design-system-generator
Generate a project-specific DESIGN_SYSTEM.md that enforces consistent UI/UX across SPAs, traditional server-rendered sites, and hybrid systems. Includes tokens, component rules, accessibility gates, and production asset/manifest guidance.
What this skill does
# Design System Generator ## Overview This skill generates a project-specific **`DESIGN_SYSTEM.md`** that enforces consistent UI/UX across: - SPAs (React/Vue/Svelte/Angular) - Traditional server-rendered sites (Laravel, Rails, Django, WordPress, etc.) - Hybrid systems (admin + marketing + docs) The design system must be **component-based**, portable, and practical for real implementation. **When to use this skill:** - Setting up UI consistency rules for a new project - Standardizing component patterns across teams - Establishing design tokens (colors, typography, spacing) - Defining accessibility and performance requirements ## Interactive Workflow ### Required Questions Ask these questions before generating the document: ``` 1. Project type: SPA / Traditional / Hybrid 2. Primary framework(s): React/Vue/Svelte/Angular/None + backend/framework 3. Existing UI/template/design system already in use? (yes/no) 4. CSS approach preference: a) Tailwind/utility-first b) SCSS/SASS c) CSS Modules d) styled-components/emotion e) Component library (MUI/Ant/etc.) 5. Do you need light mode only, light+dark, or multi-theme? 6. Accessibility target (recommend WCAG AA) and keyboard support expectations 7. Browser/device support constraints 8. i18n/RTL requirements (if any) 9. Do you want design tokens exported? (CSS vars / JSON / both) Reply examples: - Short: `1a 2b 3no 4a 5b 6aa 7modern 8no 9both` - Detailed: `SPA with Vue 3, no existing design system, using Tailwind, light+dark theme, WCAG AA, modern browsers only, no RTL, export both CSS vars and JSON` ``` ### Optional Questions (ask only if relevant) - Figma link or brand guide? - Multi-tenant theming? - Mobile app alignment? ## Decision Policy ### Rule 1: Prefer existing stack If the project already uses a template or styling system, adapt to it. ### Rule 2: Choose one best-fit direction Do not provide 3-5 "options" unless the user requests comparison. Pick one approach and commit. ### Safe Defaults - **React SPA**: TailwindCSS + shadcn/ui (Radix primitives) + CSS variables tokens - **Vue SPA**: TailwindCSS + headless components + CSS variables tokens - **Angular**: Angular Material OR Tailwind + CDK (based on preference) - **Traditional**: SCSS or PostCSS layered architecture (tokens/base/components/utilities), optional bundler ## Output Files ### Primary - `DESIGN_SYSTEM.md` ### Optional (only if user wants) - `design-tokens.json` - `tokens.css` - Sample component snippets ## Non-Negotiables (must appear in DESIGN_SYSTEM.md) ### Accessibility - Visible focus states - Keyboard navigation for interactive elements - Contrast targets (WCAG AA recommended) - Reduced motion support - Semantic HTML first; ARIA only when necessary ### Performance / Production - Hashed asset filenames + manifest mapping (cache busting) - Minify CSS/JS for production - Image optimization pipeline (including SVG optimization) - Font loading strategy (`font-display: swap`, limit weights) ## Document Style `DESIGN_SYSTEM.md` is a **team artifact**: - Do not mention "AI", "assistant", "model", or "prompt" - Use clear "Do/Don't" guidance - Keep readable in ~10-15 minutes ## DESIGN_SYSTEM.md Required Structure Generate a tailored document using this structure: 1. **Scope** 2. **Design principles** (3-5 bullet max) 3. **Supported platforms & constraints** 4. **Design tokens** - Color system - Typography - Spacing/layout - Radius/borders/shadows - Motion 5. **UI foundations** - Base styles/reset - Focus/interaction states - Iconography 6. **Component architecture** - Portability across SPA + Traditional - Naming + folder conventions - Required states (hover/focus/disabled/loading/error) 7. **Component inventory** (minimum viable list) 8. **CSS strategy & tooling** - SPA path vs Traditional path 9. **Production build & asset strategy** - dist structure - Manifest requirement - Optimization checklist 10. **Accessibility checklist** (ship gate) 11. **Examples** (token usage + one component example) ## SPA vs Traditional Guidance ### SPA guidance must include: - Recommended bundler (Vite/Webpack/Rollup) aligned with stack - CSS strategy (Tailwind/CSS Modules/SCSS) - Component library decision (if any) - Theming mechanism (CSS variables recommended) ### Traditional guidance must include: - SCSS/PostCSS architecture: - tokens layer - base layer - components layer - utilities layer - Recommendation for bundling (optional but encouraged) - Manifest strategy so server templates reference hashed assets ## Required Manifest Guidance (Cache Busting) Include an explicit section stating: - Build output must produce a manifest mapping logical asset names to hashed filenames - Server must read manifest to include assets - Avoid stale browser caches in production ## Agent-Doc Patch Snippet (Required Output) After generating `DESIGN_SYSTEM.md`, also output a short patch snippet to add to `AGENTS.md` and/or `CLAUDE.md`: ```markdown ## Design System All UI components and pages must follow `DESIGN_SYSTEM.md`: - Use design tokens (no hardcoded colors/sizes). - Implement component states (hover/focus/disabled/loading/error). - Meet accessibility and performance requirements. ``` ## Reference Files Before generating `DESIGN_SYSTEM.md`, read these reference files: - **Template**: `TEMPLATE_DESIGN_SYSTEM.md` - Use this as the base structure for generation - **Example CSS tokens**: `examples/tokens.css` - Reference for CSS variable token format - **Example JSON tokens**: `examples/design-tokens.json` - Reference for JSON token export format - **Example manifest**: `examples/manifest.example.json` - Reference for asset manifest structure - **AGENTS.md patch**: `examples/AGENTS.patch.md` - The exact snippet to add to AGENTS.md/CLAUDE.md ## Acceptance Criteria - `DESIGN_SYSTEM.md` is tailored to the user's stack and constraints - Contains token rules, component state rules, accessibility gates, and production/manifest rules - Avoids "AI" language entirely in the generated docs - Recommends a single coherent approach (unless user asked for alternatives) - Includes an `AGENTS.md` / `CLAUDE.md` patch snippet referencing `DESIGN_SYSTEM.md` --- *This skill is part of the awesome-ai-agent-skills community library.*
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 — 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 — 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 — 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.