ui-implementer
Implements UI components from scratch based on design references (Figma, screenshots, mockups) with intelligent validation and adaptive agent switching. Use when user provides a design and wants pixel-perfect UI implementation with design fidelity validation. Triggers automatically when user mentions Figma links, design screenshots, or wants to implement UI from designs.
What this skill does
# UI Implementer This Skill implements UI components from scratch based on design references using specialized UI development agents with intelligent validation and adaptive agent switching for optimal results. ## When to use this Skill Claude should invoke this Skill when: **Design References Provided:** - User shares a Figma URL (e.g., "Here's the Figma design: https://figma.com/...") - User provides a screenshot/mockup path (e.g., "I have a design at /path/to/design.png") - User mentions a design URL they want to implement **Intent to Implement UI:** - "Implement this UI design" - "Create components from this Figma file" - "Build this interface from the mockup" - "Make this screen match the design" **Pixel-Perfect Requirements:** - "Make it look exactly like the design" - "Implement pixel-perfect from Figma" - "Match the design specifications exactly" **Examples of User Messages:** - "Here's a Figma link, can you implement the UserProfile component?" - "I have a design screenshot, please create the dashboard layout" - "Implement this navbar from the mockup at designs/navbar.png" - "Build the product card to match this Figma: https://figma.com/..." ## DO NOT use this Skill when: - User just wants to validate existing UI (use browser-debugger or /validate-ui instead) - User wants to fix existing components (use regular developer agent) - User wants to implement features without design reference (use regular implementation flow) ## Instructions This Skill implements the same workflow as the `/implement-ui` command. Follow these phases: ### PHASE 0: Initialize Workflow Create a global todo list to track progress: ``` TodoWrite with: - PHASE 1: Gather inputs (design reference, component description, preferences) - PHASE 1: Validate inputs and find target location - PHASE 2: Launch UI Developer for initial implementation - PHASE 3: Start validation and iterative fixing loop - PHASE 3: Quality gate - ensure design fidelity achieved - PHASE 4: Generate final implementation report - PHASE 4: Present results and complete handoff ``` ### PHASE 1: Gather User Inputs **Step 1: Extract Design Reference** Check if user already provided design reference in their message: - Scan for Figma URLs: `https://figma.com/design/...` or `https://figma.com/file/...` - Scan for file paths: `/path/to/design.png`, `~/designs/mockup.jpg` - Scan for remote URLs: `http://example.com/design.png` If design reference found in user's message: - Extract and store as `design_reference` - Log: "Design reference detected: [design_reference]" If NOT found, ask: ``` I'd like to implement UI from your design reference. Please provide the design reference: 1. Figma URL (e.g., https://figma.com/design/abc123.../node-id=136-5051) 2. Screenshot file path (local file on your machine) 3. Remote URL (live design reference) What is your design reference? ``` **Step 2: Extract Component Description** Check if user mentioned what to implement: - Look for component names: "UserProfile", "navbar", "dashboard", "ProductCard" - Look for descriptions: "implement the header", "create the sidebar", "build the form" If found: - Extract and store as `component_description` If NOT found, ask: ``` What UI component(s) should I implement from this design? Examples: - "User profile card component" - "Navigation header with mobile menu" - "Product listing grid with filters" - "Dashboard layout with widgets" What component(s) should I implement? ``` **Step 3: Ask for Target Location** Ask: ``` Where should I create this component? Options: 1. Provide a specific directory path (e.g., "src/components/profile/") 2. Let me suggest based on component type 3. I'll tell you after seeing the component structure Where should I create the component files? ``` Store as `target_location`. **Step 4: Ask for Application URL** Ask: ``` What is the URL where I can preview the implementation? Examples: - http://localhost:5173 (Vite default) - http://localhost:3000 (Next.js/CRA default) - https://staging.yourapp.com Preview URL? ``` Store as `app_url`. **Step 5: Ask for UI Developer Codex Preference** Use AskUserQuestion: ``` Enable intelligent agent switching with UI Developer Codex? When enabled: - If UI Developer struggles (2 consecutive failures), switches to UI Developer Codex - If UI Developer Codex struggles (2 consecutive failures), switches back - Provides adaptive fixing with both agents for best results Enable intelligent agent switching? ``` Options: - "Yes - Enable intelligent agent switching" - "No - Use only UI Developer" Store as `codex_enabled` (boolean). **Step 6: Validate Inputs** Validate all inputs using the same logic as /implement-ui command: - Design reference format (Figma/Remote/Local) - Component description not empty - Target location valid - Application URL valid ### PHASE 2: Initial Implementation from Scratch Launch UI Developer agent using Task tool with `subagent_type: frontend:ui-developer`: ``` Implement the following UI component(s) from scratch based on the design reference. **Design Reference**: [design_reference] **Component Description**: [component_description] **Target Location**: [target_location] **Application URL**: [app_url] **Your Task:** 1. **Analyze the design reference:** - If Figma: Use Figma MCP to fetch design screenshot and specs - If Remote URL: Use Chrome DevTools MCP to capture screenshot - If Local file: Read the file to view design 2. **Plan component structure:** - Determine component hierarchy - Identify reusable sub-components - Plan file structure (atomic design principles) 3. **Implement UI components from scratch using modern best practices:** - React 19 with TypeScript - Tailwind CSS 4 (utility-first, static classes only, no @apply) - Mobile-first responsive design - Accessibility (WCAG 2.1 AA, ARIA attributes) - Use existing design system components if available 4. **Match design reference exactly:** - Colors (Tailwind theme or exact hex) - Typography (families, sizes, weights, line heights) - Spacing (Tailwind scale: p-4, p-6, etc.) - Layout (flexbox, grid, alignment) - Visual elements (borders, shadows, border-radius) - Interactive states (hover, focus, active, disabled) 5. **Create component files in target location:** - Use Write tool to create files - Follow project conventions - Include TypeScript types - Add JSDoc comments 6. **Ensure code quality:** - Run typecheck: `npx tsc --noEmit` - Run linter: `npm run lint` - Run build: `npm run build` - Fix any errors 7. **Provide implementation summary:** - Files created - Components implemented - Key decisions - Any assumptions Return detailed implementation summary when complete. ``` Wait for UI Developer to complete. ### PHASE 3: Validation and Adaptive Fixing Loop Initialize loop variables: ``` iteration_count = 0 max_iterations = 10 previous_issues_count = None current_issues_count = None last_agent_used = None ui_developer_consecutive_failures = 0 codex_consecutive_failures = 0 design_fidelity_achieved = false ``` **Loop: While iteration_count < max_iterations AND NOT design_fidelity_achieved** **Step 3.1: Launch Designer for Validation** Use Task tool with `subagent_type: frontend:designer`: ``` Review the implemented UI component against the design reference. **Iteration**: [iteration_count + 1] / 10 **Design Reference**: [design_reference] **Component Description**: [component_description] **Implementation Files**: [List of files] **Application URL**: [app_url] **Your Task:** 1. Fetch design reference screenshot 2. Capture implementation screenshot at [app_url] 3. Perform comprehensive design review: - Colors & theming - Typography - Spacing & layout - Visual elements - Responsive design - Accessibility (WCAG 2.1 AA) - Interactive states 4. Document ALL discrepancies 5. Categorize by severity (CRITICAL/MEDIUM/LOW) 6. Provide actionab
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.