.agents/skills/penpot-uiux-design/SKILL.md
Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design systems with components and tokens, (3) Designing dashboards, forms, navigation, or landing pages, (4) Applying accessibility standards and best practices, (5) Following platform guidelines (iOS, Android, Material Design), (6) Reviewing or improving existing Penpot designs for usability. Triggers: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landing page", "make it accessible", "design system", "component library".
npx skillsauth add em-jones/staccato-toolkit penpot-uiux-designInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create professional, user-centered designs in Penpot using the penpot/penpot-mcp MCP server and proven UI/UX principles.
| Tool | Purpose |
| ---- | ------- |
| mcp__penpot__execute_code | Run JavaScript in Penpot plugin context to create/modify designs |
| mcp__penpot__export_shape | Export shapes as PNG/SVG for visual inspection |
| mcp__penpot__import_image | Import images (icons, photos, logos) into designs |
| mcp__penpot__penpot_api_info | Retrieve Penpot API documentation |
The Penpot MCP tools require the penpot/penpot-mcp server running locally. For detailed installation and troubleshooting, see setup-troubleshooting.md.
Always check if the MCP server is already available before attempting setup:
Try calling a tool first: Attempt mcp__penpot__penpot_api_info - if it succeeds, the server is running and connected. No setup needed.
If the tool fails, ask the user:
"The Penpot MCP server doesn't appear to be connected. Is the server already installed and running? If so, I can help troubleshoot. If not, I can guide you through the setup."
Only proceed with setup instructions if the user confirms the server is not installed.
# Clone and install
git clone https://github.com/penpot/penpot-mcp.git
cd penpot-mcp
npm install
# Build and start servers
npm run bootstrap
Then in Penpot:
http://localhost:4400/manifest.jsonAdd to settings.json:
{
"mcp": {
"servers": {
"penpot": {
"url": "http://localhost:4401/sse"
}
}
}
}
| Issue | Solution |
| ----- | -------- |
| Plugin won't connect | Check servers are running (npm run start:all in penpot-mcp dir) |
| Browser blocks localhost | Allow local network access prompt, or disable Brave Shield, or try Firefox |
| Tools not appearing in client | Restart VS Code/Claude completely after config changes |
| Tool execution fails/times out | Ensure Penpot plugin UI is open and shows "Connected" |
| "WebSocket connection failed" | Check firewall allows ports 4400, 4401, 4402 |
| Task | Reference File | | ---- | -------------- | | MCP server installation & troubleshooting | setup-troubleshooting.md | | Component specs (buttons, forms, nav) | component-patterns.md | | Accessibility (contrast, touch targets) | accessibility.md | | Screen sizes & platform specs | platform-guidelines.md |
mcp__penpot__execute_code with penpotUtils.shapeStructure() to see hierarchypenpotUtils.findShapes() to locate elements by type or namepenpot.createBoard(), penpot.createRectangle(), penpot.createText() etc.addFlexLayout() for responsive containersmcp__penpot__export_shape to visually check your workBefore creating designs, determine if the user has an existing design system:
// Discover existing design patterns in current file
const allShapes = penpotUtils.findShapes(() => true, penpot.root);
// Find existing colors in use
const colors = new Set();
allShapes.forEach(s => {
if (s.fills) s.fills.forEach(f => colors.add(f.fillColor));
});
// Find existing text styles (font sizes, weights)
const textStyles = allShapes
.filter(s => s.type === 'text')
.map(s => ({ fontSize: s.fontSize, fontWeight: s.fontWeight }));
// Find existing components
const components = penpot.library.local.components;
return { colors: [...colors], textStyles, componentCount: components.length };
If user HAS a design system:
If user has NO design system:
width/height are READ-ONLY → use shape.resize(w, h)parentX/parentY are READ-ONLY → use penpotUtils.setParentXY(shape, x, y)insertChild(index, shape) for z-ordering (not appendChild)dir="column" or dir="row"text.resize(), reset growType to "auto-width" or "auto-height"Always check existing boards before creating new ones to avoid overlap:
// Find all existing boards and calculate next position
const boards = penpotUtils.findShapes(s => s.type === 'board', penpot.root);
let nextX = 0;
const gap = 100; // Space between boards
if (boards.length > 0) {
// Find rightmost board edge
boards.forEach(b => {
const rightEdge = b.x + b.width;
if (rightEdge + gap > nextX) {
nextX = rightEdge + gap;
}
});
}
// Create new board at calculated position
const newBoard = penpot.createBoard();
newBoard.x = nextX;
newBoard.y = 0;
newBoard.resize(375, 812);
Board spacing guidelines:
Use these defaults only when user has no design system. Always prefer user's tokens if available.
| Token | Value | Usage |
| ----- | ----- | ----- |
| spacing-xs | 4px | Tight inline elements |
| spacing-sm | 8px | Related elements |
| spacing-md | 16px | Default padding |
| spacing-lg | 24px | Section spacing |
| spacing-xl | 32px | Major sections |
| spacing-2xl | 48px | Page-level spacing |
| Level | Size | Weight | Usage | | ----- | ---- | ------ | ----- | | Display | 48-64px | Bold | Hero headlines | | H1 | 32-40px | Bold | Page titles | | H2 | 24-28px | Semibold | Section headers | | H3 | 20-22px | Semibold | Subsections | | Body | 16px | Regular | Main content | | Small | 14px | Regular | Secondary text | | Caption | 12px | Regular | Labels, hints |
| Purpose | Recommendation | | ------- | -------------- | | Primary | Main brand color, CTAs | | Secondary | Supporting actions | | Success | #22C55E range (confirmations) | | Warning | #F59E0B range (caution) | | Error | #EF4444 range (errors) | | Neutral | Gray scale for text/borders |
┌─────────────────────────────┐
│ Status Bar (44px) │
├─────────────────────────────┤
│ Header/Nav (56px) │
├─────────────────────────────┤
│ │
│ Content Area │
│ (Scrollable) │
│ Padding: 16px horizontal │
│ │
├─────────────────────────────┤
│ Bottom Nav/CTA (84px) │
└─────────────────────────────┘
┌──────┬──────────────────────────────────┐
│ │ Header (64px) │
│ Side │──────────────────────────────────│
│ bar │ Page Title + Actions │
│ │──────────────────────────────────│
│ 240 │ Content Grid │
│ px │ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ │
│ │ │Card │ │Card │ │Card │ │Card │ │
│ │ └─────┘ └─────┘ └─────┘ └─────┘ │
│ │ │
└──────┴──────────────────────────────────┘
Before finalizing any design:
Use these validation approaches with mcp__penpot__execute_code:
| Check | Method |
| ----- | ------ |
| Elements outside bounds | penpotUtils.analyzeDescendants() with isContainedIn() |
| Text too small (<12px) | penpotUtils.findShapes() filtering by fontSize |
| Missing contrast | Call mcp__penpot__export_shape and visually inspect |
| Hierarchy structure | penpotUtils.shapeStructure() to review nesting |
Use penpot.generateStyle(selection, { type: 'css', includeChildren: true }) via mcp__penpot__execute_code to extract CSS from designs.
tools
<!--VITE PLUS START--> # Using Vite+, the Unified Toolchain for the Web This project is using Vite+, a unified toolchain built on top of Vite, Rolldown, Vitest, tsdown, Oxlint, Oxfmt, and Vite Task. Vite+ wraps runtime management, package management, and frontend tooling in a single global CLI called `vp`. Vite+ is distinct from Vite, but it invokes Vite through `vp dev` and `vp build`. ## Vite+ Workflow `vp` is a global binary that handles the full development lifecycle. Run `vp help` to pr
development
Guide for building performant data tables. Uses tanstack-table for table logic (sorting, filtering, pagination) and tanstack-virtual for rendering large datasets efficiently.
development
Expert guidance for building observable, expressive, and fault-tolerant TypeScript applications using the effect-ts/effect ecosystem. Covers Effect<A, E, R> type, error management, dependency injection via Layers, observability (logging, metrics, tracing), concurrency with Fibers, retry/scheduling, Schema validation, Streams, and Sinks.
tools
Complete E2E (end-to-end) and integration testing skill for TypeScript/NestJS projects using Jest, real infrastructure via Docker, and GWT pattern. ALWAYS use this skill when user needs to: **SETUP** - Initialize or configure E2E testing infrastructure: - Set up E2E testing for a new project - Configure docker-compose for testing (Kafka, PostgreSQL, MongoDB, Redis) - Create jest-e2e.config.ts or E2E Jest configuration - Set up test helpers for database, Kafka, or Redis - Configure .env.e2e environment variables - Create test/e2e directory structure **WRITE** - Create or add E2E/integration tests: - Write, create, add, or generate e2e tests or integration tests - Test API endpoints, workflows, or complete features end-to-end - Test with real databases, message brokers, or external services - Test Kafka consumers/producers, event-driven workflows - Working on any file ending in .e2e-spec.ts or in test/e2e/ directory - Use GWT (Given-When-Then) pattern for tests **REVIEW** - Audit or evaluate E2E tests: - Review existing E2E tests for quality - Check test isolation and cleanup patterns - Audit GWT pattern compliance - Evaluate assertion quality and specificity - Check for anti-patterns (multiple WHEN actions, conditional assertions) **RUN** - Execute or analyze E2E test results: - Run E2E tests - Start/stop Docker infrastructure for testing - Analyze E2E test results - Verify Docker services are healthy - Interpret test output and failures **DEBUG** - Fix failing or flaky E2E tests: - Fix failing E2E tests - Debug flaky tests or test isolation issues - Troubleshoot connection errors (database, Kafka, Redis) - Fix timeout issues or async operation failures - Diagnose race conditions or state leakage - Debug Kafka message consumption issues **OPTIMIZE** - Improve E2E test performance: - Speed up slow E2E tests - Optimize Docker infrastructure startup - Replace fixed waits with smart polling - Reduce beforeEach cleanup time - Improve test parallelization where safe Keywords: e2e, end-to-end, integration test, e2e-spec.ts, test/e2e, Jest, supertest, NestJS, Kafka, Redpanda, PostgreSQL, MongoDB, Redis, docker-compose, GWT pattern, Given-When-Then, real infrastructure, test isolation, flaky test, MSW, nock, waitForMessages, fix e2e, debug e2e, run e2e, review e2e, optimize e2e, setup e2e