Analyze Stitch design projects and generate semantic DESIGN.md files as prompting source of truth.
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add google-labs-code/stitch-skills --skill design-mdCompatible with
Supported agents
Retrieves screen metadata, HTML/CSS source, and design assets from Stitch projects via MCP Server tools to extract design tokens and visual patterns
Synthesizes findings into structured DESIGN.md files covering atmosphere, color palette with hex codes, typography, component styling, and layout principles
Translates technical values (Tailwind classes, border-radius, shadows) into evocati
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiondesign-mdExecute the skills CLI command in your project's root directory to begin installation:
epx add google-labs-code/stitch-skills --skill design-mdFetches design-md from google-labs-code/stitch-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/design-md
Restart Cursor to activate design-md. Access via /design-mdin your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
tui-design
hyperb1iss/hyperskills · Frontend · tag: design
frontend-design
buildermethods/design-os · Frontend · tag: design
expo-app-design
skillcreatorai/ai-agent-skills · Frontend · tag: design
pencil-design
chiroro-jr/pencil-design-skill · Frontend · tag: design
ios-ux-design
mosif16/codex-skills · Frontend · tag: design
react-vite-best-practices
asyrafhussin/agent-skills · Frontend · same category
design-md reduced setup friction for our internal harness; good balance of opinion and flexibility.
Solid pick for teams standardizing on skills: design-md is focused, and the summary matches what you get after install.
design-md reduced setup friction for our internal harness; good balance of opinion and flexibility.
design-md is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Keeps context tight: design-md is the kind of skill you can hand to a new teammate without a long onboarding doc.
Registry listing for design-md matched our evaluation — installs cleanly and behaves as described in the markdown.
design-md has been reliable in day-to-day use. Documentation quality is above average for community skills.
We added design-md from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Solid pick for teams standardizing on skills: design-md is focused, and the summary matches what you get after install.
I recommend design-md for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 69