A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
Are you the author? Sign in to claim
A Claude Code SKILL for designing beautiful, consistent web pages — spec first, code second.
A Claude Code SKILL for designing beautiful, consistent web pages — spec first, code second.
Feed the SKILL a PRD, a reference URL, or a screenshot — any combination works. It produces a readable, editable, portable DESIGN.md first. Only then does it generate the web code.
The result: UI, visuals, motion, and responsiveness that all land. Consistent across pages, portable across AI tools, editable by hand.
Phase A · Understand. Extracts design cues from PRD / URL / screenshot / keywords / brand name. A graceful fallback chain keeps it working even with sparse inputs.
Phase B · Produce DESIGN.md. A full 9-section spec: color · type · component · layout · motion · depth · do's & don'ts · responsive · accessibility. Once you approve it, the spec lives in your project and can be edited by hand.
Phase C · Generate code. Strictly follows the spec. Self-audits against a 100-score quality checklist. Diff-audits when a reference URL exists.
web-design/
├── SKILL.md # the skill itself (instructions for Claude)
├── references/ # design systems, style seeds, motion library,
│ # interaction patterns, quality checklist
├── scripts/ # Playwright crawler, static token extractor,
│ # Unsplash image fetcher
└── docs/ # landing page (served by GitHub Pages)
├── index.html
├── styles.css
├── app.js
├── DESIGN.md # the page's own spec (produced by the SKILL itself)
└── images/
Clone into your Claude Code skills directory:
git clone https://github.com/KAOPU-XiaoPu/web-design ~/.claude/skills/web-design
Claude Code will auto-discover the SKILL the next time you start a session.
cd web-design/docs
python3 -m http.server 8000
# open http://localhost:8000
Opening index.html directly with file:// won't work — Google Fonts and the OGL ES module need an HTTP origin.
Motion effects on the landing page derive from work by David Haz:
Reference inspirations for the DESIGN.md structure draw from awesome-design-md (MIT).
MIT — use it, fork it, ship it.
Built with ❤️ by @KAOPU-XiaoPu
ML engineering — model training, deployment, MLOps, monitoring
DevOps practices — CI/CD, containers, monitoring, infrastructure automation
Professional skills marketplace with production-ready skills for enhanced development
Self-learning system that captures corrections and syncs them to CLAUDE.md and AGENTS.md