design-md
Skill0 starsChanged 2 months agoMITView on GitHub
Extracts Google-spec DESIGN.md from any URL via static HTML/CSS analysis (no headless browser). Outputs tokens.json, preview.html, lint report, optional drift vs local DESIGN.md.
- Reads credentials
- Installs packages
68 other projects use a version of this.
Adopted by
Most recently taken up by
- YKUNAKORN/power-app-yamltheir own version, first seen Nov 16, 2026
- Josephbadigar/sitepeeltheir own version, first seen Nov 16, 2026
- wxxb789/hoatheir own version, first seen Nov 16, 2026
- rajdeepbhattacharyya25-pixel/agents-for-antigravity-their own version, first seen Nov 15, 2026
- CaesiumY/ko-design-mdtheir own version, first seen Nov 10, 2026
- rakaarwaky/agents-arwakytheir own version, first seen Nov 8, 2026
Used with
Projects with it also use touchdesigner-mcp, teams-meeting-pipeline and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 7 projects that use this
john-data-chenSkillteams-meeting-pipeline
Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.
Also in 9 projects that use this
mae616Skillp5js
p5.js(クリエイティブコーディング)のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。
Also in 12 projects that use this
jh941213Skilldocs-ci
문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.
Also in 3 projects that use this
jh941213Skilldocs-interfaces
API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.
Also in 3 projects that use this
Tommy-ywSkillpopular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.
Also in 11 projects that use this
- +4 more from jh941213
Other versions68 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 68
- loongclaw-ai/loongclaw★ 640same name
- bifrost-proxy/bifrost★ 168same name
- diodeme/Gold-Band★ 165same name
- jh941213/ADLC-harness★ 125same name
- jh941213/my-cc-harness★ 125same name
- jh941213/my-claude-code-asset★ 125same name
- CaesiumY/ko-design-md★ 78same name
- vobase/vobase★ 60same name
- tdimino/claude-code-minoan★ 41same name
- wundercorp/loki★ 28same name
58 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- copywriting-frameworksSkill
- format-carouselSkill
- format-hooksSkill
- format-linkedinSkill
- format-reelsSkill
- funnel-designSkill
- humanizationSkill
- launch-playbooksSkill
- offer-designSkill
- pipeline-brandSkill
- pipeline-campaignSkill
- pipeline-contentSkill
- pipeline-copySkill
- pipeline-landing-pageSkill
- pipeline-luxoSkill
- pipeline-refino-uiSkill
- pipeline-sistemaSkill
- scroll-worldSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 59 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 187
Don't add Playwright / Puppeteer / Hyperbrowser.
- Very specific: line 188
Don't call the Anthropic API directly.
- Very specific: line 189
Don't bypass the content-validation gate without --no-content-gate — thin content (bot blocks, paywalls, JS shells) wastes LLM turns.
“Common” is measured: kept by at least 6 in 10 of the 59 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/design-md — URL → DESIGN.md Pipeline
Built by Alan Nicolas (@oalanicolas) — github.com/oalanicolas
Extract a Google-spec DESIGN.md from any public URL using static analysis only — no headless browser, no Playwright, no Hyperbrowser. The cognition layer is claude -p (default) or OpenRouter Haiku.
Standalone skill. Self-contained — copy the
design-md/folder into any Claude Code project's.claude/skills/and runnpm installinside it. No host-repo coupling.
When to invoke
- User asks to "extract design from
<URL>", "get a DESIGN.md from<site>", "rip the DS from<url>", or similar - User wants drift detection: "is my DESIGN.md still aligned with
<live URL>?" - User wants
tokens.json+preview.htmlgenerated from any public site - User wants a stack/style fingerprint of an unknown site
Skip if the user wants TSX components (use /print-to-code style skills instead) or motion-only extraction.
Install
# 1. Drop the folder into your project
cp -R design-md .claude/skills/
# 2. Install local deps
cd .claude/skills/design-md && npm install
# 3. (Optional) install the lint dependency once globally so npx is offline-friendly
npx --yes @google/design.md@0.1.0 --versionThe skill only requires Node 18+. The claude -p provider needs the Claude Code CLI on PATH. The openrouter provider needs OPENROUTER_API_KEY set.
Quick run
node .claude/skills/design-md/run.cjs --url https://www.anthropic.com/Output lands under one folder per URL variant in outputs/design-md/{slug}/ (relative to your CWD). The slugger is subdomain- and path-aware so different DSes under the same company don't collide:
https://www.anthropic.com/→anthropichttps://www.shopify.com/→shopifyhttps://www.shopify.com/br/enterprise→shopify-br-enterprise(different DS from root)https://brand.acme.com/brandbook/guidelines→acme-brand-brandbook-guidelineshttps://app.linear.app/→linear-app(product UI ≠ marketing root)
www. is stripped silently; other subdomains and the first 4 path segments become qualifiers (capped at 80 chars). Root URLs of the same company are backwards-compatible (still slug to bare company name).
{company}/ ← latest "best" extraction at root
DESIGN.md ← Google-spec, with provenance comments inline
tokens.json ← parsed YAML frontmatter
extraction-log.yaml ← provenance + confidence summary (machine-readable)
lint-report.json ← @google/design.md lint output
quality-score.json ← A-F across 7 categories
preview.html ← single-file standalone (Google Fonts CDN + Prism)
style-fingerprint.json ← visual archetype classification
agent-prompt.txt ← reusable LLM prompt with extracted tokens
telemetry.json ← run timing, model, cost, reuse trace
inputs/ ← raw HTML, CSS, tokens-detected, fingerprints, prompt
history/
{YYYYMMDD-HHmmss}/ ← prior runs, archived when supersededThe latest run only stays at the company root if it scores >= the previous best (quality + confidence_high · 0.5 − lint_errors · 5). Otherwise it goes to history/{ts}/ and the previous best stays at root.
Override the outputs root via the --out flag or by setting DESIGN_MD_OUTPUTS_DIR=/abs/path (used by the scripts/*.cjs helpers).
Drift mode
Compare a live URL against a local DESIGN.md:
node .claude/skills/design-md/run.cjs \
--url https://brand.acme.com/brandbook/guidelines \
--compare apps/my-app/DESIGN.mdAdds drift-report.json + verdict in stdout: in-sync / minor-drift / notable-drift / major-drift.
Flags
| Flag | Default | Notes |
--url <url> | required | Public http(s) URL |
--out <dir> | outputs/design-md/{slug}/ (CWD-relative) | Output directory |
--prompt <file> | data/url-extract-prompt.txt (in skill) | Override LLM prompt template |
--compare <file> | — | Local DESIGN.md to drift-check against |
--no-content-gate | off | Skip the content-validation gate (R1) |
--no-llm-retry | off | CI mode — fail hard on first LLM error |
--no-reuse | off | Disable phase reuse from prior runs (force cold run) |
--provider <id> | auto | claude-cli (local) or openrouter (CI/Vercel) |
--model <id> | provider default | claude-cli → Opus 4.7; openrouter → Haiku 4.5 (allow-list enforced) |
--max-tokens <n> | 8192 | Only used by openrouter |
Environment variables
| Var | Purpose |
OPENROUTER_API_KEY | Required when --provider openrouter |
DESIGN_MD_OUTPUTS_DIR | Override outputs root for the scripts/*.cjs helpers |
DESIGN_MD_POST_HOOK | Optional Node script invoked after each successful extract (node $HOOK $outDir). Fire-and-forget — failures don't fail the extract. |
DESIGN_MD_SKIP_HOOK | Set to 1 to bypass the post-hook |
Phase reuse (default on)
Re-running the extractor on a URL with a prior fresh extract (< 24h) reuses outputs phase-by-phase from {company}/ (the current "best" run) instead of re-fetching, re-detecting, or re-calling the LLM.
| Phase | Reuse condition | Skips on hit |
fetch | {company}/inputs/page.html exists and is < 24h old | HTTP fetch + headers |
collect | Phase fetch hit AND {company}/inputs/css-collected.css exists | CSS bundle download (often 0.5–2 MB) + favicon + logo |
detect | Phase collect hit AND all 13 detection files + style-fingerprint.json exist | All regex/static analysis |
markdown | Phase fetch hit AND {company}/inputs/page.md exists | HTML → markdown conversion |
llm | Prior run telemetry has same model AND prompt content matches (path-normalized) | LLM call + retry loop |
End-of-run telemetry includes reuse.trace and a one-liner: [reuse] 5/5 phases reused from {slug} — fetch=HIT collect=HIT detect=HIT markdown=HIT llm=HIT. Pass --no-reuse for CI/auditing where each run must be deterministic from cold.
Migrating existing extracts
A one-shot script consolidates legacy {slug}-{timestamp}/ dirs into the new {company}/ layout:
# Preview migration plan
node scripts/organize.cjs --dry-run
# Apply (drops failed extracts without DESIGN.md)
node scripts/organize.cjs --apply --skip-junkBest-run selection: complete → high quality_score → high confidence_high → low lint errors → most recent.
Pipeline (8 phases)
axios.get(url)→ HTMLcheeriowalks<link rel="stylesheet">, inline<style>,style=""→ fetches and concatenates all CSS (preload +@importresolved)- Regex pass detects: hex/rgb/hsl,
font-family|size|weight,line-height,border-radius,padding|margin|gap, Google Fonts URLs. Emitsstack.json(Next.js, Tailwind, Radix, GSAP, …) andstyle-fingerprint.json(shadcn-neutral, carbon-enterprise, apple-glass, polaris-friendly, marketing-gradient, …) turndownHTML → markdown; first heading + first long paragraph become the type specimenpageCopy- Templates
data/url-extract-prompt.txtwith input file paths (HTML, CSS, page-copy, tokens-detected, css-vars, font-faces, stack-summary). Fingerprints feed prose tone — LLM matches archetype rather than producing generic descriptions claude -p <prompt> --output-format text(or OpenRouter API) — instructed to use the Write tool to emitDESIGN.mdat the resolved output path. Normalize + lint (@google/design.md@0.1.0) + retry once on max-turns / missing sections- Parse YAML frontmatter →
tokens.json. Buildextraction-log.yaml, quality score, drift report (if--compare). Embed fonts as data: URLs - Render single-file
preview.html— color swatches, typography (Google Fonts), spacing/radius scales, raw DESIGN.md (Prism CDN), audit panel with fingerprint summary
Optional Phase 9: invoke DESIGN_MD_POST_HOOK if set (fire-and-forget — failures don't fail the extract).
Exit codes
| Code | Meaning |
| 0 | Success — DESIGN.md produced, preview rendered |
| 1 | Usage error (missing --url) |
| 2 | LLM ran but DESIGN.md was not written. Check inputs/prompt.txt |
| 4 | Content-validation gate failed (bot detection / paywall / SPA shell). Override with --no-content-gate |
| 5 | LLM exhausted budget AND retry failed, OR missing required sections after retry |
| 6 | --provider openrouter chosen but OPENROUTER_API_KEY not set |
| 7 | OpenRouter HTTP error after retry exhausted |
Confidence ladder (C1)
Each top-level token in the YAML frontmatter is annotated with a provenance comment that the script grades:
| Level | Source | Example comment |
high | CSS var or @font-face | # from --swatch--clay |
medium | Non-var CSS declaration | # from h1 declaration |
low | Inferred | # inferred from primary darker variant |
Aggregated in extraction-log.yaml#confidence_summary and rendered as colored badges in the preview header.
Tests
cd .claude/skills/design-md
npm test
# or directly:
node --test lib/*.test.cjs lib/providers/*.test.cjsAnti-patterns
- Don't add Playwright / Puppeteer / Hyperbrowser. The constraint is intentional — prove static analysis + headless LLM works before adding browsers.
- Don't call the Anthropic API directly. The cognition layer is
claude -p(or OpenRouter pass-through). Provider/model policy lives inlib/llm.cjs(PROVIDER_DEFAULTS). - Don't bypass the content-validation gate without
--no-content-gate— thin content (bot blocks, paywalls, JS shells) wastes LLM turns.
References
- Spec: Google
@google/design.mdv0.1.0 - Awesome catalog: VoltAgent/awesome-design-md
- Provider docs: Claude Code · OpenRouter
Author
Alan Nicolas — @oalanicolas — github.com/oalanicolas
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

