UX Audit

SkillAI & models

Systematic UX evaluation using Nielsen heuristics and accessibility checks. Use when reviewing UI, "is this usable", improving user experience, or pre-launch.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the UX Audit skill

What this skill tells your AI

The instructions your AI receives, as published by lev-os/agents in skills-db/design-ux/ux-audit/SKILL.md and read by ahel’s review.

Core Insight: Users don't read manuals. If it's not obvious, it's broken.

THE EXACT PROMPT

Conduct a UX audit of this [application/CLI/interface]:

1. Nielsen's 10 Usability Heuristics
2. Accessibility basics (keyboard, contrast, screen reader)
3. User flow analysis (happy path + error paths)
4. Cognitive load assessment

Produce prioritized report:
- Critical (blocking)
- Important (degraded experience)
- Suggestions (polish)

Include file:line references and concrete fixes.

Quick Check (5 min)

| Area | Status | Notes |
|------|--------|-------|
| Navigation | 🟢/🟡/🔴 | |
| Forms | 🟢/🟡/🔴 | |
| Errors | 🟢/🟡/🔴 | |
| Accessibility | 🟢/🟡/🔴 | |
| Mobile/Responsive | 🟢/🟡/🔴 | |

Nielsen's 10 Heuristics (Quick Reference)

#HeuristicKey Question
1VisibilityDoes user know what's happening?
2Real WorldFamiliar language & concepts?
3ControlCan user undo/escape?
4ConsistencySame action = same result?
5Error PreventionPrevents mistakes before they happen?
6RecognitionOptions visible vs. memorized?
7FlexibilityShortcuts for experts?
8MinimalVisual clutter removed?
9Error HelpError messages helpful?
10DocumentationHelp available when needed?

Deep dive: HEURISTICS.md


CLI-Specific Heuristics

HeuristicCLI Application
Visibility--verbose, progress bars, spinners
Real worldStandard flags (--help, --version)
ControlCtrl+C works, --dry-run available
Consistency-v short, --verbose long
Error preventionConfirmation prompts, --force
Recognition--help shows all options
FlexibilityShort + long flags, piping
MinimalClean default, verbose optional
Error helpActionable messages, suggested fixes
Documentation--help, man pages, examples

Generate checklist: ./scripts/generate-checklist.py cli


Accessibility Quick Check

The Big 4

  • Keyboard: All interactive elements reachable via Tab?
  • Contrast: Text 4.5:1 ratio minimum?
  • Not color-only: Icons/patterns, not just color?
  • Screen reader: Labels, alt text, ARIA?

Deep dive: A11Y.md


Output Template

# UX Audit: [Project]

## Summary
**Score:** X/10 | **Critical:** N | **Important:** N | **Suggestions:** N

## Critical Issues (Must Fix)
### 1. [Title]
**Heuristic:** #N - [Name]
**Location:** `file:line`
**Problem:** [What's wrong]
**Fix:** [Specific solution]

## Important Issues (Should Fix)
[Same format]

## Suggestions
- [ ] [Item]

## Heuristic Scores
| Heuristic | Score |
|-----------|-------|
| 1. Visibility | X/10 |
...

Full template: EXAMPLES.md


Audit Depth

TypeTimeWhen
Quick Scan5-10 minPR review, spot check
Standard30-60 minPre-release, feature review
Deep Audit2+ hrMajor redesign, compliance

Anti-Patterns

Don'tDo
"It's intuitive"Test with fresh eyes
Ignore error pathsAudit happy AND error flows
Skip accessibilityCheck the Big 4 minimum
Vague issuesSpecific file:line + fix
All issues equalPrioritize by impact

Integration

With Hooks

Auto-run a11y check after UI edits:

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "Edit",
      "hooks": [{
        "type": "command",
        "command": "if echo \"$TOOL_INPUT_PATH\" | grep -qE '\\.(tsx|jsx|html)$'; then npx axe \"$TOOL_INPUT_PATH\" 2>/dev/null || true; fi"
      }]
    }]
  }
}

With Other Skills

Combine with...For...
multi-model-triangulationMultiple UX perspectives
multi-pass-bug-huntingInclude UX issues in sweeps
ui-polishAfter fixing critical UX issues

References

TopicFile
Full heuristic detailsHEURISTICS.md
Accessibility deep diveA11Y.md
Example auditsEXAMPLES.md

Scripts

ScriptPurpose
scripts/generate-checklist.pyGenerate project-specific checklist
./scripts/generate-checklist.py web    # Web app
./scripts/generate-checklist.py cli    # CLI tool
./scripts/generate-checklist.py mobile # Mobile app
./scripts/generate-checklist.py api    # API/DX

Signals

GitHub stars
22
Forks
2
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
ux-audit-lev-os
Source
github.com/lev-os/agents