_content)  # Regex: r'--([a-z0-9-_]+):'
-
-# Categorize variables for better Agent understanding
-color_vars = [v for v in all_token_vars if v.startswith('--color-')]
-typography_vars = [v for v in all_token_vars if v.startswith(('--font-', '--line-height-', '--letter-spacing-'))]
-spacing_vars = [v for v in all_token_vars if v.startswith('--spacing-')]
-radius_vars = [v for v in all_token_vars if v.startswith('--border-radius-')]
-shadow_vars = [v for v in all_token_vars if v.startswith('--shadow-')]
-breakpoint_vars = [v for v in all_token_vars if v.startswith('--breakpoint-')]
-
-REPORT: f"✅ Extracted {len(all_token_vars)} actual CSS variables from tokens.css"
-REPORT: f"   Colors: {len(color_vars)} | Typography: {len(typography_vars)} | Spacing: {len(spacing_vars)}"
+bash(mkdir -p {base_path}/prototypes)
 ```
 
-### Phase 2: Optimized Matrix UI Generation
+For each `target × style_id × layout_id`:
+```javascript
+Task(ui-design-agent): `
+  [LAYOUT_STYLE_ASSEMBLY]
+  🎯 Assembly task: {target} × Style-{style_id} × Layout-{layout_id}
+  Combine: Pre-extracted layout structure + design tokens → Final HTML/CSS
 
-**Strategy**: Two-layer generation reduces complexity from `O(S×L×T)` to `O(L×T)`, achieving **`S` times faster** performance.
+  TARGET: {target} | STYLE: {style_id} | LAYOUT: {layout_id}
+  BASE_PATH: {base_path}
 
-- **Layer 1**: Generate `L × T` layout templates (HTML structure + structural CSS) by agent
-- **Layer 2**: Instantiate `S × L × T` final prototypes via fast file operations
+  ## Inputs (READ ONLY - NO DESIGN DECISIONS)
+  1. Layout Template:
+     Read("{base_path}/layout-extraction/layout-templates.json")
+     Find template where: target={target} AND variant_id="layout-{layout_id}"
+     Extract: dom_structure, css_layout_rules, device_type
 
-#### Phase 2a: Layout Template Generation
+  2. Design Tokens:
+     Read("{base_path}/style-consolidation/style-{style_id}/design-tokens.json")
+     Extract: ALL token values (colors, typography, spacing, borders, shadows, breakpoints)
 
-**Parallel Executor**: → @ui-design-agent
+  ## Assembly Process
+  1. Build HTML: {base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html
+     - Recursively build from template.dom_structure
+     - Add: <!DOCTYPE html>, <head>, <meta viewport>
+     - CSS link: <link href="{target}-style-{style_id}-layout-{layout_id}.css">
+     - Inject placeholder content (Lorem ipsum, sample data)
+     - Preserve all attributes from dom_structure
 
-```bash
-CREATE: {base_path}/prototypes/_templates/
-CREATE: {base_path}/prototypes/
+  2. Build CSS: {base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.css
+     - Start with template.css_layout_rules
+     - Replace ALL var(--*) with actual token values from design-tokens.json
+       Example: var(--spacing-4) → 1rem (from tokens.spacing.4)
+       Example: var(--breakpoint-md) → 768px (from tokens.breakpoints.md)
+     - Add visual styling using design tokens:
+       * Colors: tokens.colors.*
+       * Typography: tokens.typography.*
+       * Shadows: tokens.shadows.*
+       * Border radius: tokens.border_radius.*
+     - Device-optimized for template.device_type
 
-# Launch parallel template generation tasks → @ui-design-agent
-# Total agent tasks: layout_variants × len(target_list)
-FOR layout_id IN range(1, layout_variants + 1):
-    FOR target IN target_list:
-        # Read the target-specific layout plan
-        layout_json_path = f"{base_path}/prototypes/_templates/{target}-layout-{layout_id}.json"
-        layout_plan = Read(layout_json_path)
-
-        Task(ui-design-agent): "
-          [UI_LAYOUT_TEMPLATE_GENERATION]
-
-          🚨 TARGET INDEPENDENCE: Generate template for EXACTLY ONE target: '{target}' (standalone, reusable)
-
-          LAYOUT_ID: {layout_id} | TARGET: {target} | TARGET_TYPE: {target_type}
-          BASE_PATH: {base_path}
-          {IF --session: REQUIREMENTS: .workflow/WFS-{session}/.brainstorming/synthesis-specification.md}
-
-          ## Layout Plan to Implement
-          **Path**: {layout_json_path}
-          **Plan**: {JSON.stringify(layout_plan, null, 2)}
-
-          ## Task
-          Generate TWO template files implementing the layout plan:
-          - HTML: {base_path}/prototypes/_templates/{target}-layout-{layout_id}.html
-          - CSS: {base_path}/prototypes/_templates/{target}-layout-{layout_id}.css
-
-          ## HTML Requirements
-          - Complete HTML5 document (<!DOCTYPE>, <html>, <head>, <body>)
-          - Semantic elements + ARIA attributes
-          - Body content:
-            * IF page → Full structure (header, nav, main, footer)
-            * IF component → Isolated element in presentation wrapper
-          - ⚠️ CRITICAL CSS placeholders in <head>:
-            <link rel=\"stylesheet\" href=\"{{STRUCTURAL_CSS}}\">
-            <link rel=\"stylesheet\" href=\"{{TOKEN_CSS}}\">
-
-          ## CSS Requirements - Token Reference
-
-          **1. Read tokens.css**
-          Read(\"{base_path}/style-consolidation/style-1/tokens.css\")
-          Extract all CSS variable names (pattern: lines with \"  --\" in \":root {}\")
-
-          **2. Available Tokens**
-          - Colors: {', '.join(color_vars[:5])}... ({len(color_vars)} total)
-          - Typography: {', '.join(typography_vars[:5])}... ({len(typography_vars)} total)
-          - Spacing: {', '.join(spacing_vars[:5])}... ({len(spacing_vars)} total)
-          - Radius: {', '.join(radius_vars[:3])}... ({len(radius_vars)} total)
-          - Shadows: {', '.join(shadow_vars)}
-
-          **3. Variable Usage Rules**
-          - ✅ Use ONLY variables from tokens.css (exact names)
-          - ✅ Format: var(--exact-name-from-file)
-          - ❌ NO invented/guessed variable names
-          - ❌ NO hardcoded values (colors, fonts, spacing)
-
-          **4. Optional Extension**
-          If core tokens insufficient → Create `{target}-layout-{layout_id}-tokens.css` with `--layout-*` prefix
-          Examples: `--layout-spacing-navbar-height`, `--layout-size-sidebar-width`
-
-          **CSS Scope**: Structural layout only (Flexbox, Grid, positioning)
-          **Responsive**: Mobile-first approach
-
-          ## Write Operations
-          Write(\"{base_path}/prototypes/_templates/{target}-layout-{layout_id}.html\", html_content)
-          Write(\"{base_path}/prototypes/_templates/{target}-layout-{layout_id}.css\", css_content)
-
-          Report completion with file paths. Write files directly (not text output).
-        "
-
-REPORT: "⏳ Phase 2a: Waiting for agents to complete template generation..."
+  ## Assembly Rules
+  - ✅ Pure assembly: Combine existing structure + existing style
+  - ❌ NO layout design decisions (structure pre-defined)
+  - ❌ NO style design decisions (tokens pre-defined)
+  - ✅ Replace var() with actual values
+  - ✅ Add placeholder content only
+  - Write files IMMEDIATELY
+  - CSS filename MUST match HTML <link href="...">
+`
 ```
 
-#### Phase 2a.5: Verify Agent Template File Creation
-
+### Step 2: Verify Generated Files
 ```bash
-REPORT: "📝 Phase 2a.5: Verifying agent template file creation..."
+# Count expected vs found
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
 
-# Verify each agent created template files
-FOR layout_id IN range(1, layout_variants + 1):
-    FOR target IN target_list:
-        html_label = f"{target}-layout-{layout_id}.html"
-        css_label = f"{target}-layout-{layout_id}.css"
-
-        html_path = f"{base_path}/prototypes/_templates/{html_label}"
-        css_path = f"{base_path}/prototypes/_templates/{css_label}"
-
-        # Verify files exist
-        VERIFY: exists(html_path), f"HTML template not created by agent: {html_label}"
-        VERIFY: exists(css_path), f"CSS template not created by agent: {css_label}"
-
-        # Validate content
-        TRY:
-            html_content = Read(html_path)
-            css_content = Read(css_path)
-
-            # Basic validation checks
-            VALIDATE: len(html_content) > 100, f"HTML template too short: {html_label}"
-            VALIDATE: len(css_content) > 50, f"CSS template too short: {css_label}"
-            VALIDATE: "<!DOCTYPE html>" in html_content, f"Invalid HTML structure: {html_label}"
-            VALIDATE: "var(--" in css_content, f"Missing CSS variables: {css_label}"
-
-            html_size = get_file_size(html_path)
-            css_size = get_file_size(css_path)
-            REPORT: f"   ✓ Verified: {html_label} ({html_size} KB) + {css_label} ({css_size} KB)"
-        CATCH error:
-            ERROR: f"Validation failed for {target}-layout-{layout_id}: {error}"
-            REPORT: f"   ⚠️ Files exist but validation failed - review agent output"
-
-REPORT: "✅ Phase 2a.5 complete: Verified {layout_variants * len(target_list) * 2} template files"
+# Validate samples
+Read({base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html)
+# Check: <!DOCTYPE html>, correct CSS href, sufficient CSS length
 ```
 
-#### Phase 2b: Prototype Instantiation
+**Output**: `S × L × T × 2` files verified
 
+## Phase 3: Generate Preview Files
+
+### Step 1: Run Preview Generation Script
 ```bash
-REPORT: "🚀 Phase 2b: Instantiating prototypes from templates..."
-
-# Verify tokens.css files exist (should be created in Phase 1.6)
-FOR style_id IN range(1, style_variants + 1):
-    tokens_css_path = "{base_path}/style-consolidation/style-${style_id}/tokens.css"
-    VERIFY: exists(tokens_css_path), f"tokens.css missing for style-{style_id}. Phase 1.6 may have failed."
-
-REPORT: "   ✓ Verified {style_variants} tokens.css files exist"
-
-# Use ui-instantiate-prototypes.sh script for instantiation
-prototypes_dir = "{base_path}/prototypes"
-targets_csv = ','.join(target_list)
-session_id = --session provided ? {session_id} : "standalone"
-
-# Execute instantiation script with target type
-Bash(~/.claude/scripts/ui-instantiate-prototypes.sh "{prototypes_dir}" --session-id "{session_id}" --mode "{target_type}")
-
-# The script auto-detects: Targets, Style variants, Layout variants
-# The script generates:
-# 1. S × L × T HTML prototypes with CSS links
-# 2. Implementation notes for each prototype
-# 3. compare.html (interactive matrix)
-# 4. index.html (navigation page)
-# 5. PREVIEW.md (documentation)
-
-REPORT: "✅ Phase 2b complete: Instantiated {style_variants * layout_variants * len(target_list)} final prototypes"
-REPORT: "   Mode: {target_type} | Performance: {style_variants}× faster than original approach"
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
 ```
 
-### Phase 3: Verify Preview Files
+**Script generates**:
+- `compare.html` (interactive matrix)
+- `index.html` (navigation)
+- `PREVIEW.md` (instructions)
 
+### Step 2: Verify Preview Files
 ```bash
-REPORT: "🔍 Phase 3: Verifying preview files..."
-
-expected_files = ["{base_path}/prototypes/compare.html", "{base_path}/prototypes/index.html", "{base_path}/prototypes/PREVIEW.md"]
-
-all_present = true
-FOR file_path IN expected_files:
-    IF exists(file_path): REPORT: "   ✓ Found: {basename(file_path)}"
-    ELSE: REPORT: "   ✗ Missing: {basename(file_path)}"; all_present = false
-
-IF all_present: REPORT: "✅ Phase 3 complete: All preview files verified"
-ELSE: WARN: "⚠️ Some preview files missing - script may have failed"
-
-# Optional: Generate fallback design-tokens.css for reference
-fallback_css_path = "{base_path}/prototypes/design-tokens.css"
-IF NOT exists(fallback_css_path):
-    Write(fallback_css_path, "/* Auto-generated fallback CSS custom properties */\n/* See style-consolidation/style-{n}/tokens.css for actual values */")
-    REPORT: "   ✓ Generated fallback design-tokens.css"
+bash(ls {base_path}/prototypes/compare.html {base_path}/prototypes/index.html {base_path}/prototypes/PREVIEW.md)
 ```
 
-### Phase 3.5: Cross-Target Consistency Validation
+**Output**: 3 preview files
 
-**Condition**: Only executes if `len(target_list) > 1 AND target_type == "page"`
-
-```bash
-# Skip if single target or component mode
-IF len(target_list) <= 1 OR target_type == "component": SKIP to Phase 4
-
-# For multi-page workflows, validate cross-page consistency → @ui-design-agent
-FOR style_id IN range(1, style_variants + 1):
-    FOR layout_id IN range(1, layout_variants + 1):
-        Task(@ui-design-agent): "
-          [CROSS_PAGE_CONSISTENCY_VALIDATION]
-
-          STYLE: {style_id} | LAYOUT: {layout_id} | TARGETS: {target_list} | TYPE: {target_type}
-          BASE_PATH: {base_path}
-
-          ## Input
-          {base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html/css (all targets)
-
-          ## Validate
-          1. Shared components (header/nav/footer)
-          2. Token usage (no hardcoded values)
-          3. Accessibility (ARIA, headings, landmarks)
-          4. Layout strategy consistency
-
-          ## Output
-          Write({base_path}/prototypes/consistency-report-s{style_id}-l{layout_id}.md, validation_report)
-
-          Focus on shared elements. Page-specific variations acceptable.
-        "
-
-# Aggregate consistency reports
-Write({base_path}/prototypes/CONSISTENCY_SUMMARY.md):
-# Multi-{target_type.capitalize()} Consistency Summary
-
-## Validated Combinations
-- Style Variants: {style_variants} | Layout Variants: {layout_variants}
-- Total Reports: {style_variants * layout_variants}
-
-## Report Files
-{FOR s, l: - [Style {s} Layout {l}](./consistency-report-s{s}-l{l}.md)}
-
-Run `/workflow:ui-design:update` once all issues are resolved.
-```
-
-### Phase 4: Completion
+## Completion
 
+### Todo Update
 ```javascript
 TodoWrite({todos: [
-  {content: "Resolve paths and load design systems", status: "completed", activeForm: "Loading design systems"},
-  {content: `Plan ${target_list.length}×${layout_variants} target-specific layouts`, status: "completed", activeForm: "Planning layouts"},
-  {content: `Convert ${style_variants} design token files to CSS`, status: "completed", activeForm: "Converting tokens to CSS"},
-  {content: "Extract CSS variable names from tokens.css", status: "completed", activeForm: "Extracting variable names"},
-  {content: `Generate ${layout_variants}×${target_list.length} layout templates (agent reads tokens.css)`, status: "completed", activeForm: "Generating templates"},
-  {content: `Instantiate ${style_variants}×${layout_variants}×${target_list.length} prototypes using script`, status: "completed", activeForm: "Running script"},
-  {content: "Verify preview files generation", status: "completed", activeForm: "Verifying files"}
+  {content: "Setup and validation", status: "completed", activeForm: "Loading design systems"},
+  {content: "Load layout templates", status: "completed", activeForm: "Reading layout templates"},
+  {content: "Assembly (agent)", status: "completed", activeForm: "Assembling prototypes"},
+  {content: "Verify files", status: "completed", activeForm: "Validating output"},
+  {content: "Generate previews", status: "completed", activeForm: "Creating preview files"}
 ]});
 ```
 
-**Completion Message**:
+### Output Message
 ```
-✅ Optimized Matrix UI generation complete!
+✅ UI prototype assembly complete!
 
 Configuration:
 - Style Variants: {style_variants}
-- Layout Variants: {layout_variants} (target-specific planning)
-- Target Type: {target_type_icon} {target_type}
-- Targets: {target_list}
-- Total Prototypes: {style_variants * layout_variants * len(target_list)}
-- Layout Plans: {len(target_list) × layout_variants} target-specific JSON files generated
+- Layout Variants: {layout_variants} (from layout-templates.json)
+- Device Type: {device_type}
+- Targets: {targets}
+- Total Prototypes: {S × L × T}
 
-Performance Metrics:
-- Layout Templates Generated: {layout_variants * len(target_list)} (Agent tasks)
-- Prototypes Instantiated: {style_variants * layout_variants * len(target_list)} (script-based)
-- Preview Files: compare.html, index.html, PREVIEW.md (auto-generated)
-- Speed Improvement: {style_variants}× faster than previous approach
-- Resource Efficiency: {100 * (1 - 1/style_variants)}% reduction in Agent calls
-- Script: ui-instantiate-prototypes.sh v3.0 with auto-detection
+Assembly Process:
+- Pure assembly: Combined pre-extracted layouts + design tokens
+- No design decisions: All structure and style pre-defined
+- Assembly tasks: T×S×L = {T}×{S}×{L} = {T×S×L} combinations
 
-Generated Structure:
-📂 {base_path}/prototypes/
+Quality:
+- Structure: From layout-extract (DOM, CSS layout rules)
+- Style: From consolidate (design tokens)
+- CSS: Token values directly applied (var() replaced)
+- Device-optimized: Layouts match device_type from templates
+
+Generated Files:
+{base_path}/prototypes/
 ├── _templates/
-│   ├── {target}-layout-{l}.json ({len(target_list) × layout_variants} layout plans)
-│   ├── {target}-layout-{l}.html ({layout_variants * len(target_list)} HTML templates)
-│   └── {target}-layout-{l}.css ({layout_variants * len(target_list)} CSS templates)
-├── {target}-style-{s}-layout-{l}.html ({style_variants * layout_variants * len(target_list)} final prototypes)
-├── {target}-style-{s}-layout-{l}-notes.md
-├── compare.html (interactive matrix visualization)
-└── index.html (quick navigation)
+│   └── layout-templates.json (input, pre-extracted)
+├── {target}-style-{s}-layout-{l}.html ({S×L×T} prototypes)
+├── {target}-style-{s}-layout-{l}.css
+├── compare.html (interactive matrix)
+├── index.html (navigation)
+└── PREVIEW.md (instructions)
 
-🌐 Interactive Preview:
-1. Matrix View: Open compare.html (recommended)
-2. Quick Index: Open index.html
-3. Instructions: See PREVIEW.md
+Preview:
+1. Open compare.html (recommended)
+2. Open index.html
+3. Read PREVIEW.md
 
-{IF target_type == "component": Note: Components use complete HTML5 documents with isolated body content for better comparison and styling.}
+Next: /workflow:ui-design:update
+```
 
-Next: /workflow:ui-design:update {--session flag if applicable}
+## Simple Bash Commands
 
-Note: When called from /workflow:ui-design:auto, design-update is triggered automatically.
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
 
-**Dynamic Values**: target_type_icon: "📄" for page, "🧩" for component
+# Count style variants
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+```
+
+### Validation Commands
+```bash
+# Check layout templates exist
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+
+# Check design tokens exist
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "valid")
+
+# Count generated files
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+
+# Verify preview
+bash(test -f {base_path}/prototypes/compare.html && echo "exists")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/prototypes)
+
+# Run preview script
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
 ```
 
 ## Output Structure
 
 ```
-{base_path}/prototypes/
-├── _templates/                            # Target-specific layout plans and templates
-│   ├── {target}-layout-1.json            # Layout plan JSON (target-specific)
-│   ├── {target}-layout-1.html            # Style-agnostic HTML structure
-│   ├── {target}-layout-1.css             # Structural CSS with var() references
-│   └── ... (T × L layout plans + templates)
-├── compare.html                           # Interactive matrix visualization
-├── index.html                             # Simple navigation page
-├── PREVIEW.md                             # Preview instructions
-├── design-tokens.css                      # CSS custom properties fallback
-├── {target}-style-{s}-layout-{l}.html    # Final prototypes (copied from templates)
-├── {target}-style-{s}-layout-{l}-notes.md  # Implementation notes
-└── ... (S × L × T total final files)
-
-{base_path}/style-consolidation/
-├── style-1/ (design-tokens.json, tokens.css, style-guide.md)
-├── style-2/ (same structure)
-└── ...
+{base_path}/
+├── layout-extraction/
+│   └── layout-templates.json      # Input (from layout-extract)
+├── style-consolidation/
+│   └── style-{s}/
+│       ├── design-tokens.json     # Input (from consolidate)
+│       └── style-guide.md
+└── prototypes/
+    ├── {target}-style-{s}-layout-{l}.html  # Assembled prototypes
+    ├── {target}-style-{s}-layout-{l}.css
+    ├── compare.html
+    ├── index.html
+    └── PREVIEW.md
 ```
 
 ## Error Handling
 
-### Pre-execution Checks
-- **No design systems found**: Error - Run `/workflow:ui-design:consolidate` first
-- **Invalid target names**: Extract from synthesis-specification.md or error with validation message
-- **Missing templates directory**: Auto-created in Phase 1.5
-- **Unsupported target type**: Error if target_type not in ["page", "component"]
-- **Layout planning failures**: Check Phase 1.5 agent outputs for errors
+### Common Errors
+```
+ERROR: Layout templates not found
+→ Run /workflow:ui-design:layout-extract first
 
-### Phase-Specific Errors
-- **Agent execution errors (Phase 2a)**: Report details, suggest retry with specific phase
-- **Token conversion errors (Phase 2b)**: Check design-tokens.json format, validate JSON schema
-- **Script execution errors (Phase 2b)**: Check script exists, permissions, output for specific errors
-- **Preview generation errors (Phase 3)**: Check script completed, verify template exists, review Phase 2b output
+ERROR: Design tokens not found
+→ Run /workflow:ui-design:consolidate first
+
+ERROR: Agent assembly failed
+→ Check inputs exist, validate JSON structure
+
+ERROR: Script permission denied
+→ chmod +x ~/.claude/scripts/ui-generate-preview.sh
+```
 
 ### Recovery Strategies
-- **Partial failure**: Script reports generated vs failed counts - review logs
-- **Missing templates**: Indicates Phase 2a issue - regenerate templates
-- **Auto-detection failures**: Use manual mode with explicit parameters
-- **Permission errors**: Run `chmod +x ~/.claude/scripts/ui-instantiate-prototypes.sh`
+- **Partial success**: Keep successful assembly combinations
+- **Invalid template structure**: Validate layout-templates.json
+- **Invalid tokens**: Validate design-tokens.json structure
 
-## Quality Checks
+## Quality Checklist
 
-After generation, ensure:
-- [ ] All CSS values reference design token custom properties
-- [ ] No hardcoded colors, spacing, or typography
-- [ ] Semantic HTML structure with proper element hierarchy
-- [ ] ARIA attributes present for accessibility
-- [ ] Responsive design implemented with mobile-first approach
-- [ ] File naming follows `{target}-style-{s}-layout-{l}` convention
-- [ ] compare.html loads correctly with all prototypes
-- [ ] Template files are reusable and style-agnostic
-- [ ] All templates use complete HTML5 documents with appropriate body content (full structure for pages, isolated component for components)
+- [ ] CSS uses direct token values (var() replaced)
+- [ ] HTML structure matches layout template exactly
+- [ ] Semantic HTML5 structure preserved
+- [ ] ARIA attributes from template present
+- [ ] Device-specific optimizations applied
+- [ ] All token references resolved
+- [ ] compare.html works
 
 ## Key Features
 
-1. **Target-Specific Layout Planning** 🆕 - Each target gets custom-designed layouts; Agent researches modern patterns using MCP tools; Layout plans saved as structured JSON
-2. **Unified Target Generation** - Supports both pages (full layouts) and components (isolated elements); Backward compatible with legacy `--pages` parameter
-3. **Optimized Template-Based Architecture** - Generates `L × T` reusable templates plus `L × T` layout plans; **`S` times faster**
-4. **Three-Layer Generation Strategy** - Layer 1: Layout planning (target-specific); Layer 2: Template generation (implements plans); Layer 3: Fast instantiation; Agent autonomously uses MCP tools
-5. **Script-Based Instantiation (v3.0)** - Uses `ui-instantiate-prototypes.sh` for efficient file operations; Auto-detection; Robust error handling; Integrated preview generation; Supports both page and component modes
-6. **Consistent Cross-Style Layouts** - Same layout structure applied uniformly; Easier to compare styles; Simplified maintenance
-7. **Dynamic Style Injection** - CSS custom properties enable runtime style switching; Each style variant has its own `tokens.css` file
-8. **Interactive Visualization** - Full-featured compare.html; Matrix grid view with synchronized scrolling; Enhanced index.html with statistics; Comprehensive PREVIEW.md
-9. **Production-Ready Output** - Semantic HTML5 and ARIA attributes (WCAG 2.2); Mobile-first responsive design; Token-driven styling; Implementation notes
+- **Pure Assembly**: No design decisions, only combination
+- **Separation of Concerns**: Layout (structure) + Style (tokens) kept separate until final assembly
+- **Token Resolution**: var() placeholders replaced with actual values
+- **Pre-validated**: Inputs already validated by extract/consolidate
+- **Efficient**: Simple assembly vs complex generation
+- **Production-Ready**: Semantic, accessible, token-driven
 
-## Integration Points
+## Integration
 
-- **Input**: Per-style `design-tokens.json` from `/workflow:ui-design:consolidate`; `--targets` and `--layout-variants` parameters; Optional: `synthesis-specification.md` for target requirements; Target type specification
-- **Output**: Target-specific `layout-{n}.json` files; Matrix HTML/CSS prototypes for `/workflow:ui-design:update`
-- **Template**: `~/.claude/workflows/_template-compare-matrix.html` (global)
-- **Auto Integration**: Automatically triggered by `/workflow:ui-design:explore-auto` workflow
-- **Key Change**: Layout planning moved from consolidate to generate phase; Each target gets custom-designed layouts
-- **Backward Compatibility**: Legacy `--pages` parameter continues to work
+**Prerequisites**:
+- `/workflow:ui-design:style-extract` → `style-cards.json`
+- `/workflow:ui-design:consolidate` → `design-tokens.json`
+- `/workflow:ui-design:layout-extract` → `layout-templates.json`
+
+**Input**: `layout-templates.json` + `design-tokens.json`
+**Output**: S×L×T prototypes for `/workflow:ui-design:update`
+**Called by**: `/workflow:ui-design:explore-auto`, `/workflow:ui-design:imitate-auto`

.claude/commands/workflow/ui-design/layout-extract.md

@@ -0,0 +1,371 @@
+---
+name: layout-extract
+description: Extract structural layout information from reference images, URLs, or text prompts
+usage: /workflow:ui-design:layout-extract [--base-path <path>] [--session <id>] [--images "<glob>"] [--urls "<list>"] [--prompt "<desc>"] [--targets "<list>"] [--mode <imitate|explore>] [--variants <count>] [--device-type <desktop|mobile|tablet|responsive>]
+examples:
+  - /workflow:ui-design:layout-extract --urls "home:https://linear.app" --mode imitate --targets "home"
+  - /workflow:ui-design:layout-extract --images "refs/*.png" --mode explore --variants 3 --targets "dashboard"
+  - /workflow:ui-design:layout-extract --prompt "Two-column blog with sticky sidebar" --mode explore --variants 2 --targets "blog-post"
+  - /workflow:ui-design:layout-extract --session WFS-auth --urls "login:https://clerk.dev" --device-type mobile --targets "login"
+allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), Bash(*), Task(ui-design-agent), mcp__exa__web_search_exa(*)
+---
+
+# Layout Extraction Command
+
+## Overview
+Extract structural layout information from reference images, URLs, or text prompts using AI analysis. This command separates the "scaffolding" (HTML structure and CSS layout) from the "paint" (visual tokens handled by `style-extract`).
+
+**Strategy**: AI-Driven Structural Analysis
+- **Agent-Powered**: Uses `ui-design-agent` for deep structural analysis
+- **Dual-Mode**:
+  - `imitate`: High-fidelity replication of single layout structure
+  - `explore`: Multiple structurally distinct layout variations
+- **Single Output**: `layout-templates.json` with DOM structure, component hierarchy, and CSS layout rules
+- **Device-Aware**: Optimized for specific device types (desktop, mobile, tablet, responsive)
+- **Token-Based**: CSS uses `var()` placeholders for spacing and breakpoints
+
+## Phase 0: Setup & Input Validation
+
+### Step 1: Detect Input, Mode & Targets
+```bash
+# Detect input source
+# Priority: --urls + --images → hybrid | --urls → url | --images → image | --prompt → text
+
+# Determine extraction mode
+extraction_mode = --mode OR "imitate"  # "imitate" or "explore"
+
+# Set variants count based on mode
+IF extraction_mode == "imitate":
+    variants_count = 1  # Force single variant (ignore --variants)
+ELSE IF extraction_mode == "explore":
+    variants_count = --variants OR 3  # Default to 3
+    VALIDATE: 1 <= variants_count <= 5
+
+# Resolve targets
+# Priority: --targets → prompt analysis → default ["page"]
+targets = --targets OR extract_from_prompt(--prompt) OR ["page"]
+
+# Resolve device type
+device_type = --device-type OR "responsive"  # desktop|mobile|tablet|responsive
+
+# Determine base path
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
+```
+
+### Step 2: Load Inputs & Create Directories
+```bash
+# For image mode
+bash(ls {images_pattern})  # Expand glob pattern
+Read({image_path})  # Load each image
+
+# For URL mode
+# Parse URL list format: "target:url,target:url"
+# Validate URLs are accessible
+
+# For text mode
+# Validate --prompt is non-empty
+
+# Create output directory
+bash(mkdir -p {base_path}/layout-extraction)
+```
+
+### Step 3: Memory Check (Skip if Already Done)
+```bash
+# Check if layouts already extracted
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+```
+
+**If exists**: Skip to completion message
+
+**Output**: `input_mode`, `base_path`, `extraction_mode`, `variants_count`, `targets[]`, `device_type`, loaded inputs
+
+## Phase 1: Layout Research (Explore Mode Only)
+
+### Step 1: Check Extraction Mode
+```bash
+# extraction_mode == "imitate" → skip this phase
+# extraction_mode == "explore" → execute this phase
+```
+
+**If imitate mode**: Skip to Phase 2
+
+### Step 2: Gather Layout Inspiration (Explore Mode)
+```bash
+bash(mkdir -p {base_path}/layout-extraction/_inspirations)
+
+# For each target: Research via MCP
+# mcp__exa__web_search_exa(query="{target} layout patterns {device_type}", numResults=5)
+
+# Write inspiration file
+Write({base_path}/layout-extraction/_inspirations/{target}-layout-ideas.txt, inspiration_content)
+```
+
+**Output**: Inspiration text files for each target (explore mode only)
+
+## Phase 2: Layout Analysis & Synthesis (Agent)
+
+**Executor**: `Task(ui-design-agent)`
+
+### Step 1: Launch Agent Task
+```javascript
+Task(ui-design-agent): `
+  [LAYOUT_EXTRACTION_TASK]
+  Analyze references and extract structural layout templates.
+  Focus ONLY on structure and layout. DO NOT concern with visual style (colors, fonts, etc.).
+
+  REFERENCES:
+  - Input: {reference_material}  // Images, URLs, or prompt
+  - Mode: {extraction_mode}  // 'imitate' or 'explore'
+  - Targets: {targets}  // List of page/component names
+  - Variants per Target: {variants_count}
+  - Device Type: {device_type}
+  ${exploration_mode ? "- Layout Inspiration: Read('" + base_path + "/layout-extraction/_inspirations/{target}-layout-ideas.txt')" : ""}
+
+  ## Analysis & Generation
+  For EACH target in {targets}:
+    For EACH variant (1 to {variants_count}):
+      1. **Analyze Structure**: Deconstruct reference to understand layout, hierarchy, responsiveness
+      2. **Define Philosophy**: Short description (e.g., "Asymmetrical grid with overlapping content areas")
+      3. **Generate DOM Structure**: JSON object representing semantic HTML5 structure
+         - Semantic tags: <header>, <nav>, <main>, <aside>, <section>, <footer>
+         - ARIA roles and accessibility attributes
+         - Device-specific structure:
+           * mobile: Single column, stacked sections, touch targets ≥44px
+           * desktop: Multi-column grids, hover states, larger hit areas
+           * tablet: Hybrid layouts, flexible columns
+           * responsive: Breakpoint-driven adaptive layouts (mobile-first)
+         - In 'explore' mode: Each variant structurally DISTINCT
+      4. **Define Component Hierarchy**: High-level array of main layout regions
+         Example: ["header", "main-content", "sidebar", "footer"]
+      5. **Generate CSS Layout Rules**:
+         - Focus ONLY on layout (Grid, Flexbox, position, alignment, gap, etc.)
+         - Use CSS Custom Properties for spacing/breakpoints: var(--spacing-4), var(--breakpoint-md)
+         - Device-specific styles (mobile-first @media for responsive)
+         - NO colors, NO fonts, NO shadows - layout structure only
+
+  ## Output Format
+  Return JSON object with layout_templates array.
+  Each template must include:
+  - target (string)
+  - variant_id (string, e.g., "layout-1")
+  - device_type (string)
+  - design_philosophy (string)
+  - dom_structure (JSON object)
+  - component_hierarchy (array of strings)
+  - css_layout_rules (string)
+
+  ## Notes
+  - Structure only, no visual styling
+  - Use var() for all spacing/sizing
+  - Layouts must be structurally distinct in explore mode
+  - Write complete layout-templates.json
+`
+```
+
+**Output**: Agent returns JSON with `layout_templates` array
+
+### Step 2: Write Output File
+```bash
+# Take JSON output from agent
+bash(echo '{agent_json_output}' > {base_path}/layout-extraction/layout-templates.json)
+
+# Verify output
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+bash(cat {base_path}/layout-extraction/layout-templates.json | grep -q "layout_templates" && echo "valid")
+```
+
+**Output**: `layout-templates.json` created and verified
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and input validation", status: "completed", activeForm: "Validating inputs"},
+  {content: "Layout research (explore mode)", status: "completed", activeForm: "Researching layout patterns"},
+  {content: "Layout analysis and synthesis (agent)", status: "completed", activeForm: "Generating layout templates"},
+  {content: "Write layout-templates.json", status: "completed", activeForm: "Saving templates"}
+]});
+```
+
+### Output Message
+```
+✅ Layout extraction complete!
+
+Configuration:
+- Session: {session_id}
+- Extraction Mode: {extraction_mode} (imitate/explore)
+- Device Type: {device_type}
+- Targets: {targets}
+- Variants per Target: {variants_count}
+- Total Templates: {targets.length × variants_count}
+
+{IF extraction_mode == "explore":
+Layout Research:
+- {targets.length} inspiration files generated
+- Pattern search focused on {device_type} layouts
+}
+
+Generated Templates:
+{FOR each template: - Target: {template.target} | Variant: {template.variant_id} | Philosophy: {template.design_philosophy}}
+
+Output File:
+- {base_path}/layout-extraction/layout-templates.json
+
+Next: /workflow:ui-design:generate will combine these structural templates with style systems to produce final prototypes.
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Create output directories
+bash(mkdir -p {base_path}/layout-extraction)
+bash(mkdir -p {base_path}/layout-extraction/_inspirations)  # explore mode only
+```
+
+### Validation Commands
+```bash
+# Check if already extracted
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+
+# Validate JSON structure
+bash(cat layout-templates.json | grep -q "layout_templates" && echo "valid")
+
+# Count templates
+bash(cat layout-templates.json | grep -c "\"target\":")
+```
+
+### File Operations
+```bash
+# Load image references
+bash(ls {images_pattern})
+Read({image_path})
+
+# Write inspiration files (explore mode)
+Write({base_path}/layout-extraction/_inspirations/{target}-layout-ideas.txt, content)
+
+# Write layout templates
+bash(echo '{json}' > {base_path}/layout-extraction/layout-templates.json)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── layout-extraction/
+    ├── layout-templates.json         # Structural layout templates
+    ├── layout-space-analysis.json    # Layout directions (explore mode only)
+    └── _inspirations/                 # Explore mode only
+        └── {target}-layout-ideas.txt  # Layout inspiration research
+```
+
+## layout-templates.json Format
+
+```json
+{
+  "extraction_metadata": {
+    "session_id": "...",
+    "input_mode": "image|url|prompt|hybrid",
+    "extraction_mode": "imitate|explore",
+    "device_type": "desktop|mobile|tablet|responsive",
+    "timestamp": "...",
+    "variants_count": 3,
+    "targets": ["home", "dashboard"]
+  },
+  "layout_templates": [
+    {
+      "target": "home",
+      "variant_id": "layout-1",
+      "device_type": "responsive",
+      "design_philosophy": "Responsive 3-column holy grail layout with fixed header and footer",
+      "dom_structure": {
+        "tag": "body",
+        "children": [
+          {
+            "tag": "header",
+            "attributes": {"class": "layout-header"},
+            "children": [{"tag": "nav"}]
+          },
+          {
+            "tag": "div",
+            "attributes": {"class": "layout-main-wrapper"},
+            "children": [
+              {"tag": "main", "attributes": {"class": "layout-main-content"}},
+              {"tag": "aside", "attributes": {"class": "layout-sidebar-left"}},
+              {"tag": "aside", "attributes": {"class": "layout-sidebar-right"}}
+            ]
+          },
+          {"tag": "footer", "attributes": {"class": "layout-footer"}}
+        ]
+      },
+      "component_hierarchy": [
+        "header",
+        "main-content",
+        "sidebar-left",
+        "sidebar-right",
+        "footer"
+      ],
+      "css_layout_rules": ".layout-main-wrapper { display: grid; grid-template-columns: 1fr 3fr 1fr; gap: var(--spacing-6); } @media (max-width: var(--breakpoint-md)) { .layout-main-wrapper { grid-template-columns: 1fr; } }"
+    }
+  ]
+}
+```
+
+**Requirements**: Token-based CSS (var()), semantic HTML5, device-specific structure, accessibility attributes
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No inputs provided
+→ Provide --images, --urls, or --prompt
+
+ERROR: Invalid target name
+→ Use lowercase, alphanumeric, hyphens only
+
+ERROR: Agent task failed
+→ Check agent output, retry with simplified prompt
+
+ERROR: MCP search failed (explore mode)
+→ Check network, retry
+```
+
+### Recovery Strategies
+- **Partial success**: Keep successfully extracted templates
+- **Invalid JSON**: Retry with stricter format requirements
+- **Missing inspiration**: Works without (less informed exploration)
+
+## Key Features
+
+- **Separation of Concerns** - Decouples layout (structure) from style (visuals)
+- **Structural Exploration** - Explore mode enables A/B testing of different layouts
+- **Token-Based Layout** - CSS uses `var()` placeholders for instant design system adaptation
+- **Device-Specific** - Tailored structures for different screen sizes
+- **Foundation for Assembly** - Provides structural blueprint for refactored `generate` command
+- **Agent-Powered** - Deep structural analysis with AI
+
+## Integration
+
+**Workflow Position**: Between style extraction and prototype generation
+
+**New Workflow**:
+1. `/workflow:ui-design:style-extract` → `style-cards.json` (Visual tokens)
+2. `/workflow:ui-design:consolidate` → `design-tokens.json` (Final visual system)
+3. `/workflow:ui-design:layout-extract` → `layout-templates.json` (Structural templates)
+4. `/workflow:ui-design:generate` (Refactored as assembler):
+   - **Reads**: `design-tokens.json` + `layout-templates.json`
+   - **Action**: For each style × layout combination:
+     1. Build HTML from `dom_structure`
+     2. Create layout CSS from `css_layout_rules`
+     3. Link design tokens CSS
+     4. Inject placeholder content
+   - **Output**: Complete token-driven HTML/CSS prototypes
+
+**Input**: Reference images, URLs, or text prompts
+**Output**: `layout-templates.json` for `/workflow:ui-design:generate`
+**Next**: `/workflow:ui-design:generate --session {session_id}`

.claude/commands/workflow/ui-design/style-extract.md

@@ -0,0 +1,277 @@
+---
+name: style-extract
+description: Extract design style from reference images or text prompts using Claude's analysis
+usage: /workflow:ui-design:style-extract [--base-path <path>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--mode <imitate|explore>] [--variants <count>]
+examples:
+  - /workflow:ui-design:style-extract --images "design-refs/*.png" --mode explore --variants 3
+  - /workflow:ui-design:style-extract --prompt "Modern minimalist blog, dark theme" --mode explore --variants 3
+  - /workflow:ui-design:style-extract --session WFS-auth --images "refs/*.png" --prompt "Linear.app style" --mode imitate
+  - /workflow:ui-design:style-extract --base-path ".workflow/WFS-auth/design-run-20250109-143022" --images "refs/*.png" --mode explore --variants 3
+  - /workflow:ui-design:style-extract --prompt "Bold vibrant" --mode imitate  # High-fidelity single style
+allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*)
+---
+
+# Style Extraction Command
+
+## Overview
+Extract design style from reference images or text prompts using Claude's built-in analysis. Generates `style-cards.json` with multiple design variants containing token proposals for consolidation.
+
+**Strategy**: AI-Driven Design Space Exploration
+- **Claude-Native**: 100% Claude analysis, no external tools
+- **Single Output**: `style-cards.json` with embedded token proposals
+- **Flexible Input**: Images, text prompts, or both (hybrid mode)
+- **Maximum Contrast**: AI generates maximally divergent design directions
+
+## Phase 0: Setup & Input Validation
+
+### Step 1: Detect Input Mode, Extraction Mode & Base Path
+```bash
+# Detect input source
+# Priority: --images + --prompt → hybrid | --images → image | --prompt → text
+
+# Determine extraction mode
+# Priority: --mode parameter → default "imitate"
+extraction_mode = --mode OR "imitate"  # "imitate" or "explore"
+
+# Set variants count based on mode
+IF extraction_mode == "imitate":
+    variants_count = 1  # Force single variant for imitate mode (ignore --variants)
+ELSE IF extraction_mode == "explore":
+    variants_count = --variants OR 3  # Default to 3 for explore mode
+    VALIDATE: 1 <= variants_count <= 5
+
+# Determine base path
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
+```
+
+### Step 2: Load Inputs
+```bash
+# For image mode
+bash(ls {images_pattern})  # Expand glob pattern
+Read({image_path})  # Load each image
+
+# For text mode
+# Validate --prompt is non-empty
+
+# Create output directory
+bash(mkdir -p {base_path}/style-extraction/)
+```
+
+### Step 3: Memory Check (Skip if Already Done)
+```bash
+# Check if already extracted
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "exists")
+```
+
+**If exists**: Skip to completion message
+
+**Output**: `input_mode`, `base_path`, `extraction_mode`, `variants_count`, `loaded_images[]` or `prompt_guidance`
+
+## Phase 1: Design Space Analysis (Explore Mode Only)
+
+### Step 1: Check Extraction Mode
+```bash
+# Check extraction mode
+# extraction_mode == "imitate" → skip this phase
+# extraction_mode == "explore" → execute this phase
+```
+
+**If imitate mode**: Skip to Phase 2
+
+### Step 2: Load Project Context (Explore Mode)
+```bash
+# Load brainstorming context if available
+bash(test -f {base_path}/.brainstorming/synthesis-specification.md && cat it)
+```
+
+### Step 3: Generate Divergent Directions (Claude Native)
+AI analyzes requirements and generates `variants_count` maximally contrasting design directions:
+
+**Input**: User prompt + project context + image count
+**Analysis**: 6D attribute space (color saturation, visual weight, formality, organic/geometric, innovation, density)
+**Output**: JSON with divergent_directions, each having:
+- philosophy_name (2-3 words)
+- design_attributes (specific scores)
+- search_keywords (3-5 keywords)
+- anti_keywords (2-3 keywords)
+- rationale (contrast explanation)
+
+### Step 4: Write Design Space Analysis
+```bash
+bash(echo '{design_space_analysis}' > {base_path}/style-extraction/design-space-analysis.json)
+
+# Verify output
+bash(test -f design-space-analysis.json && echo "saved")
+```
+
+**Output**: `design-space-analysis.json` for consolidation phase
+
+## Phase 2: Style Synthesis & File Write
+
+### Step 1: Claude Native Analysis
+AI generates `variants_count` design style proposals:
+
+**Input**:
+- Input mode (image/text/hybrid)
+- Visual references or text guidance
+- Design space analysis (explore mode only)
+- Variant-specific directions (explore mode only)
+
+**Analysis Rules**:
+- **Explore mode**: Each variant follows pre-defined philosophy and attributes, maintains maximum contrast
+- **Imitate mode**: High-fidelity replication of reference design
+- OKLCH color format
+- Complete token proposals (colors, typography, spacing, border_radius, shadows, breakpoints)
+- WCAG AA accessibility (4.5:1 text, 3:1 UI)
+
+**Output Format**: `style-cards.json` with:
+- extraction_metadata (session_id, input_mode, extraction_mode, timestamp, variants_count)
+- style_cards[] (id, name, description, design_philosophy, preview, proposed_tokens)
+
+### Step 2: Write Style Cards
+```bash
+bash(echo '{style_cards_json}' > {base_path}/style-extraction/style-cards.json)
+```
+
+**Output**: `style-cards.json` with `variants_count` complete variants
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and input validation", status: "completed", activeForm: "Validating inputs"},
+  {content: "Design space analysis (explore mode)", status: "completed", activeForm: "Analyzing design space"},
+  {content: "Style synthesis and file write", status: "completed", activeForm: "Generating style cards"}
+]});
+```
+
+### Output Message
+```
+✅ Style extraction complete!
+
+Configuration:
+- Session: {session_id}
+- Extraction Mode: {extraction_mode} (imitate/explore)
+- Input Mode: {input_mode} (image/text/hybrid)
+- Variants: {variants_count}
+
+{IF extraction_mode == "explore":
+Design Space Analysis:
+- {variants_count} maximally contrasting design directions
+- Min contrast distance: {design_space_analysis.contrast_verification.min_pairwise_distance}
+}
+
+Generated Variants:
+{FOR each card: - {card.name} - {card.design_philosophy}}
+
+Output Files:
+- {base_path}/style-extraction/style-cards.json
+{IF extraction_mode == "explore": - {base_path}/style-extraction/design-space-analysis.json}
+
+Next: /workflow:ui-design:consolidate --session {session_id} --variants {variants_count}
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Expand image pattern
+bash(ls {images_pattern})
+
+# Create output directory
+bash(mkdir -p {base_path}/style-extraction/)
+```
+
+### Validation Commands
+```bash
+# Check if already extracted
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "exists")
+
+# Count variants
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
+
+# Validate JSON
+bash(cat style-cards.json | grep -q "extraction_metadata" && echo "valid")
+```
+
+### File Operations
+```bash
+# Load brainstorming context
+bash(test -f .brainstorming/synthesis-specification.md && cat it)
+
+# Write output
+bash(echo '{json}' > {base_path}/style-extraction/style-cards.json)
+
+# Verify output
+bash(test -f design-space-analysis.json && echo "saved")
+```
+
+## Output Structure
+
+```
+{base_path}/style-extraction/
+├── style-cards.json              # Complete style variants with token proposals
+└── design-space-analysis.json    # Design directions (explore mode only)
+```
+
+## style-cards.json Format
+
+```json
+{
+  "extraction_metadata": {"session_id": "...", "input_mode": "image|text|hybrid", "extraction_mode": "imitate|explore", "timestamp": "...", "variants_count": N},
+  "style_cards": [
+    {
+      "id": "variant-1", "name": "Style Name", "description": "...",
+      "design_philosophy": "Core principles",
+      "preview": {"primary": "oklch(...)", "background": "oklch(...)", "font_heading": "...", "border_radius": "..."},
+      "proposed_tokens": {
+        "colors": {"brand": {...}, "surface": {...}, "semantic": {...}, "text": {...}, "border": {...}},
+        "typography": {"font_family": {...}, "font_size": {...}, "font_weight": {...}, "line_height": {...}, "letter_spacing": {...}},
+        "spacing": {"0": "0", ..., "24": "6rem"},
+        "border_radius": {"none": "0", ..., "full": "9999px"},
+        "shadows": {"sm": "...", ..., "xl": "..."},
+        "breakpoints": {"sm": "640px", ..., "2xl": "1536px"}
+      }
+    }
+    // Repeat for all variants
+  ]
+}
+```
+
+**Requirements**: All colors in OKLCH format, complete token proposals, semantic naming
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No images found
+→ Check glob pattern
+
+ERROR: Invalid prompt
+→ Provide non-empty string
+
+ERROR: Claude JSON parsing error
+→ Retry with stricter format
+```
+
+## Key Features
+
+- **AI-Driven Design Space Exploration** - 6D attribute space analysis for maximum contrast
+- **Variant-Specific Directions** - Each variant has unique philosophy, keywords, anti-patterns
+- **Maximum Contrast Guarantee** - Variants maximally distant in attribute space
+- **Claude-Native** - No external tools, fast deterministic synthesis
+- **Flexible Input** - Images, text, or hybrid mode
+- **Production-Ready** - OKLCH colors, WCAG AA, semantic naming
+
+## Integration
+
+**Input**: Reference images or text prompts
+**Output**: `style-cards.json` for consolidation
+**Next**: `/workflow:ui-design:consolidate --session {session_id} --variants {count}`
+
+**Note**: This command only extracts visual style (colors, typography, spacing). For layout structure extraction, use `/workflow:ui-design:layout-extract`.

.claude/commands/workflow/ui-design/update.md

@@ -52,6 +52,21 @@ VALIDATE: Specified prototypes exist IF --selected-prototypes
 REPORT: "Found {count} design artifacts, {prototype_count} prototypes"
 ```
 
+### Phase 1.1: Memory Check (Skip if Already Updated)
+
+```bash
+# Check if synthesis-specification.md contains current design run reference
+synthesis_spec_path = ".workflow/WFS-{session}/.brainstorming/synthesis-specification.md"
+current_design_run = basename(latest_design)  # e.g., "design-run-20250109-143022"
+
+IF exists(synthesis_spec_path):
+    synthesis_content = Read(synthesis_spec_path)
+    IF "## UI/UX Guidelines" in synthesis_content AND current_design_run in synthesis_content:
+        REPORT: "✅ Design system references already updated (found in memory)"
+        REPORT: "   Skipping: Phase 2-5 (Load Target Artifacts, Update Synthesis, Update UI Designer Guide, Completion)"
+        EXIT 0
+```
+
 ### Phase 2: Load Target Artifacts Only
 
 **What to Load**: Only the files we need to **update**, not the design files we're referencing.

.claude/scripts/ui-generate-preview.sh

@@ -4,7 +4,7 @@
 # Purpose: Generate compare.html and index.html using template substitution
 # Template: ~/.claude/workflows/_template-compare-matrix.html
 #
-# Usage: ui-generate-preview-v2.sh <prototypes_dir> [--template <path>]
+# Usage: ui-generate-preview.sh <prototypes_dir> [--template <path>]
 #
 
 set -e

.claude/workflows/intelligent-tools-strategy.md

@@ -19,8 +19,8 @@ type: strategic-guideline
 ## ⚡ Core Framework
 
 ### Tool Overview
-- **Gemini**: Analysis, understanding, exploration & documentation
-- **Qwen**: Architecture analysis, code generation & implementation
+- **Gemini**: Analysis, understanding, exploration & documentation (primary)
+- **Qwen**: Analysis, understanding, exploration & documentation (fallback, same capabilities as Gemini)
 - **Codex**: Development, implementation & automation
 
 ### Decision Principles
@@ -32,8 +32,8 @@ type: strategic-guideline
 - **⚠️ Write operation protection** - For local codebase write/modify operations, require EXPLICIT user confirmation unless user provides clear instructions containing MODE=write or MODE=auto
 
 ### Quick Decision Rules
-1. **Exploring/Understanding?** → Start with Gemini
-2. **Architecture/Code generation?** → Start with Qwen
+1. **Exploring/Understanding?** → Start with Gemini (fallback to Qwen if needed)
+2. **Architecture/Analysis?** → Start with Gemini (fallback to Qwen if needed)
 3. **Building/Fixing?** → Start with Codex
 4. **Not sure?** → Use multiple tools in parallel
 5. **Small task?** → Still use tools - they're faster than manual work
@@ -56,15 +56,16 @@ type: strategic-guideline
 
 ### Qwen
 - **Command**: `~/.claude/scripts/qwen-wrapper`
-- **Strengths**: Architecture analysis, pattern recognition
-- **Best For**: System design analysis, architectural review
-- **Permissions**: Architecture analysis only, no automatic code generation
+- **Strengths**: Large context window, pattern recognition (same as Gemini)
+- **Best For**: Analysis, documentation generation, code exploration (fallback option when Gemini unavailable)
+- **Permissions**: Default read-only analysis, MODE=write requires explicit specification (auto-enables --approval-mode yolo)
 - **Default MODE**: `analysis` (read-only)
-- **⚠️ Write Trigger**: Explicitly prohibited from auto-calling write mode
+- **⚠️ Write Trigger**: Only when user explicitly requests "generate documentation", "modify code", or specifies MODE=write
+- **Priority**: Secondary to Gemini - use as fallback for same tasks
 
 #### MODE Options
-- `analysis` (default) - Architecture analysis only, no code generation/modification (read-only)
-- `write` - ⚠️ Code generation (requires explicit specification, disabled by default)
+- `analysis` (default) - Read-only analysis and documentation generation (same as Gemini)
+- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)
 
 ### Codex
 - **Command**: `codex --full-auto exec`
@@ -149,13 +150,13 @@ RULES: [template reference and constraints]
 
 #### Qwen Commands
 ```bash
-# Qwen Architecture Analysis (read-only, default)
+# Qwen Analysis (read-only, default) - Same as Gemini, use as fallback
 cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: [clear architecture goal]
+PURPOSE: [clear analysis goal]
 TASK: [specific analysis task]
 MODE: analysis
 CONTEXT: [file references and memory context]
-EXPECTED: [expected deliverables]
+EXPECTED: [expected output]
 RULES: [template reference and constraints]
 "
 
@@ -166,7 +167,7 @@ PURPOSE: [clear goal]
 TASK: [specific task]
 MODE: write
 CONTEXT: [file references and memory context]
-EXPECTED: [expected deliverables]
+EXPECTED: [expected output]
 RULES: [template reference and constraints]
 "
 ```
@@ -256,14 +257,13 @@ RULES: Focus on type safety and component composition
 
 | Task Type | Tool | Use Case | Template |
 |-----------|------|----------|-----------|
-| **Analysis** | Gemini | Code exploration, architecture review, patterns | `analysis/pattern.txt` |
-| **Architecture** | Qwen | System design, code generation, architectural analysis | `analysis/architecture.txt` |
-| **Code Generation** | Qwen | Implementation patterns, code scaffolding, component creation | `development/feature.txt` |
+| **Analysis** | Gemini (Qwen fallback) | Code exploration, architecture review, patterns | `analysis/pattern.txt` |
+| **Architecture** | Gemini (Qwen fallback) | System design, architectural analysis | `analysis/architecture.txt` |
+| **Documentation** | Gemini (Qwen fallback) | Code docs, API specs, guides | `analysis/quality.txt` |
 | **Development** | Codex | Feature implementation, bug fixes, testing | `development/feature.txt` |
-| **Planning** | Multiple | Task breakdown, migration planning | `planning/task-breakdown.txt` |
-| **Documentation** | Multiple | Code docs, API specs, guides | `analysis/quality.txt` |
+| **Planning** | Gemini/Qwen | Task breakdown, migration planning | `planning/task-breakdown.txt` |
 | **Security** | Codex | Vulnerability assessment, fixes | `analysis/security.txt` |
-| **Refactoring** | Multiple | Gemini for analysis, Qwen/Codex for execution | `development/refactor.txt` |
+| **Refactoring** | Multiple | Gemini/Qwen for analysis, Codex for execution | `development/refactor.txt` |
 
 ### Template System
 
@@ -302,9 +302,9 @@ tech-stacks/
 ### Workflow Integration (REQUIRED)
 When planning any coding task, **ALWAYS** integrate CLI tools:
 
-1. **Understanding Phase**: Use Gemini for analysis
-2. **Architecture Phase**: Use Qwen for design and code generation
-3. **Implementation Phase**: Use Qwen/Codex for development
+1. **Understanding Phase**: Use Gemini for analysis (Qwen as fallback)
+2. **Architecture Phase**: Use Gemini for design and analysis (Qwen as fallback)
+3. **Implementation Phase**: Use Codex for development
 4. **Quality Phase**: Use Codex for testing and validation
 
 ### Common Scenarios
@@ -333,8 +333,19 @@ RULES: Follow project documentation standards
 "
 ```
 
-#### Architecture Analysis
+#### Architecture Analysis (Qwen as Gemini fallback)
 ```bash
+# Prefer Gemini for architecture analysis
+cd src/auth && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Analyze authentication system architecture
+TASK: Review JWT-based auth system design
+MODE: analysis
+CONTEXT: @{src/auth/**/*} Existing patterns and requirements
+EXPECTED: Architecture analysis report with recommendations
+RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on security
+"
+
+# Use Qwen only if Gemini unavailable
 cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: Analyze authentication system architecture
 TASK: Review JWT-based auth system design
@@ -419,7 +430,7 @@ EXPECTED: Pattern documentation
 RULES: Focus on security best practices
 "
 
-# Qwen - Architecture analysis
+# Qwen - Analysis (fallback option, same as Gemini)
 cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: Analyze auth architecture
 TASK: Review auth system design and patterns

CHANGELOG.md

@@ -5,6 +5,366 @@ All notable changes to Claude Code Workflow (CCW) will be documented in this fil
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [4.4.0] - 2025-10-11
+
+### 🏗️ UI Design Workflow V3 - Layout/Style Separation Architecture
+
+This release introduces a fundamental architectural refactoring that separates layout structure extraction from style token extraction, enabling the `generate` command to become a pure assembler.
+
+#### Breaking Changes
+
+**Command Renaming**:
+```bash
+# ❌ Old (v4.3.0 and earlier)
+/workflow:ui-design:extract
+
+# ✅ New (v4.4.0)
+/workflow:ui-design:style-extract
+```
+
+**New Required Command**:
+- **`/workflow:ui-design:layout-extract`**: Now mandatory for workflows using `generate`
+- Layout templates must be generated before prototype assembly
+- Both `imitate-auto` and `explore-auto` now include Phase 2.5 (layout extraction)
+
+**Workflow Changes**:
+```bash
+# ❌ Old Flow (v4.3.0)
+style-extract → consolidate → generate → update
+
+# ✅ New Flow (v4.4.0)
+style-extract → consolidate → layout-extract → generate (assembler) → update
+```
+
+#### Added
+
+**New Command: `/workflow:ui-design:layout-extract`**:
+- **Purpose**: Extract structural layout information separate from visual style
+- **Features**:
+  - Agent-powered structural analysis using `ui-design-agent`
+  - Dual-mode operation: `imitate` (high-fidelity replication) / `explore` (multiple variants)
+  - Device-aware layouts: desktop, mobile, tablet, responsive
+  - Generates `layout-templates.json` with DOM structure and CSS layout rules
+  - MCP-integrated layout pattern research (explore mode only)
+  - Token-based CSS using `var()` placeholders for spacing and breakpoints
+- **Output**: `layout-extraction/layout-templates.json` with:
+  - DOM structure (semantic HTML5 with ARIA)
+  - Component hierarchy (high-level layout regions)
+  - CSS layout rules (Grid/Flexbox, no visual styling)
+  - Device-specific structures and responsive breakpoints
+
+**Enhanced Layout Extraction Architecture**:
+```json
+{
+  "layout_templates": [
+    {
+      "target": "home",
+      "variant_id": "layout-1",
+      "device_type": "responsive",
+      "design_philosophy": "3-column holy grail with fixed header",
+      "dom_structure": { /* JSON object */ },
+      "component_hierarchy": ["header", "main", "sidebar", "footer"],
+      "css_layout_rules": "/* Grid/Flexbox only, uses var() */"
+    }
+  ]
+}
+```
+
+**Device-Aware Layout Generation**:
+- **Desktop**: 1920×1080px - Multi-column grids, spacious layouts
+- **Mobile**: 375×812px - Single column, stacked sections, touch targets ≥44px
+- **Tablet**: 768×1024px - Hybrid layouts, flexible columns
+- **Responsive**: Mobile-first breakpoint-driven adaptive layouts
+
+**MCP Integration (Explore Mode)**:
+- `mcp__exa__web_search_exa` for layout pattern inspiration
+- Pattern research: `{target} layout patterns {device_type}`
+- Inspiration files: `layout-extraction/_inspirations/{target}-layout-ideas.txt`
+
+#### Changed
+
+**`/workflow:ui-design:style-extract` (Renamed from `extract`)**:
+- **File Renamed**: `extract.md` → `style-extract.md`
+- **Scope Clarified**: Focus exclusively on visual style (colors, typography, spacing)
+- **Documentation Updated**: Added note about layout extraction separation
+- **No Functionality Change**: All style extraction features preserved
+- **Output**: Still generates `style-cards.json` with `proposed_tokens`
+
+**`/workflow:ui-design:generate` (Refactored to Pure Assembler)**:
+- **Before (v4.3.0)**: Layout design + style application agent
+  - Agent made layout decisions during generation
+  - Mixed structural and visual responsibilities
+  - CSS contained both layout and style rules
+
+- **After (v4.4.0)**: Pure assembly only
+  - **Reads**: `layout-templates.json` + `design-tokens.json`
+  - **Action**: Combines pre-extracted components:
+    1. Build HTML from `dom_structure`
+    2. Apply `css_layout_rules` (structure)
+    3. Link design tokens CSS (visual style)
+    4. Inject placeholder content
+  - **No Design Logic**: All layout and style decisions pre-made
+  - **Agent Prompt Updated**: Removed layout design instructions
+
+**Agent Instructions Simplification** (`generate.md`):
+```javascript
+// ❌ Old (v4.3.0): Agent designs layout + applies style
+Agent: "Design page layout based on requirements, then apply design tokens"
+
+// ✅ New (v4.4.0): Agent only assembles
+Agent: "
+  [LAYOUT_STYLE_ASSEMBLY]
+  Read layout-templates.json → Extract dom_structure, css_layout_rules
+  Read design-tokens.json → Extract ALL token values
+  Build HTML from dom_structure
+  Build CSS from css_layout_rules + token values
+  Write files IMMEDIATELY
+"
+```
+
+**Workflow Commands Updated**:
+- **`/workflow:ui-design:imitate-auto`**:
+  - Added Phase 2.5: Layout Extraction (imitate mode, single variant)
+  - Generates `layout-templates.json` before Phase 4 (UI Assembly)
+  - Uses `--mode imitate` for high-fidelity layout replication
+
+- **`/workflow:ui-design:explore-auto`**:
+  - Added Phase 2.5: Layout Extraction (explore mode, multiple variants)
+  - Generates `{targets × layout_variants}` layout templates
+  - Uses `--mode explore` for structural variety
+  - MCP-powered layout pattern research
+
+**Output Structure Changes**:
+```
+{base_path}/
+├── style-extraction/         # Visual tokens (unchanged)
+│   └── style-cards.json
+├── layout-extraction/        # NEW: Structural templates
+│   ├── layout-templates.json
+│   ├── layout-space-analysis.json (explore mode)
+│   └── _inspirations/ (explore mode)
+├── style-consolidation/      # Final design tokens (unchanged)
+│   └── style-1/
+│       └── design-tokens.json
+└── prototypes/               # Assembled output (unchanged)
+    └── {target}-style-{s}-layout-{l}.html
+```
+
+#### Improved
+
+**Separation of Concerns**:
+- 🎨 **Style (style-extract)**: Colors, typography, spacing → design-tokens.json
+- 🏗️ **Layout (layout-extract)**: DOM structure, CSS layout → layout-templates.json
+- 📦 **Assembly (generate)**: Combine structure + style → final prototypes
+- ✅ **Result**: Each phase has single, clear responsibility
+
+**Quality Improvements**:
+- 🎯 **Better Layout Variety**: Explore mode generates structurally distinct layouts
+- 🔄 **Reusability**: Layout templates can be combined with different styles
+- 📊 **Clarity**: All structural decisions in layout-templates.json
+- 🧪 **Testability**: Layout structure and visual style tested independently
+
+**Performance Benefits**:
+- ⚡ **Faster Generation**: Assembly is simpler than design + application
+- 🔄 **Better Caching**: Layout templates reused across style variants
+- 📉 **Reduced Complexity**: Generate agent has single responsibility
+
+#### Technical Details
+
+**Phase Flow Comparison**:
+
+**Old Flow (v4.3.0)**:
+```
+Phase 1: style-extract → style-cards.json
+Phase 2: consolidate → design-tokens.json
+Phase 3: generate (design+apply) → prototypes
+Phase 4: update
+```
+
+**New Flow (v4.4.0)**:
+```
+Phase 1: style-extract → style-cards.json
+Phase 2: consolidate → design-tokens.json
+Phase 2.5: layout-extract → layout-templates.json  [NEW]
+Phase 3: generate (pure assembly) → prototypes
+Phase 4: update
+```
+
+**Agent Task Changes**:
+
+**Before (Mixed Responsibility)**:
+```javascript
+Agent Task: "
+  Design page layout for {target}
+  Apply design tokens from design-tokens.json
+  Generate HTML + CSS
+"
+// Problems:
+// - Layout decisions made during generation
+// - Style application mixed with structure
+// - Agent has dual responsibility
+```
+
+**After (Pure Assembly)**:
+```javascript
+Agent Task: "
+  [LAYOUT_STYLE_ASSEMBLY]
+  INPUT 1: layout-templates.json → dom_structure, css_layout_rules
+  INPUT 2: design-tokens.json → token values
+
+  ASSEMBLY:
+  1. Build HTML from dom_structure
+  2. Build CSS from css_layout_rules (replace var())
+  3. Add visual styling using token values
+  4. Write files IMMEDIATELY
+
+  RULES:
+  ✅ Pure assembly only
+  ❌ NO layout design decisions
+  ❌ NO style design decisions
+"
+```
+
+**Layout Template Structure**:
+```json
+{
+  "target": "home",
+  "variant_id": "layout-1",
+  "device_type": "responsive",
+  "design_philosophy": "F-pattern with sticky nav",
+  "dom_structure": {
+    "tag": "body",
+    "children": [
+      {"tag": "header", "attributes": {"class": "layout-header"}},
+      {"tag": "main", "attributes": {"class": "layout-main"}},
+      {"tag": "footer", "attributes": {"class": "layout-footer"}}
+    ]
+  },
+  "component_hierarchy": ["header", "main", "footer"],
+  "css_layout_rules": ".layout-main { display: grid; grid-template-columns: 1fr 3fr; gap: var(--spacing-6); }"
+}
+```
+
+**Token-Based CSS Pattern**:
+```css
+/* Layout rules use var() for spacing/breakpoints */
+.layout-wrapper {
+  display: grid;
+  gap: var(--spacing-4);
+  padding: var(--spacing-8);
+}
+
+@media (max-width: var(--breakpoint-md)) {
+  .layout-wrapper {
+    grid-template-columns: 1fr;
+  }
+}
+```
+
+#### Migration Guide
+
+**For Existing Workflows**:
+1. **Update Command Names**:
+   ```bash
+   # Old: /workflow:ui-design:extract
+   # New: /workflow:ui-design:style-extract
+   ```
+
+2. **Add Layout Extraction Step**:
+   ```bash
+   # After consolidate, before generate:
+   /workflow:ui-design:layout-extract --session WFS-xxx --targets "dashboard,settings" --mode explore --variants 3
+   ```
+
+3. **Update Orchestrator Workflows**:
+   - `imitate-auto`: Automatically includes Phase 2.5
+   - `explore-auto`: Automatically includes Phase 2.5
+   - Manual workflows: Add `layout-extract` call
+
+**Backward Compatibility**:
+- ✅ Old `extract` command files archived (not deleted)
+- ✅ New `style-extract` command name explicit and clear
+- ✅ All output structures backward compatible
+- ⚠️ **Breaking**: `generate` now requires `layout-templates.json` input
+
+**For New Projects**:
+- Use new workflow: `style-extract → consolidate → layout-extract → generate → update`
+- Leverage layout variants: `--layout-variants` in explore-auto
+- Device-specific layouts: `--device-type` parameter
+
+#### Files Changed
+
+**Renamed**:
+- `.claude/commands/workflow/ui-design/extract.md` → `style-extract.md`
+
+**Added**:
+- `.claude/commands/workflow/ui-design/layout-extract.md` (new command, 370+ lines)
+
+**Modified**:
+- `.claude/commands/workflow/ui-design/generate.md`:
+  - Refactored to pure assembler (agent instructions simplified)
+  - Added Phase 2: Load Layout Templates
+  - Updated agent prompt to focus on assembly only
+  - Documentation updates for separation of concerns
+
+- `.claude/commands/workflow/ui-design/imitate-auto.md`:
+  - Added Phase 2.5: Layout Extraction (imitate mode)
+  - Updated workflow orchestration
+  - Phase numbering shifted (old Phase 3 → Phase 4)
+
+- `.claude/commands/workflow/ui-design/explore-auto.md`:
+  - Added Phase 2.5: Layout Extraction (explore mode)
+  - Updated workflow orchestration
+  - Matrix calculation updated: `style_variants × layout_variants × targets`
+  - Phase numbering shifted (old Phase 3 → Phase 4)
+
+- `.claude/commands/workflow/ui-design/consolidate.md`:
+  - Documentation updates
+  - Note added about layout-extract requirement
+
+**Removed**:
+- ❌ **V2 Commands Deprecated**: All `-v2` command variants removed
+  - `generate-v2.md` removed (merged into main `generate.md`)
+  - `explore-auto-v2.md` removed (merged into main `explore-auto.md`)
+  - Self-contained CSS architecture now standard in all commands
+  - No more v1/v2 split - unified workflow
+
+**Total Impact**:
+- 5 files changed
+- 1 file renamed
+- 1 new command (layout-extract, 370+ lines)
+- 2 deprecated commands removed (generate-v2, explore-auto-v2)
+- ~200 lines modified in existing commands
+- Net: +400 lines (improved separation of concerns)
+
+#### Benefits
+
+**Architectural Clarity**:
+- ✅ **Single Responsibility**: Each command has one job
+- ✅ **Clear Contracts**: Explicit input/output for each phase
+- ✅ **Better Testing**: Components testable independently
+- ✅ **Maintainability**: Changes localized to relevant phase
+
+**Developer Experience**:
+- 🎯 **Predictable**: Layout structure visible before assembly
+- 🔍 **Debuggable**: Easier to identify issues (layout vs style)
+- 🔄 **Flexible**: Reuse layouts with different styles
+- 📚 **Understandable**: Each phase has clear documentation
+
+**Design Quality**:
+- 🎨 **Style Independence**: Visual tokens separate from structure
+- 🏗️ **Layout Variety**: Explore mode generates structurally different layouts
+- 📐 **Device Optimization**: Layout templates device-specific
+- ♿ **Accessibility**: Semantic HTML5 structure with ARIA
+
+**Implementation Quality**:
+- 🧩 **Modular**: Components can be developed independently
+- 🔄 **Reusable**: Layout templates work with any style
+- 🧪 **Testable**: Structure and style tested separately
+- 📦 **Production-Ready**: Token-driven, semantic, accessible
+
+---
+
 ## [4.3.0] - 2025-10-10
 
 ### 🎨 UI Design Workflow V2 - Self-Contained CSS Architecture

README.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v4.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v4.4.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)]()
 [![MCP Tools](https://img.shields.io/badge/🔧_MCP_Tools-Experimental-orange.svg)](https://github.com/modelcontextprotocol)
@@ -15,13 +15,13 @@
 
 **Claude Code Workflow (CCW)** is a next-generation multi-agent automation framework that orchestrates complex software development tasks through intelligent workflow management and autonomous execution.
 
-> **🎉 Latest: v4.2.1** - Documentation Refactoring for UI Design Workflow. See [CHANGELOG.md](CHANGELOG.md) for details.
+> **🎉 Latest: v4.4.0** - UI Design Workflow V3 with Layout/Style Separation Architecture. See [CHANGELOG.md](CHANGELOG.md) for details.
 >
-> **What's New in v4.2.1**:
-> - 📚 **Documentation Optimization**: Reduced file sizes by 15-20% while preserving all functionality
-> - 🎯 **Clearer Structure**: Merged duplicate concepts and streamlined content organization
-> - ✨ **Improved Maintainability**: Better content separation and consistent formatting patterns
-> - 📖 **Zero Functionality Loss**: All features, workflows, and technical details preserved
+> **What's New in v4.4.0**:
+> - 🏗️ **Layout/Style Separation**: New `layout-extract` command separates structure from visual tokens
+> - 📦 **Pure Assembler**: `generate` command now purely combines pre-extracted layouts + styles
+> - 🎯 **Better Variety**: Layout exploration generates structurally distinct designs
+> - ✅ **Single Responsibility**: Each phase (style, layout, assembly) has clear purpose
 
 ---
 
@@ -259,10 +259,11 @@ MCP (Model Context Protocol) tools provide advanced codebase analysis. **Recomme
 # With session integration
 /workflow:ui-design:explore-auto --session WFS-auth --images "refs/*.png" --style-variants 2 --layout-variants 3
 
-# Or run individual design phases
-/workflow:ui-design:extract --images "refs/*.png" --variants 3
+# Or run individual design phases (v4.4.0+)
+/workflow:ui-design:style-extract --images "refs/*.png" --mode explore --variants 3
 /workflow:ui-design:consolidate --variants "variant-1,variant-3"
-/workflow:ui-design:generate --pages "dashboard,auth" --style-variants 2 --layout-variants 2
+/workflow:ui-design:layout-extract --targets "dashboard,auth" --mode explore --variants 2 --device-type responsive
+/workflow:ui-design:generate --style-variants 1 --layout-variants 2
 
 # Preview generated prototypes
 # Option 1: Open .workflow/WFS-auth/.design/prototypes/compare.html in browser
@@ -364,12 +365,13 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 |---|---|
 | `/workflow:session:*` | Manage development sessions (`start`, `pause`, `resume`, `list`, `switch`, `complete`). |
 | `/workflow:brainstorm:*` | Use role-based agents for multi-perspective planning. |
-| `/workflow:ui-design:explore-auto` | **v4.2.1** Matrix exploration mode - Generate multiple style × layout variants for comprehensive design exploration. |
-| `/workflow:ui-design:imitate-auto` | **v4.2.1** Fast imitation mode - Rapid single-design replication with auto-screenshot and direct token extraction. |
-| `/workflow:ui-design:extract` | **v4.2.1** Extract design from images/text using Claude-native analysis. Single-pass variant generation. |
-| `/workflow:ui-design:consolidate` | **v4.2.1** Consolidate style variants into validated design tokens using Claude synthesis. |
-| `/workflow:ui-design:generate` | **v4.2.1** Generate token-driven HTML/CSS prototypes in matrix mode (style × layout combinations). |
-| `/workflow:ui-design:update` | **v4.2.1** Integrate finalized design system into brainstorming artifacts. |
+| `/workflow:ui-design:explore-auto` | **v4.4.0** Matrix exploration mode - Generate multiple style × layout variants with layout/style separation. |
+| `/workflow:ui-design:imitate-auto` | **v4.4.0** Fast imitation mode - Rapid UI replication with auto-screenshot, layout extraction, and assembly. |
+| `/workflow:ui-design:style-extract` | **v4.4.0** Extract visual style (colors, typography, spacing) from images/text using Claude-native analysis. |
+| `/workflow:ui-design:layout-extract` | **v4.4.0** Extract structural layout (DOM, CSS layout rules) with device-aware templates. |
+| `/workflow:ui-design:consolidate` | **v4.4.0** Consolidate style variants into validated design tokens using Claude synthesis. |
+| `/workflow:ui-design:generate` | **v4.4.0** Pure assembler - Combine layout templates + design tokens → HTML/CSS prototypes. |
+| `/workflow:ui-design:update` | **v4.4.0** Integrate finalized design system into brainstorming artifacts. |
 | `/workflow:plan` | Create a detailed, executable plan from a description. |
 | `/workflow:tdd-plan` | Create TDD workflow (6 phases) with test coverage analysis and Red-Green-Refactor cycles. |
 | `/workflow:execute` | Execute the current workflow plan autonomously. |
@@ -381,9 +383,9 @@ cd .workflow/WFS-auth/.design/prototypes && python -m http.server 8080
 | `/workflow:tools:test-concept-enhanced` | Generate test strategy and requirements analysis using Gemini. |
 | `/workflow:tools:test-task-generate` | Generate test task JSON with test-fix-cycle specification. |
 
-### **UI Design Workflow Commands (`/workflow:ui-design:*`)** *(v4.2.1)*
+### **UI Design Workflow Commands (`/workflow:ui-design:*`)** *(v4.4.0)*
 
-The design workflow system provides complete UI design refinement with **pure Claude execution**, **intelligent page inference**, and **zero external dependencies**.
+The design workflow system provides complete UI design refinement with **layout/style separation architecture**, **pure Claude execution**, **intelligent target inference**, and **zero external dependencies**.
 
 #### Core Commands
 
@@ -420,21 +422,41 @@ The design workflow system provides complete UI design refinement with **pure Cl
 - **🎯 Direct Extraction**: Skip variant selection, go straight to implementation
 - **🔧 Single Design Focus**: Best for copying existing designs quickly
 
-**`/workflow:ui-design:extract`** - Style analysis with dual input sources
+**`/workflow:ui-design:style-extract`** - Visual style extraction (v4.4.0)
 ```bash
 # Pure text prompt
-/workflow:ui-design:extract --prompt "Modern minimalist, dark theme" --variants 3
+/workflow:ui-design:style-extract --prompt "Modern minimalist, dark theme" --mode explore --variants 3
 
 # Pure images
-/workflow:ui-design:extract --images "refs/*.png" --variants 3
+/workflow:ui-design:style-extract --images "refs/*.png" --mode explore --variants 3
 
 # Hybrid (text guides image analysis)
-/workflow:ui-design:extract --images "refs/*.png" --prompt "Linear.app style" --variants 2
+/workflow:ui-design:style-extract --images "refs/*.png" --prompt "Linear.app style" --mode imitate
+
+# High-fidelity single style
+/workflow:ui-design:style-extract --images "design.png" --mode imitate
 ```
+- **🎨 Visual Tokens Only**: Colors, typography, spacing (no layout structure)
+- **🔄 Dual Mode**: Imitate (single variant) / Explore (multiple variants)
 - **Claude-Native**: Single-pass analysis, no external tools
-- **Enhanced Output**: `style-cards.json` with embedded `proposed_tokens`
-- **Reproducible**: Deterministic structure, version-controlled logic
-- **Output**: 1 file (vs 4+ in previous versions)
+- **Output**: `style-cards.json` with embedded `proposed_tokens`
+
+**`/workflow:ui-design:layout-extract`** - Structural layout extraction (v4.4.0)
+```bash
+# Explore mode - multiple layout variants
+/workflow:ui-design:layout-extract --targets "home,dashboard" --mode explore --variants 3 --device-type responsive
+
+# Imitate mode - single layout replication
+/workflow:ui-design:layout-extract --images "refs/*.png" --targets "dashboard" --mode imitate --device-type desktop
+
+# With MCP research (explore mode)
+/workflow:ui-design:layout-extract --prompt "E-commerce checkout" --targets "cart,checkout" --mode explore --variants 2
+```
+- **🏗️ Structure Only**: DOM hierarchy, CSS layout rules (no visual style)
+- **📱 Device-Aware**: Desktop, mobile, tablet, responsive optimizations
+- **🧠 Agent-Powered**: Uses ui-design-agent for structural analysis
+- **🔍 MCP Research**: Layout pattern inspiration (explore mode)
+- **Output**: `layout-templates.json` with token-based CSS
 
 **`/workflow:ui-design:consolidate`** - Validate and merge tokens
 ```bash
@@ -445,19 +467,19 @@ The design workflow system provides complete UI design refinement with **pure Cl
 - **Features**: WCAG AA validation, OKLCH colors, W3C token format
 - **Output**: `design-tokens.json`, `style-guide.md`, `tailwind.config.js`, `validation-report.json`
 
-**`/workflow:ui-design:generate`** - Generate HTML/CSS prototypes
+**`/workflow:ui-design:generate`** - Pure assembler (v4.4.0)
 ```bash
-# Matrix mode - style × layout combinations
-/workflow:ui-design:generate --pages "dashboard,auth" --style-variants 2 --layout-variants 3
+# Combine layout templates + design tokens
+/workflow:ui-design:generate --style-variants 1 --layout-variants 2
 
-# Single page with multiple variants
-/workflow:ui-design:generate --pages "home" --style-variants 3 --layout-variants 2
+# Multiple styles with multiple layouts
+/workflow:ui-design:generate --style-variants 2 --layout-variants 3
 ```
-- **🎯 Matrix Generation**: Creates all style × layout combinations
-- **📊 Multi-page Support**: Consistent design system across pages
-- **✅ Consistency Validation**: Automatic cross-page consistency reports (v4.2.0+)
+- **📦 Pure Assembly**: Combines pre-extracted layout-templates.json + design-tokens.json
+- **❌ No Design Logic**: All layout/style decisions made in previous phases
+- **✅ Token Resolution**: Replaces var() placeholders with actual token values
+- **🎯 Matrix Output**: Generates style × layout × targets prototypes
 - **🔍 Interactive Preview**: `compare.html` with side-by-side comparison
-- **📋 Batch Selection**: Quick selection by style or layout filters
 
 **`/workflow:ui-design:update`** - Integrate design system
 ```bash

README_CN.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v4.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v4.3.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)]()
 [![MCP工具](https://img.shields.io/badge/🔧_MCP工具-实验性-orange.svg)](https://github.com/modelcontextprotocol)
@@ -15,13 +15,13 @@
 
 **Claude Code Workflow (CCW)** 是一个新一代的多智能体自动化开发框架，通过智能工作流管理和自主执行来协调复杂的软件开发任务。
 
-> **🎉 最新版本: v4.2.1** - UI 设计工作流文档重构。详见 [CHANGELOG.md](CHANGELOG.md)。
+> **🎉 最新版本: v4.3.0** - UI 设计工作流 V2 自包含 CSS 架构。详见 [CHANGELOG.md](CHANGELOG.md)。
 >
-> **v4.2.1 版本新特性**:
-> - 📚 **文档优化**: 文件大小减少 15-20%，同时保留所有功能
-> - 🎯 **更清晰的结构**: 合并重复概念，优化内容组织
-> - ✨ **改进的可维护性**: 更好的内容分离和一致的格式模式
-> - 📖 **零功能损失**: 保留所有特性、工作流和技术细节
+> **v4.3.0 版本新特性**:
+> - 🎨 **自包含 CSS**: Agent 从 design-tokens.json 直接生成独立 CSS
+> - ⚡ **简化工作流**: 移除占位符机制和令牌转换步骤
+> - 💪 **更强风格差异**: CSS 使用直接令牌值，实现更强视觉区分
+> - 📉 **代码减少 31%**: 移除 346 行代码，职责更清晰
 
 ---