uiux-toolkit
Comprehensive UX/UI evaluation meta-skill combining design theory and UX methodology. Use when conducting UI/UX audits, visual design reviews, accessibility compliance (WCAG 2.2), user flow analysis, responsive testing, interaction design evaluation, or design system audits. Evaluates using Nielsen's heuristics, Gestalt principles, typography theory, color theory, and modern methodologies (OOUX, JTBD, Cognitive Walkthrough).
Best use case
uiux-toolkit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Comprehensive UX/UI evaluation meta-skill combining design theory and UX methodology. Use when conducting UI/UX audits, visual design reviews, accessibility compliance (WCAG 2.2), user flow analysis, responsive testing, interaction design evaluation, or design system audits. Evaluates using Nielsen's heuristics, Gestalt principles, typography theory, color theory, and modern methodologies (OOUX, JTBD, Cognitive Walkthrough).
Teams using uiux-toolkit should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/uiux-toolkit/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How uiux-toolkit Compares
| Feature / Agent | uiux-toolkit | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Comprehensive UX/UI evaluation meta-skill combining design theory and UX methodology. Use when conducting UI/UX audits, visual design reviews, accessibility compliance (WCAG 2.2), user flow analysis, responsive testing, interaction design evaluation, or design system audits. Evaluates using Nielsen's heuristics, Gestalt principles, typography theory, color theory, and modern methodologies (OOUX, JTBD, Cognitive Walkthrough).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# UI/UX Toolkit
Professional UX/UI evaluation across 9 domains. Combines design theory w/ UX methodology. Framework-agnostic for web, mobile & desktop.
## Audit Type Selection
| Need | Load |
|------|------|
| Full UX Audit | ALL references |
| Visual Design | visual-design.md + interaction-review.md |
| Accessibility | accessibility-inspector.md |
| Usability | heuristic-audit.md + user-flow-analysis.md |
| Responsive/Mobile | responsive-behavior.md |
| Design System | design-system-audit.md |
| Content | content-ux-audit.md |
| AI Interface | ai-ux-patterns.md |
| Privacy/Ethics | privacy-ethics-audit.md |
## Sub-Workflows
| Domain | Reference | Purpose |
|--------|-----------|---------|
| Visual | `references/visual-design.md` | Hierarchy, typography, color, Gestalt, spacing |
| Heuristic | `references/heuristic-audit.md` | Nielsen's 10 + modern methods |
| A11Y | `references/accessibility-inspector.md` | WCAG 2.2 AA/AAA, keyboard, screen readers |
| Flow | `references/user-flow-analysis.md` | Task paths, friction, cognitive load |
| Responsive | `references/responsive-behavior.md` | Breakpoints, touch, RTL/LTR, PWA |
| Interactions | `references/interaction-review.md` | Micro-interactions, animations, feedback |
| Design System | `references/design-system-audit.md` | Token consistency, component audit |
| Content | `references/content-ux-audit.md` | UX writing, readability, voice & tone |
| AI/ML | `references/ai-ux-patterns.md` | Explainability, trust, error handling |
| Privacy | `references/privacy-ethics-audit.md` | Dark patterns, consent, GDPR/DSA |
## Quick Start
### 1. Define Scope
```
Audit Scope:
├── Screens: [target screens]
├── Flows: [primary tasks, conversion paths]
├── Platform: [Web/iOS/Android/Desktop/All]
├── WCAG: [A/AA/AAA]
└── Focus: [Visual/A11Y/Usability/Perf]
```
### 2. Select Type
| Type | Refs | Coverage |
|------|------|----------|
| Quick Visual | visual-design.md | Design theory |
| Quick A11Y | accessibility-inspector.md | Automated + keyboard |
| Heuristic | heuristic-audit.md | Nielsen's 10 |
| Full | All 9 refs | Complete eval |
| Focused | 2-3 refs | Targeted review |
### 3. Execute
Each ref contains checklists w/ pass/fail criteria, severity & remediation.
## Severity
| Level | Impact | Action |
|-------|--------|--------|
| 🔴 Critical | Blocks task/access | Fix immediately |
| 🟠 Major | >50% users affected | Fix before release |
| 🟡 Minor | <50% users affected | Next sprint |
| 🟢 Enhancement | Polish/delight | Backlog |
### Priority Matrix
```
HIGH FREQ
│
┌───────┼───────┐
│ MAJOR │ CRIT │
│ (P1) │ (P0) │
LOW ├───────┼───────┤ HIGH
IMP │ ENH │ MINOR │ IMP
│ (P3) │ (P2) │
└───────┼───────┘
LOW FREQ
```
### Effort
| Level | Examples |
|-------|----------|
| Low | CSS fix, alt text, label |
| Med | Component refactor, validation |
| High | Nav restructure, focus mgmt |
## Quick Checklist
```
□ Hierarchy → Importance clear? (Squint test)
□ Typography → Readable, scale, max 2-3 fonts?
□ Color → Contrast, semantic, 60-30-10?
□ Spacing → 8pt grid, consistent rhythm?
□ Gestalt → Items grouped logically?
□ Usability → Actions discoverable, feedback clear?
□ A11Y → WCAG AA, keyboard, screen reader?
□ Consistency → Design system followed?
□ Content → Clear, scannable, actionable?
□ Responsive → All breakpoints, touch-friendly?
```
## Scoring
| Grade | Criteria |
|-------|----------|
| A | Professional, polished, accessible, delightful |
| B | Solid fundamentals, minor refinements |
| C | Functional w/ notable issues |
| D | Usable w/ significant problems |
| F | Major usability/a11y failures |
## Output Format
```markdown
## UX Eval: [Component/Page]
### Scope
- Platform: [Web/iOS/Android]
- WCAG: [AA/AAA]
- Domains: [List]
### Assessment
[1-2 sentence summary + grade A-F]
### Critical (P0)
- **[Issue]**: [Desc]
- *Principle*: [violated]
- *Fix*: [rec]
- *Effort*: [L/M/H]
### Major (P1) / Minor (P2) / Enhancements (P3)
[Same format]
### Strengths
- [What works]
### Priority Actions
1. [Top fix]
2. [Second]
3. [Third]
```
## Anti-Patterns
| Pattern | Category | Sev |
|---------|----------|-----|
| Confirm-shaming | Dark | 🔴 |
| Hidden costs | Dark | 🔴 |
| Keyboard traps | A11Y | 🔴 |
| No loading feedback | Visibility | 🟠 |
| Color-only indicators | A11Y | 🟠 |
| Auto-play video+sound | Attention | 🟠 |
| Infinite scroll w/o footer | Nav | 🟡 |
## Methodologies
| Method | Focus | Use |
|--------|-------|-----|
| Cognitive Walkthrough | Task completion | Complex flows |
| OOUX | Object-noun consistency | IA |
| JTBD | Job stories | Feature validation |
| Gestalt | Visual grouping | Layout |
| Baymard | E-commerce | Shopping flows |
## Platform Testing
| Platform | Auto | Manual |
|----------|------|--------|
| Web | axe-core, Lighthouse | DevTools, keyboard |
| iOS | Accessibility Inspector | VoiceOver |
| Android | Accessibility Scanner | TalkBack |
| Design | Stark, Contrast plugins | Review |
---
Load `references/*.md` for detailed checklists & criteria.Related Skills
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-quality
Web quality optimization skills based on Google Lighthouse guidelines and Core Web Vitals. Use when asked to audit web quality, optimize performance, improve accessibility, fix SEO, apply best practices, or analyze Core Web Vitals (LCP, INP, CLS).
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
upgrade-packages-js
Safely upgrade JavaScript packages with breaking change detection, migration guidance, and automated code migrations (npm/pnpm/yarn). Cross-platform with git safety branch enforcement.
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
trailofbits-security
Security-focused static analysis and code auditing skills from Trail of Bits. Includes CodeQL deep analysis, Semgrep scanning, and SARIF result processing. Use when performing security audits, running static analysis, scanning for vulnerabilities, or processing scan results.
token-optimizer
Reduce token count in prompts, docs, and prose. Covers prompt compression (40-60% savings), doc formatting, TOON data serialization, and Strunk's prose clarity rules. Use when compressing prompts, optimizing docs for LLM context, or writing clear technical prose.
testing-automation-expert
Production-grade testing strategies for robust, maintainable systems. Covers unit/integration/E2E testing, contract testing, accessibility, mutation testing, and CI/CD patterns. Supports Python (pytest) and TypeScript (Jest/Vitest/Playwright).
test-levels
This skill explains the 3 test levels (Unit, Integration, E2E) using the "Building a Car" analogy and provides guidance on when to use each type. Includes project-specific Playwright examples.
terraform
Terraform infrastructure-as-code skills from HashiCorp. Covers HCL code generation with style conventions, testing with .tftest.hcl files, and module refactoring. Use when writing, reviewing, generating, or refactoring Terraform configurations, creating tests, or designing modules.
system-architect
System architecture skill for designing scalable, maintainable software systems. Covers microservices/monolith decisions, API design, DB selection, caching, security, and scalability planning.
swiftui-patterns
SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.