design-guide
Extract comprehensive design language from websites including colors, typography, animations, interactive states, shadows, gradients, component patterns, and UX behaviors. Generates pixel-perfect design guides with responsive screenshots and complete design system documentation. Use when analyzing website design, creating design systems, or rebuilding sites.
What this skill does
# Comprehensive Design Guide Generator Extract the complete design language from any website with automated analysis of colors, typography, animations, interactions, and UX patterns. Goes far beyond basic CSS extraction to capture the full design system. ## When to Use This Skill Use this skill when you want to: - **Analyze a website's complete design system** - Not just colors and fonts, but the entire design language - **Extract interactive design patterns** - Hover states, transitions, animations, micro-interactions - **Document component libraries** - Buttons, cards, forms, navigation patterns - **Create pixel-perfect recreations** - Comprehensive data for exact replicas - **Build design systems** - Complete token systems with all design decisions documented - **Understand UX patterns** - Interaction patterns, accessibility features, responsive behavior - **Reverse-engineer designs** - Full extraction of design decisions from live websites ## What This Skill Extracts ### ๐จ Visual Design **Colors & Gradients** - Text colors (all variations) - Background colors - Border colors - Shadow colors (extracted from box-shadow) - Linear and radial gradients - Complete color palette with CSS custom properties **Typography System** - Font families and fallback stacks - Complete type scale (all font sizes used) - Font weights (100-900) - Line heights - Letter spacing - Text transforms - Heading hierarchy (H1-H6) with exact styles - Body text specifications **Visual Effects** - Box shadows (all variations) - Text shadows - CSS filters (blur, brightness, contrast, etc.) - Transform properties - Opacity values - Border radius values ### โก Interactive Design **Interactive States** - Hover effects (color, transform, shadow changes) - Focus states - Active states - Transition properties - Before/after comparisons for hover states - Screenshots of interactive elements in hover state **Animations** - CSS transitions (timing, easing, duration) - Keyframe animations - Animated element detection - Animation names and rules ### ๐ Layout & Spacing **Spacing System** - Margin values (sorted scale) - Padding values (sorted scale) - Gap values (Flexbox/Grid) - Complete spacing token system **Layout Patterns** - Container max-widths - Centered container patterns - Flexbox configurations - Grid layouts - Sticky/fixed positioning ### ๐งฉ Component Patterns **UI Components Identified** - Buttons (with exact styling) - Cards (background, shadow, radius, padding) - Navigation bars - Forms and inputs - Modals - Badges - Alerts **Component Documentation** - Exact CSS for each component variant - Component text content - Visual hierarchy ### ๐ญ UX & Behavior **Interaction Patterns** - Scroll behavior - Cursor styles used - Interactive element count - Sticky/fixed element patterns **Accessibility Features** - ARIA labels count - ARIA descriptions count - Role attributes count - Image alt text usage ### ๐ฑ Responsive Design **Multi-Device Analysis** - Mobile screenshots (375x812) - Tablet screenshots (768x1024) - Desktop screenshots (1920x1080) - Layout metrics at each breakpoint - Viewport-specific behaviors ## Instructions for Claude ### Step 1: Verify Setup Navigate to the skill directory: ```bash cd /Users/tchen/projects/mycode/claude-skills/design-guide ``` Ensure dependencies are installed (first time only): ```bash uv sync playwright install chromium ``` ### Step 2: Gather Requirements Ask the user for: - **URL** (required): The website to analyze - **Output directory** (optional): Where to save results (default: `./output`) - **Viewport size** (optional): Custom viewport dimensions (default: 1600x1200) ### Step 3: Run the Enhanced Extractor Execute the comprehensive extraction: ```bash uv run main.py --url <URL> [OPTIONS] ``` **Available Options:** - `--url, -u`: Website URL to analyze (required) - `--output, -o`: Output directory (default: `./output`) - `--viewport-width`: Viewport width in pixels (default: 1600) - `--viewport-height`: Viewport height in pixels (default: 1200) **What happens during extraction:** The tool will: 1. ๐ Load the page and wait for network idle 2. ๐ธ Take viewport and full-page screenshots 3. ๐ Extract HTML structure 4. ๐ Extract all CSS (linked and inline) 5. ๐ฏ Compute styles for every element 6. โก Capture interactive states (hover 10 elements) 7. ๐จ Analyze complete color palette 8. ๐ Extract typography system 9. ๐ Analyze layout and spacing 10. โจ Detect animations and transitions 11. ๐ Extract shadows and visual effects 12. ๐งฉ Identify component patterns 13. ๐ญ Analyze UX patterns 14. ๐ฑ Test responsive behavior (3 breakpoints) 15. ๐พ Save all data and generate design guide ### Step 4: Review Generated Assets After extraction, the output directory contains: **Documentation** - `design-guide.md` - Comprehensive design guide (main deliverable) - `design_data.json` - Complete structured data **Visual Assets** - `viewport_screenshot.png` - Desktop viewport capture - `fullpage_screenshot.png` - Complete page capture - `interactive_hover.png` - Hover state demonstrations - `responsive_mobile.png` - Mobile view (375x812) - `responsive_tablet.png` - Tablet view (768x1024) - `responsive_desktop.png` - Large desktop view (1920x1080) **Source Code** - `extracted.html` - Original HTML - `extracted.css` - All CSS (can be 2-3MB for complex sites) - `computed_styles.json` - Computed styles for every element (can be large) ### Step 5: Explore the Design Guide The generated `design-guide.md` contains: 1. **Visual Assets** - All screenshots with descriptions 2. **Color System** - Complete palette with CSS variables 3. **Typography System** - Font stacks, type scale, heading hierarchy 4. **Spacing & Layout** - Complete spacing tokens and container patterns 5. **Visual Effects** - Shadows, filters, transforms, opacity 6. **Animations & Transitions** - All transitions and keyframe animations 7. **Interactive States** - Hover effects with before/after comparisons 8. **Component Patterns** - Button, card, form, nav styling 9. **UX Patterns** - Accessibility, cursor styles, sticky elements 10. **Responsive Design** - Breakpoint analysis 11. **Implementation Guide** - Step-by-step recreation instructions ### Step 6: Analyze Design Patterns Use the extracted data to understand: **Design System Maturity** - Consistent spacing scale? (Check margin/padding variations) - Defined type scale? (Check font size progression) - Component library? (Check identified components) - Accessibility? (Check ARIA features) **Design Decisions** - Color choices and usage patterns - Typography hierarchy clarity - Animation smoothness (check transition timings) - Shadow depth system - Border radius consistency ### Step 7: Pixel-Perfect Recreation (Advanced) For recreating the design: 1. **Use Design Tokens**: Copy CSS variables from design guide 2. **Match Typography**: Use exact font stacks and sizes 3. **Implement Spacing**: Follow extracted spacing scale 4. **Apply Effects**: Use exact shadow and border-radius values 5. **Add Interactions**: Implement hover/focus states as documented 6. **Test Responsive**: Match layouts at all breakpoints 7. **Verify Visually**: Compare with extracted screenshots ### Step 8: Interactive Exploration with Playwright MCP (Optional) If you need deeper interaction analysis: ```python # Use Playwright MCP to: 1. Navigate to specific pages/states 2. Test form interactions 3. Trigger modals/dropdowns 4. Capture specific UI states 5. Test animations manually 6. Explore navigation flows ``` ## Usage Examples ### Basic Usage - Any Website ```bash uv run main.py --url https://stripe.com ``` ### E-commerce Site Analysis ```bash uv run main.py --url https://shopify.com --output ./shopify-design ``` ### Custom Viewport ```bash uv run main.py --url https://github.com --viewport-width 1920 --viewport-height 1080 ``` ### Design System Extraction ```bash # Extract from design system documentation uv run main.p
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context โ no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes โ information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development โ guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.