elegant-design
Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and streaming content. Use when building user interfaces that need professional polish and developer-focused features.
What this skill does
# Designing Elegant Interfaces
## Philosophy
World-class design is intentional, accessible, and delightful. Every element serves a purpose, every interaction feels natural, and the experience adapts gracefully across contexts.
**Core Principles:**
- **Clarity over cleverness** - Users should never wonder what to do next
- **Consistency over novelty** - Patterns should repeat predictably
- **Performance over features** - Fast, smooth interactions trump visual complexity
- **Accessibility always** - Design for all users from the start
- **Progressive disclosure** - Reveal complexity only when needed
- **Intentional friction** - Make destructive actions harder, constructive actions effortless
## When to Use This Skill
Use this skill when:
- Building web applications with React/Next.js/similar frameworks
- Creating developer tools or technical interfaces
- Designing interfaces with chat, terminals, or code display
- Implementing real-time or streaming features
- Ensuring accessibility and responsive design
- Working with shadcn/ui, daisyUI, or HeroUI design systems
## Design Process Workflow
Follow this workflow for optimal results:
### 1. Discovery & Planning (15-30 min)
**Map User Experience:**
```bash
# Create flow diagrams with Graphviz
cat > user-flow.dot << 'EOF'
digraph UserFlow {
Start -> "Observe State"
"Observe State" -> "Orient Understanding"
"Orient Understanding" -> "Decide Action"
"Decide Action" -> "Act Execute"
"Act Execute" -> "Observe State" [label="OODA loop"]
}
EOF
dot -Tpng user-flow.dot -o user-flow.png
```
**OODA Loop Mapping:**
For each major user goal, optimize the cycle:
1. **Observe** - What information does the user need?
2. **Orient** - How do they make sense of it?
3. **Decide** - What choices are available?
4. **Act** - How do they execute?
**Document States:**
- Entry points (how users arrive)
- Core loops (repeated actions)
- Success states (goals achieved)
- Failure states (errors, recovery paths)
- Edge cases (empty, loading, error, extreme data)
**List Affordances:**
Identify every UI element needed:
- Navigation (movement between sections)
- Actions (buttons, links, controls)
- Inputs (forms, editors, pickers)
- Feedback (success, error, loading)
- Content (text, images, data)
- Wayfinding (breadcrumbs, progress)
**Before Building Custom Components:**
1. Search shadcn/ui first (https://ui.shadcn.com)
2. Check daisyUI (https://daisyui.com)
3. Explore HeroUI (https://heroui.com)
4. Build custom only when necessary
### 2. Design Foundation (20-40 min)
**Establish Visual System:**
Read the detailed foundation guides:
- `foundation/typography.md` - Font selection (Geist, JetBrains Mono), scales, loading
- `foundation/colors-and-spacing.md` - Color palettes, spacing systems, dark mode
- `foundation/layout-patterns.md` - Grids, containers, white space, responsive breakpoints
**Quick Reference:**
- **Typography**: Geist for UI, JetBrains Mono for code (14px minimum)
- **Spacing**: 8px base system (0.5rem, 1rem, 1.5rem, 2rem, 3rem, 4rem, 6rem, 8rem)
- **Colors**: Semantic tokens (--color-background, --color-primary, --color-error, etc.)
- **Layout**: Mobile-first, 12-column grid, generous white space
### 3. Interactive Elements (30-60 min)
For sophisticated interactive features, reference the specialized guides:
**Chat & Messaging:**
- Read `interactive/chat-and-messaging.md` when building conversational interfaces
- Covers message states, streaming, auto-scrolling, markdown rendering
**Terminals & Code Display:**
- Read `interactive/terminals-and-code.md` for terminal emulators, syntax highlighting, semantic highlighting
- Covers ANSI colors, Shiki integration, copy buttons, line highlighting
**Streaming & Loading:**
- Read `interactive/streaming-and-loading.md` for progressive loading, streaming text, optimistic updates
- Covers skeleton screens, progress indicators, loading hierarchies
**Diffs & Logs:**
- Read `interactive/diffs-and-logs.md` for version control UIs, log viewers
- Covers split/unified diffs, character-level changes, virtual scrolling
### 4. Implementation (1-3 hours)
**Build Components:**
- Read `implementation/components-and-accessibility.md` for component architecture and WCAG compliance
- Use atomic design: atoms → molecules → organisms → templates → pages
- Ensure keyboard navigation and screen reader support
**Optimize Performance:**
- Read `implementation/performance.md` for Core Web Vitals optimization
- Lazy load, code split, optimize images, measure with Lighthouse
**Test & Refine:**
- Read `implementation/testing-and-qa.md` for comprehensive testing approach
- Test on multiple devices, screen sizes, and with accessibility tools
### 5. Validation & Refinement
**Pre-Launch Checklist:**
- [ ] User flows tested and OODA loops optimized
- [ ] All states handled (empty, loading, error, success)
- [ ] Mobile responsive (tested on real devices)
- [ ] Accessibility compliant (WCAG AA)
- [ ] Performance measured (Lighthouse score > 90)
- [ ] Geist used for UI, JetBrains Mono for code
- [ ] Design system components used where possible
- [ ] Consistent spacing and typography
- [ ] Both light and dark modes work
- [ ] Keyboard navigation complete
- [ ] Interactive elements polished (see interactive guides)
## Quick Decision Tree
**Need to understand the basics?**
→ Read `foundation/` files first
**Building chat or messaging?**
→ Read `interactive/chat-and-messaging.md`
**Building terminal or code editor?**
→ Read `interactive/terminals-and-code.md`
**Need streaming or loading states?**
→ Read `interactive/streaming-and-loading.md`
**Building diffs or log viewers?**
→ Read `interactive/diffs-and-logs.md`
**Ready to implement?**
→ Read `implementation/` files
**Need tools or want to avoid mistakes?**
→ Read `reference/` files
## Design Systems Priority
1. **shadcn/ui** (https://ui.shadcn.com) - PRIMARY CHOICE
- Excellent accessibility defaults
- Radix UI primitives
- Tailwind-based, customizable
- Copy-paste into project
2. **daisyUI** (https://daisyui.com)
- Semantic component names
- Tailwind plugin
- Rapid prototyping
3. **HeroUI** (https://heroui.com)
- Modern, polished
- Strong design language
- Product interfaces
See `reference/design-systems.md` for detailed comparison and usage patterns.
## Typography Standards
**Use these fonts exclusively:**
- **Geist** (https://vercel.com/font) - For ALL interface text
- UI labels, body text, headings
- 95% of your typography
- **JetBrains Mono** (https://jetbrains.com/mono) - For ALL code/technical content
- Code blocks, terminals, logs, diffs
- 14px minimum size
- Enable ligatures
Never mix multiple sans-serif or multiple monospace fonts.
See `foundation/typography.md` for complete guidance.
## Inspiration Sites
Study these for design patterns:
- **Vercel** (https://vercel.com) - Generous white space, clear typography
- **Hex** (https://hex.tech) - Data-dense but organized
- **Baseten** (https://docs.baseten.co) - Clear documentation structure
- **Weather Underground** (https://wunderground.com) - Complex data, clean presentation
- **Ghostty** (https://ghostty.org) - Modern terminal, elegant design
## Common Anti-Patterns
**Avoid these mistakes:**
- ❌ Building custom components when design system has them
- ❌ Using absolute positioning for layout
- ❌ Animating expensive properties (width, height)
- ❌ Skipping mobile testing
- ❌ Ignoring accessibility
- ❌ Using `<div>` for everything
- ❌ Mixing multiple monospace fonts
- ❌ Auto-scrolling when user is reading
- ❌ Showing raw ANSI codes in terminals
- ❌ Forgetting empty/loading/error states
See `reference/anti-patterns.md` for complete list with explanations.
## Iterative Development
**For simple interfaces (single page, few components):**
1. Start with foundation (read foundation files)
2. Use design system components
3. Test and refine
**For complex interfaces (multiple features, interactive elements):**
1. 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.