ui-ux-audit

Mandatory audit workflow for UI/UX changes that reads current state FIRST, checks for redundancy, respects clean design philosophy, and identifies genuine gaps before implementation. Auto-invoked when user mentions UI, UX, design, layout, homepage, page improvements, visual changes, or interface modifications.

Best use case

ui-ux-audit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Mandatory audit workflow for UI/UX changes that reads current state FIRST, checks for redundancy, respects clean design philosophy, and identifies genuine gaps before implementation. Auto-invoked when user mentions UI, UX, design, layout, homepage, page improvements, visual changes, or interface modifications.

Teams using ui-ux-audit 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

$curl -o ~/.claude/skills/ui-ux-audit/SKILL.md --create-dirs "https://raw.githubusercontent.com/WomenDefiningAI/claude-code-skills/main/skills/ui-ux-audit/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/ui-ux-audit/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How ui-ux-audit Compares

Feature / Agentui-ux-auditStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Mandatory audit workflow for UI/UX changes that reads current state FIRST, checks for redundancy, respects clean design philosophy, and identifies genuine gaps before implementation. Auto-invoked when user mentions UI, UX, design, layout, homepage, page improvements, visual changes, or interface modifications.

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

<!--
Created by: Madina Gbotoe (https://madinagbotoe.com/)
Project: Claude Code Skills - Professional Development Toolkit
Version: 1.0
Created: October 28, 2025
Last Updated: October 29, 2025
License: MIT License
Attribution Required: Yes - Include author name and link when sharing/modifying
GitHub: https://github.com/mgbotoe/claude-code-share
Find latest version: https://github.com/mgbotoe/claude-code-share/tree/main/claude-code-skills/ui-ux-audit

Purpose: UI/UX Audit skill - Prevents redundant implementations by auditing current state before UI/UX changes
-->

# UI/UX Audit Skill

## 🚨 CRITICAL: This Skill Runs BEFORE Implementation

**Purpose:** Prevent redundant implementations and cluttered designs by auditing current state FIRST.

**When to invoke:** Automatically when user mentions:
- UI/UX work: "improve UI", "enhance UX", "better design", "update layout"
- Page work: "fix homepage", "improve page", "update interface", "redesign"
- Visual changes: "add visual elements", "enhance visuals", "improve appearance"
- Component work: "add component", "new feature", "improve section"
- General improvements: "make it better", "improve experience", "enhance site"

**Order of execution:**
1. ✅ This skill runs FIRST (audit phase)
2. Then present findings to user
3. Then optionally invoke ui-ux-designer agent (design critique)
4. Then implement approved changes

---

## Mandatory Audit Process (READ FIRST, IMPLEMENT SECOND)

### Step 1: Read Current State (Non-Negotiable)

**Before making ANY recommendations, read these files:**

```bash
# Target page file
Read: src/app/[target-page]/page.tsx

# Related components (if modifying existing sections)
Read: src/components/sections/[component].tsx

# Related data files
Read: src/data/[related-data].tsx
Read: src/data/page-content/[page]-content.ts

# Check for existing similar functionality
Grep: Search for keywords related to proposed feature
```

**Example:**
```markdown
User: "Improve homepage"

MUST READ FIRST:
- src/app/page.tsx
- src/components/sections/Hero.tsx
- src/data/page-content/home-content.ts

THEN analyze what EXISTS before proposing anything
```

### Step 2: Document What EXISTS (Evidence-Based)

**Create inventory of current state:**

```markdown
## Current State Audit: [Page Name]

### Existing Components
- Component 1: [Description, location, purpose]
- Component 2: [Description, location, purpose]

### Existing Data Display
- Portfolio metrics: [Where shown, format]
- CTAs: [Location, text, purpose]
- Content sections: [List all sections]

### Design Characteristics
- Layout: [Grid, flex, columns]
- White space: [Generous, tight, balanced]
- Information density: [Minimal, moderate, dense]
- Visual style: [Clean, busy, colorful, minimal]

### Evidence
[Show actual code snippets proving what exists]
```

### Step 3: Redundancy Check (Critical)

**Before proposing ANY addition, verify:**

- [ ] Is this data already displayed elsewhere on the page?
- [ ] Does similar functionality exist in different form?
- [ ] Would this duplicate existing content?
- [ ] Would this clutter a clean design?
- [ ] Is information shown more than once?

**Anti-Patterns to Avoid (from October 2025 lessons):**

❌ **Portfolio Visualization** when impact cards already show portfolio breakdown
❌ **Large AI Assistant card** when primary CTAs already exist in hero
❌ **Metric sidebars** on document-style pages (like /brief)
❌ **Dashboards** on intentionally minimal pages (like /ai-lab)
❌ **Duplicate data displays** in multiple sections
❌ **Bulk additions** without clear value proposition

### Step 4: Identify GENUINE Gaps (Not Assumed Gaps)

**Only propose additions for:**

✅ **Missing functionality** (proven by code audit)
✅ **Genuine UX problems** (demonstrated, not assumed)
✅ **Clear value add** (specific benefit articulated)
✅ **Respects clean design** (doesn't add bulk)

**Template:**
```markdown
## Genuine Gaps Identified

### Gap 1: [Specific missing element]
- Evidence: [Code shows this doesn't exist]
- User need: [Why user needs this]
- Value: [Specific benefit]
- Simple solution: [Minimal approach]
- No redundancy: [Confirmed doesn't duplicate X]

### Gap 2: [Next gap]
...
```

### Step 5: Design Philosophy Check

**This portfolio has a CLEAN, MINIMAL aesthetic by design:**

Check against these principles:
- [ ] Simple, scannable layouts
- [ ] Strategic use of white space
- [ ] Information shown ONCE, not repeated
- [ ] Document-style pages stay document-like
- [ ] No bulk additions without clear need

**Questions to ask:**
- Does this ADD value or just ADD BULK?
- Is this the SIMPLEST solution?
- Does this respect the existing clean design?
- Would this survive user review or get reverted?

---

## Audit Output Template

**Present findings in this format:**

```markdown
# UI/UX Audit Report: [Page Name]

## Current State Summary
[2-3 sentences describing current design]

## What Already EXISTS
1. [Component/feature]: [Description with code location]
2. [Component/feature]: [Description with code location]
3. [Component/feature]: [Description with code location]

Evidence: [Code snippets proving these exist]

## Redundancy Check Results
✅ No redundancy detected: [Explain]
OR
⚠️ Potential redundancy: [Show what duplicates what]

## Genuine Gaps Identified
### Priority 1: [Most important gap]
- Evidence: [Why this is missing]
- User impact: [Specific problem it solves]
- Proposed solution: [Minimal approach]
- No redundancy: [Confirmed]

### Priority 2: [Next gap]
...

## NOT Recommended (Would Create Redundancy)
❌ [Proposed feature]: Already exists as [existing feature]
❌ [Proposed feature]: Would duplicate [existing data]

## Design Philosophy Compliance
✅ Respects clean, minimal aesthetic
✅ Adds value without adding bulk
✅ No information duplication
OR
⚠️ Concerns: [List any design philosophy violations]

## Recommendation
**Recommended:** Implement Priority 1 gap ([brief description])
**Not Recommended:** [List features that would add redundancy]

**Next Steps:**
1. User review of findings
2. (Optional) Invoke ui-ux-designer agent for design critique
3. Implement approved changes incrementally
```

---

## Verification Checklist

**Before completing audit, verify:**

- [ ] Did I read all target page/component files FIRST?
- [ ] Did I document what EXISTS (not what I assume is missing)?
- [ ] Did I check for redundancy systematically?
- [ ] Did I identify GENUINE gaps (not assumed gaps)?
- [ ] Did I verify no information duplication?
- [ ] Does recommendation respect clean, minimal design?
- [ ] Did I propose SIMPLEST solution?
- [ ] Would this survive user review?

**If any answer is NO, STOP and reassess.**

---

## Example: Good vs. Bad Audit

### ❌ BAD Audit (What NOT to do)

```markdown
User: "Improve homepage"

Bad Response:
"I recommend adding:
1. Portfolio visualization showing $156M breakdown
2. Large dashboard with metrics
3. Section transitions between content
4. Enhanced testimonials with animations"

Problem: Didn't read current state, didn't check for redundancy
```

### ✅ GOOD Audit (What TO do)

```markdown
User: "Improve homepage"

Good Response:
"Let me audit the current homepage first..."

[Reads src/app/page.tsx]

"Current State Audit:

What EXISTS:
- Impact cards already display portfolio breakdown ($156M, $91M, etc.)
- Hero has primary CTAs (View Work, See Skills, Get In Touch)
- Testimonials section exists
- EKG dividers separate sections

Redundancy Check:
⚠️ Adding portfolio visualization would DUPLICATE impact card data

GENUINE Gap:
✅ No CTA after testimonials section (natural conversion point)

Recommendation:
- Add single strategic CTA after testimonials
- Do NOT add portfolio visualization (redundant)
- Keep clean, minimal design

Would you like to proceed with the CTA addition?"
```

---

## Integration with CLAUDE.md Rules

This skill enforces the mandatory rules from CLAUDE.md:

1. ✅ READ FIRST, IMPLEMENT SECOND (enforced by Step 1)
2. ✅ REDUNDANCY CHECK (enforced by Step 3)
3. ✅ RESPECT DESIGN PHILOSOPHY (enforced by Step 5)
4. ✅ MANDATORY AUDIT BEFORE UI/UX WORK (this entire skill)
5. ✅ VERIFICATION CHECKLIST (enforced by final checklist)

---

## Trigger Keywords Reference

**Auto-invoke this skill when user says:**

**UI/UX Terms:**
- improve UI, enhance UX, better design, update layout
- improve user experience, enhance interface, better visuals
- redesign, refactor UI, update design, modernize
- make it look better, improve appearance, visual improvements

**Page Terms:**
- fix homepage, improve page, update page, enhance page
- homepage improvements, page redesign, layout changes
- improve landing page, better home screen

**Component Terms:**
- add component, new feature, improve section
- enhance hero, update header, improve footer
- add visualization, add dashboard, add metrics
- new UI element, add interface component

**General Improvement:**
- make it better, improve experience, enhance site
- improve portfolio, better showcase, enhance presentation
- improve conversion, better engagement, increase impact

**Question Form:**
- "How can I improve X?"
- "What should I add to X?"
- "Should I add X to the page?"

---

## Remember: This Skill Prevents the October 2025 Session Mistakes

**What went wrong that day:**
- Implemented Phase 3 UI/UX recommendations without reading pages
- Added PortfolioVisualization despite impact cards showing same data
- Added large AI Assistant card overshadowing primary CTAs
- Added bulk to AI Lab page making it "look like two pages in one"
- User had to revert everything

**This skill prevents those mistakes by:**
- Reading current state FIRST (always)
- Checking for redundancy BEFORE proposing
- Respecting clean, minimal design philosophy
- Identifying genuine gaps (not assumed gaps)
- Presenting evidence-based findings to user BEFORE implementing

---

## Supporting Files & Resources

This skill includes additional resources for comprehensive audits:

### REFERENCE.md - Detailed UX Research
**When to read:**
- Need detailed WCAG 2.1 AA requirements
- Want UX research citations (Nielsen Norman Group, etc.)
- Understanding design patterns and anti-patterns
- Deep dive into audit methodology

**Contains:**
- Left-attention pattern research (80/20 rule)
- F-pattern reading principles
- Cognitive load principles (Miller's Law, Hick's Law)
- Complete WCAG 2.1 AA requirements
- Design pattern library
- Measurement frameworks

**Read with:** `Read: [skill-directory]/REFERENCE.md`

---

### FORMS.md - Pre-Filled Templates
**When to read:**
- Starting a new audit (copy template)
- Need structured checklist format
- Want standardized audit output

**Contains:**
- Quick Audit Template (5-10 min)
- Comprehensive Audit Template (30+ min)
- Redundancy Checklist
- Gap Analysis Template
- WCAG Compliance Checklist
- Mobile Optimization Checklist
- Performance Audit Template

**Read with:** `Read: [skill-directory]/FORMS.md`

---

### resources/ - Examples & Case Studies
**When to read:**
- First-time conducting UI/UX audit
- Unsure if approach is correct
- Learning from real examples
- Training others

**Contains:**
- `examples/good-audit-example.md` - Gold standard audit
- `examples/bad-audit-example.md` - What NOT to do
- `case-studies/october-2025-incident.md` - Real incident that inspired this skill
- `README.md` - Navigation guide

**Read with:** `Read: [skill-directory]/resources/[filename]`

---

## Usage Guide for Supporting Files

### Quick Audit (< 10 minutes):
1. Use **SKILL.md** (this file) for process
2. Copy template from **FORMS.md** (Quick Audit Template)
3. Follow 5 steps, fill in template

### Comprehensive Audit (30+ minutes):
1. Use **SKILL.md** for overall process
2. Copy template from **FORMS.md** (Comprehensive Audit Template)
3. Reference **REFERENCE.md** for detailed requirements
4. Compare your work to **resources/examples/good-audit-example.md**

### Learning/Training:
1. Read **resources/examples/good-audit-example.md** (see gold standard)
2. Read **resources/examples/bad-audit-example.md** (learn what to avoid)
3. Read **resources/case-studies/october-2025-incident.md** (understand why this skill exists)
4. Practice using **FORMS.md** templates

---

## Final Note

**This is not optional.** When user mentions UI/UX work, this skill MUST run first to audit current state before any implementation begins.

The goal: Prevent redundant implementations, respect existing design, propose targeted improvements only.

**New to UI/UX audits?** Start with `resources/examples/good-audit-example.md` to see the process in action.

Related Skills

skill-contributor

5
from WomenDefiningAI/claude-code-skills

Guides contributors through adding new skills to the claude-code-skills repository via Pull Request with proper validation and documentation

skill-builder

5
from WomenDefiningAI/claude-code-skills

Guide users through creating new Claude Code Skills with proper structure, validation, and best practices

shownotes-generator

5
from WomenDefiningAI/claude-code-skills

Generate comprehensive "Shownotes" summaries from longform articles, papers, transcripts, videos, or audio content. Use when users request shownotes, episode summaries, content summaries with takeaways, or when they reference the mdynotes.com format. Creates structured summaries with metadata, hooks, takeaways, quotes, and references.

frontend-ui

5
from WomenDefiningAI/claude-code-skills

Create aesthetically pleasing, visually distinctive frontend UIs using research-backed prompting strategies from Anthropic's frontend aesthetics cookbook

feature-orchestrator

5
from WomenDefiningAI/claude-code-skills

Research-backed feature implementation workflow enforcing gap analysis, incremental planning, agent coordination, and continuous integration best practices. Auto-invoked for ALL feature implementation requests to prevent code duplication and ensure CLAUDE.md compliance.

code-reviewer

5
from WomenDefiningAI/claude-code-skills

Research-backed code review skill with OWASP Top 10 security checks, SAST tool integration (SonarQube, CodeQL, Snyk), performance pattern detection, and automated quality standards enforcement. Auto-invoked for code review, security audit, PR analysis, and bug checking. Implements 2025 best practices with 92% faster vulnerability remediation.

code-refactoring

5
from WomenDefiningAI/claude-code-skills

Proactively monitors file sizes and suggests refactoring BEFORE editing. Auto-invoked when files exceed size thresholds (150/200/300 lines) or complexity patterns detected. Works across JavaScript/TypeScript, Python, and general codebases. Prevents accidental complexity growth.

cairo-auditor

9
from cartridge-gg/nums

Systematic Cairo/Starknet security audit workflow with deterministic preflight, parallel vector specialists, adversarial reasoning, and strict false-positive gating.

skill-audit

9
from exiao/skills

Audit and score any skill against best practices. Use when: audit this skill, review this skill, check this skill, score this skill, is this skill good, skill health check, skill review, rate this skill. Takes a skill directory path, evaluates structure/content/patterns against a checklist, and outputs a scorecard with specific fixes.

audit

9
from exiao/skills

Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.

aso-audit

9
from exiao/skills

When the user wants a full ASO health audit, review their App Store listing quality, or diagnose why their app isn't ranking. Also use when the user mentions "ASO audit", "ASO score", "why am I not ranking", "listing review", or "optimize my app store page". For keyword-specific research, see keyword-research. For metadata writing, see metadata-optimization.

security-auditor

9
from cofin/flow

Use when reviewing authentication, authorization, user input, secrets, API keys, database queries, file uploads, session management, external API calls, OWASP risks, or data handling attack surface.