Not in the top 1,000 by GitHub stars
Ashutos1997/claude-design-auditor-skill
A Claude skill that audits designs against 19 professional design rules.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e7a1f3153d8e
No earlier version was observed for comparison.
93GitHub stars
4stars in 7 days
1skill in this repository
0commits in 30 days
Heat
3.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
design-auditor
When your agent uses it
Audit designs against 19 rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Auto-detects framework and design system (MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap). Runs code superpowers across all 19 categories: aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing, states, microcopy, elevation, iconography/SVG. Flags color blindness risk. Audits dark patterns, ethical design, Nielsen's heuristics. Outputs before/after diffs, developer handoff reports, wireframe-to-spec. English and Korean. Triggers on: check my design, review my UI, audit my layout, is this accessible, design review, color contrast, WCAG, a11y, pixel perfect, Figma audit, CSS check, dark patterns, is this GDPR compliant, is this manipulative, is my form accessible, is my dark mode correct, wireframe to spec, heuristic review, Nielsen audit, usability heuristics, 디자인 검토, 접근성 확인, 색상 대비, 다크 패턴, 와이어프레임 스펙.
What it loads into context
Frontmatter
257 tokensAlways available to the agent
SKILL.md
38,011 tokensWhen the skill is activated
Reference documents
64,868 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: Language Detection & Beginner Check (Always Do This First)
- Tone Guidelines (Apply Throughout Every Step)
- Step 1: Gather the Design
- Figma MCP Workflow
- Step 1.5: Set Confidence Level — and act on it
- Step 1.6: Code Input Extraction (HTML / CSS / React / Vue)
- Step 1.7: Code Fix Output Format
- Step 2: Run the Design Audit
- 📐 Design Spec — [Component/Screen Name]
Files
README.mddoc28,935 bytesREADME_KR.mddoc20,040 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesSKILL.mdcore160,297 bytesreferences/animation.mddoc12,210 bytesreferences/color.mddoc9,279 bytesreferences/corner-radius.mddoc11,373 bytesreferences/elevation.mddoc8,379 bytesreferences/ethics.mddoc48,686 bytesreferences/figma-mcp.mddoc13,269 bytesreferences/heuristics.mddoc32,815 bytesreferences/i18n.mddoc8,723 bytesreferences/iconography.mddoc6,952 bytesreferences/microcopy.mddoc10,450 bytesreferences/navigation.mddoc11,928 bytesreferences/spacing.mddoc11,377 bytesreferences/states.mddoc12,144 bytesreferences/tokens.mddoc9,639 bytesreferences/typography.mddoc9,164 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- design-auditor
Repository facts
- License
- No license detected
- Created
- Mar 4, 2026
- Last pushed
- May 17, 2026
- Forks
- 16
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 33 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 15 network referencesin 5 files: README.md:78 README_KR.md:78 SKILL.md:75 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 15 signals by file
README.md
- Network accessline 78
1. Download [`design-auditor.skill`](../../releases/latest) from the releases page 2. Go to [Claude.ai](https://claude.ai) → **Customize** → **Skills** - Network accessline 79
2. Go to [Claude.ai](https://claude.ai) → **Customize** → **Skills** - Network accessline 309
| URL Type | Confidence | How it's handled | |---|---|---| | Live website (`https://...`) | 🟡 Medium | `web_fetch`, login handling, multi-page offer | - Network accessline 310
|---|---|---| | Live website (`https://...`) | 🟡 Medium | `web_fetch`, login handling, multi-page offer | | Vercel / Netlify preview | 🟡 Medium | Same as live website | - Network accessline 311
| Live website (`https://...`) | 🟡 Medium | `web_fetch`, login handling, multi-page offer | - Network accessline 504
*Built with [Claude](https://claude.ai) · Skill format by [Anthropic](https://anthropic.com)*
README_KR.md
- Network accessline 78
1. 릴리즈 페이지에서 [`design-auditor.skill`](../../releases/latest) 다운로드 2. [Claude.ai](https://claude.ai) → **커스터마이즈** → **스킬** - Network accessline 79
2. [Claude.ai](https://claude.ai) → **커스터마이즈** → **스킬** - Network accessline 108
| URL 유형 | 신뢰도 | 처리 방식 | |---|---|---| | 라이브 웹사이트 (`https://...`) | 🟡 보통 | web_fetch, 로그인 처리, 다중 페이지 제안 | - Network accessline 109
|---|---|---| | 라이브 웹사이트 (`https://...`) | 🟡 보통 | web_fetch, 로그인 처리, 다중 페이지 제안 | | Vercel / Netlify 프리뷰 | 🟡 보통 | 라이브 웹사이트와 동일 | - Network accessline 110
| 라이브 웹사이트 (`https://...`) | 🟡 보통 | web_fetch, 로그인 처리, 다중 페이지 제안 | - Network accessline 327
*[Claude](https://claude.ai)로 제작 · 스킬 형식: [Anthropic](https://anthropic.com)*
SKILL.md
- Network accessline 75
#### Live Website URL (`https://domain.com/...`)
references/color.md
- Network accessline 59
**Check tool**: During an audit, the inline **Contrast Checker** widget renders automatically when a contrast failure is found — it pre-populates the failing pair, shows all 5 WCAG levels live, and calculates the nearest passing hex fix. Fo
references/figma-mcp.md
- Network accessline 14
input: { shortlink: "https://fig.com/abc123" }
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 15 facts
- Network access in prose of documentationREADME.md:78Low confidence
- Network access in prose of documentationREADME.md:79Low confidence
- Network access in prose of documentationREADME.md:309Low confidence
- Network access in prose of documentationREADME.md:310Low confidence
- Network access in prose of documentationREADME.md:311Low confidence
- Network access in prose of documentationREADME.md:504Low confidence
- Network access in prose of documentationREADME_KR.md:78Low confidence
- Network access in prose of documentationREADME_KR.md:79Low confidence
- Network access in prose of documentationREADME_KR.md:108Low confidence
- Network access in prose of documentationREADME_KR.md:109Low confidence
- Network access in prose of documentationREADME_KR.md:110Low confidence
- Network access in prose of documentationREADME_KR.md:327Low confidence
- Network access in prose of the SKILL.mdSKILL.md:75Low confidence
- Network access in prose of documentationreferences/color.md:59Low confidence
- Network access in code of documentationreferences/figma-mcp.md:14Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
