AC

ashutos1997/claude-design-auditor-skill

Developer tools
91 stars Quality 47 Trend 19

A Claude skill that audits designs against 19 professional design rules.

Overview

A Claude skill that audits designs against — built for developers, non-designers, and anyone who wants expert design validation without needing to know the rules themselves. Works with (via Figma MCP), (HTML/CSS/React/Vue), , , and written descriptions. Supports . Compatible with , , and other agents that support SKILL.md-based skills. Drop in a Figma link, paste your CSS, upload a screenshot, or share a wireframe — Design Auditor checks your work against 19 categories of design rules and gives you: - A with per-category breakdown (with mini bar chart per row) - A separate (WCAG coverage across Cat 2, 6, 7, 15, 16) - A separate (dark patterns and manipulative design across Cat 18) - A separate (Cat 19 — H1/H2/H3/H6/H7/H10, with Nielsen cross-reference for H4/H5/H8/H9) - A for legal/compliance violations (WCAG AA, GDPR, PECR) — separate from Critical issues - Issues ranked by severity (🚫 Blocker / 🔴 Critical / 🟡 Warning / 🟢 Tip) - — every failing color pair annotated with the...

README

🇰🇷 한국어 버전 →

🎨 Design Auditor — Claude Skill

A Claude skill that audits designs against 19 professional design categories — built for developers, non-designers, and anyone who wants expert design validation without needing to know the rules themselves.

Works with Figma files (via Figma MCP), code (HTML/CSS/React/Vue), screenshots, wireframes, and written descriptions. Supports English and Korean.

Compatible with Claude, Manus, and other agents that support SKILL.md-based skills.


What It Does

Drop in a Figma link, paste your CSS, upload a screenshot, or share a wireframe — Design Auditor checks your work against 19 categories of design rules and gives you:

  • A score out of 100 with per-category breakdown (with mini bar chart per row)
  • A separate Accessibility Score (WCAG coverage across Cat 2, 6, 7, 15, 16)
  • A separate Ethics Score (dark patterns and manipulative design across Cat 18)
  • A separate Usability Score (Cat 19 — H1/H2/H3/H6/H7/H10, with Nielsen cross-reference for H4/H5/H8/H9)
  • A 🚫 Blocker tier for legal/compliance violations (WCAG AA, GDPR, PECR) — separate from Critical issues
  • Issues ranked by severity (🚫 Blocker / 🔴 Critical / 🟡 Warning / 🟢 Tip)
  • Color blindness context — every failing color pair annotated with the affected blindness type
  • SVG accessibility checks — decorative vs. meaningful SVG patterns, aria-hidden, role=“img”
  • Design System detection — MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap (system-specific fixes)
  • Figma Auto Layout scan — detects frames using manual positioning where Auto Layout should be used
  • Plain-language explanations of why each rule matters
  • “Teach Me” mode — explains the design principles behind your top 3 issues, not just the fixes
  • An Issue Priority Matrix — every issue plotted by effort vs. impact
  • Before/after code diffs when fixing issues in HTML/CSS/React/Vue
  • Direct fixes in your Figma file via Figma MCP
  • Figma Code Connect — detects design-to-code mapping gaps (get_code_connect_suggestions)
  • Wireframe to Spec — converts wireframes into annotated dev-ready specs
  • Visual audit report exportable to Canva for stakeholder sharing
  • Developer handoff report — CSS spec table, a11y checklist, critical fixes
  • Export report as Markdown — ready for Notion, GitHub, Linear, or Jira

The 19 Audit Categories

# Category What It Checks
1 Typography Hierarchy, font count, size, line height, contrast
2 Color & Contrast WCAG ratios, semantic color use, palette consistency
3 Spacing & Layout 8-point grid, proximity, alignment, whitespace
4 Visual Hierarchy Primary action clarity, reading patterns, size/contrast mapping
5 Consistency Component reuse, icon families, corner radius, interaction states
6 Accessibility (A11y / WCAG) Touch targets, focus states, alt text, form labels, reading order
7 Forms & Inputs Labels, sizing, validation timing, error placement, submit states
8 Motion & Animation Purpose, duration, easing, reduced-motion support
9 Dark Mode Not just inverted, surface elevation, saturation, icon legibility
10 Responsive & Adaptive Breakpoints, overflow, touch targets, type scaling
11 Loading, Empty & Error States Skeletons, empty state anatomy, error levels, success confirmation, Peak-End Rule, Goal Gradient progress checks
12 Content & Microcopy Button labels, error messages, tone consistency, terminology
13 Internationalization & RTL Text expansion, RTL mirroring, locale-aware formatting, font support
14 Elevation & Shadows Shadow scale, elevation hierarchy, dark mode depth
15 Iconography Icon families, optical sizing, touch targets, meaning consistency
16 Navigation Patterns Tabs, breadcrumbs, back buttons, mobile nav, active states
17 Design Tokens & Variables Semantic naming, hardcoded values, dark mode token swapping
18 Ethical Design & Dark Patterns Confirmshaming, false urgency, pre-checked consent, CTA hierarchy inversion, privacy zuckering, hidden costs, decoy pricing, manipulative anchoring, and 17 more manipulative patterns across 6 groups — including a Regulatory Compliance Baseline (cookie consent, subscription disclosure, privacy at collection, cancellation policy, age gates, accessibility legal status)
19 Nielsen’s 10 Usability Heuristics Rules Nielsen’s 10 Usability Heuristics are the most widely used framework for evaluating interface usability. They were developed by Jakob Nielsen and are grounded in decades of usability research

Who It’s For

  • Developers building UIs who don’t have a design background
  • Designers who want a fast second opinion or WCAG check
  • Teams using Figma MCP or VS Code who want design validation in their workflow
  • Product managers and founders who want to ship ethical, accessible products
  • Anyone who’s ever wondered “does this look right?”

How to Install

  1. Download design-auditor.skill from the releases page
  2. Go to Claude.ai → Customize → Skills
  3. Click Upload skill and select the file
  4. Done — the skill is now active in your conversations

How to Use

Once installed, just talk to Claude naturally:

English:

"Check my design" → choose scope (full / quick / custom), then audit
"Is this accessible?" → accessibility-focused audit
"Review my form" → partial audit, relevant categories only
"Does this follow WCAG?" → contrast & a11y audit
"Check my Figma file: [link]" → Figma MCP audit
"Any dark patterns here?" → ethics audit
"Wireframe to spec" → annotated dev-ready spec from wireframe

Korean:

"디자인 검토해줘" → 전체 감사
"접근성 확인해줘" → 접근성 중심 감사
"내 디자인 괜찮아 보여?" → 전체 감사
"UI 검토해줘" → 전체 감사
"색상 대비 확인해줘" → 색상 및 접근성 감사
"와이어프레임 스펙 출력해줘" → 와이어프레임 스펙 모드

Example Output

## 🔍 Design Audit Report

**Input:** Checkout flow · 3 frames
**Type:** Figma MCP
**Confidence:** 🟢 High
**Component health:** 71% coverage · 2 detached instances · 8 unnamed layers
**Code Connect:** 8 components mapped · 3 unmapped

### Overall Score: 62/100
100 − (1 × 🚫 12) − (2 × 🔴 8) − (4 × 🟡 4) − (2 × 🟢 1) = 62/100
A legal compliance failure and contrast issues are the main drag.

### Accessibility Score: 55/100 — significant gaps ⚠️ Contains legal compliance failures
### Ethics Score: 85/100 — minor concerns

### 🚫 Blockers (−12pts each)
- **Text contrast failure** — #aaa on white = 2.3:1 → Fix: use #595959 (7:1)
  Legal basis: WCAG 2.1 SC 1.4.3

### 🔴 Critical Issues (−8pts each)
- **Missing form labels** — placeholder-only inputs lose label on type
  → Fix: add  above each input.

### 🟡 Warnings (−4pts each)
- **Off-grid spacing** — padding: 13px → Fix: use 12px or 16px
- **CTA hierarchy inversion** — "Accept all" primary, "Reject all" grey text
  → Fix: equivalent visual weight (GDPR requirement)

Skill Structure

design-auditor/
├── SKILL.md                        — Main skill instructions (19 categories)
└── references/
    ├── typography.md               — Font rules, sizing, hierarchy, type scale algorithm
    ├── color.md                    — WCAG luminance formula, contrast, palette guidance
    ├── spacing.md                  — 8-point grid, layout, proximity, code checks
    ├── corner-radius.md            — Nested radius rule, scale, pill shapes, code checks
    ├── elevation.md                — Shadow scale, elevation hierarchy, code shadow audit
    ├── iconography.md              — Icon families, sizing, touch targets
    ├── navigation.md               — Tabs, breadcrumbs, back buttons, mobile nav, code checks
    ├── tokens.md                   — Design tokens, semantic naming, dark mode architecture
    ├── figma-mcp.md                — Figma MCP workflow, Code Connect, page structure, safe editing
    ├── heuristics.md               — Nielsen's 10 Usability Heuristics: H1/H2/H3/H6/H7/H10 gap coverage
    ├── states.md                   — Loading, empty, error, success states + code checks
    ├── microcopy.md                — Button labels, errors, tone, per-role audit guide
    ├── animation.md                — Easing curves, duration scales, reduced motion, code checks
    ├── i18n.md                     — RTL support, locale formatting, i18n
    └── ethics.md                   — Dark patterns, ethical design, persuasion vs manipulation

Changelog

v1.2.13

Regulatory Compliance Baseline added to Cat 18.

New: Regulatory Compliance Baseline (Cat 18 Group F) 6 cross-jurisdiction UI-detectable compliance checks — applicable across EU, US, UK, Canada, Brazil, Australia. 🚫 Blocker when a legal requirement is clearly absent, 🟡 Warning when ambiguous. Each includes a code signal and a caveat that this is a UI signal layer, not a legal audit. Full Korean translations throughout.

  • Cookie & consent banner — GDPR, PECR, CCPA: banner presence, Reject All at equal prominence to Accept All, granular consent categories
  • Subscription & auto-renewal disclosure — FTC, CMA, EU Consumer Rights: renewal frequency, amount, and cancellation method visible before confirmation
  • Privacy at point of collection — GDPR Art. 13, CCPA, PIPEDA: policy link or “why we need this” near sensitive input fields
  • Right of withdrawal / cancellation policy — EU CRD, UK CRA, FTC: policy link visible near final checkout CTA
  • Age gate for restricted content — COPPA, GDPR Art. 8, UK Age-Appropriate Design Code: verification mechanism before restricted content
  • Accessibility legal baseline — ADA/Section 508 (US), EAA (EU — mandatory June 2025), PSBAR (UK), DDA (Australia), AODA (Canada): Cat 6 Blockers carry legal weight

v1.2.12

Behavioural patterns from nudges.fyi, bug fixes, and visual report improvements.

New: 5 behavioural pattern additions

  • Overchoice Paradox → Cat 4 — 4+ equal-weight sibling actions with no primary → 🟡; 6+ → 🔴. Exempt: lists, nav menus, data tables
  • Peak-End Rule → Cat 11 — audits success/completion screens for memorability: named action, next step, positive visual signal, auto-redirect timing
  • Goal Gradient Theory → Cat 11 — detects multi-step flows with no progress bar, static fill bars, missing step totals, and aria-valuenow gaps
  • Decoy Pricing → Cat 18 Group A — 3-column pricing with one tier strictly dominated on every axis
  • Manipulative Anchoring → Cat 18 Group D — text-decoration: line-through / .was-price / .rrp patterns near current price elements

Bug fixes

  • Cat 18 pattern count updated: 20 → 22 (both READMEs)
  • Cat 6 SVG ``: added xlink:href legacy check alongside href
  • Cat 19 H1 “Multi-step progress” cross-references new Cat 11 Goal Gradient checks to avoid double-flagging
  • Scores panel: Ethics Score formula caveat added — 🔴 −15 · 🟡 −7 · 🟢 0, distinct from standard formula
  • heuristics.md separator in skill structure: - → —
  • README Cat 11 row updated to mention Peak-End Rule and Goal Gradient

Visual report improvements

  • Radar chart: binary purple/red → three-colour scale — purple (8–10) · amber (6–7) · red (≤ 5)
  • Radar chart: fallback to Score by Category table when Visualizer unavailable (EN + KR)
  • Issue Priority Matrix: Korean axis labels added — 수정 난이도 (x) · 개선 효과 (y)
  • Score by Category table: score band footnote — ≥ 8 ✅ · 5–7 🟡 · ≤ 4 🔴 (EN + KR)
  • Re-audit delta: before/after bar pair rendered via Visualizer with colour-coded delta badge
  • Teach Me mode: 3-card Visualizer layout after lessons, each card clickable via sendPrompt()

v1.2.11

Code parity, design system detection, accessibility improvements, and bug fixes.

  • Code superpowers — added 📋 Code input: blocks to Cat 4 (Visual Hierarchy), Cat 5 (Consistency), Cat 11 (States), Cat 12 (Microcopy), Cat 14 (Elevation), Cat 15 (Iconography) — completing all 19 categories
  • Design System detection — auto-detects MUI, Chakra UI, shadcn/ui, Ant Design, Radix, Bootstrap; system-specific issue types and fix paths
  • Color blindness context — every failing color pair annotated with affected blindness type (Deuteranopia, Protanopia, Tritanopia)
  • SVG accessibility — decorative aria-hidden, meaningful role="img" + ``, icon-button label checks across Cat 6 and Cat 15
  • Figma Auto Layout scan — detects frames using manual positioning where Auto Layout should be used; shown in report header
  • Accessibility Score — expanded from Cat 2/6/7/16 to Cat 2/6/7/15/16 (Cat 15 SVG checks are WCAG legal violations)
  • Nielsen cross-reference — H4/H5/H8/H9 mapped in scores panel to Cat 5/7/4/11–12
  • “Teach Me” mode — explains design principles behind top 3 issues (beginner + expert depth, full Korean)
  • Scoring formula — Blockers now explicit: 100 − (blockers × 12) − (criticals × 8) − (warnings × 4) − (tips × 1)
  • Dev Handoff Report — added missing 🟢 Tips section; Korean translation included
  • Output — mini bar column in Score by Category table; Design System + Auto Layout rows in report header; Cat 9 color-scheme meta tag check
  • Bug fixes — category count “17” → “19” throughout; Cat 18/19 numbering corrected; i19n.md → i18n.md; Korean README category count corrected

v1.2.10

Dev Handoff Report, Wireframe to Spec — restructured. Korean coverage for both.

Dev Handoff Report restructured:

  • ━━━ dividers between all sections for consistent visual separation
  • Blockers separated into their own section (🚫 BLOCKERS — fix before any other work) above Critical Fixes — previously grouped together
  • All four scores in the metadata table: Overall, A11y, Ethics, Usability (with conditional notes for Ethics and Usability)
  • Code Connect mapping table included in template
  • Consistent ━━━-wrapped footer

Wireframe to Spec restructured:

  • All 8 sections now have ━━━ dividers with emoji headers (📐 📏 🔤 🧩 ✍️ 🖱️ ♿ ❓)
  • Context notes moved into section headers directly after each ━━━ block, instead of scattered inline

Korean support added for both:

  • Dev Handoff Report — Korean note block: title, all 6 field labels, all 7 section headers, all 12 table column headers, footer
  • Wireframe to Spec — bilingual footer lines + Korean note block: title, field labels, all 8 section headers with context notes, table column headers

README:

  • v1.0.0–v1.2.4 changelog entries collapsed into a `

Contributing

Found a design rule that should be in here? Open an issue or PR.

Areas that could use expansion:

  • UX flow analysis & information architecture
  • Data visualization & charts
  • Native mobile (iOS/Android) specific patterns
  • Print / PDF layout rules

License

MIT — use it, fork it, build on it.


Built with Claude · Skill format by Anthropic

View the full README on GitHub

Recommended Tools

Try a different keyword or remove a filter.

Install

npx skillfish add ashutos1997/claude-design-auditor-skill
New to MCP? Start with the mcpskill.org guide →