agentleFS
samsam007bsamsam007b/claude-code-standards-kit/skills/ux-heuristic-audit/SKILL.md

ux-heuristic-audit

Skill2 starsChanged 8 months agoMITView on GitHub

Audit an interface using Nielsen heuristics and Laws of UX. Prioritized report with issues and recommendations.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before/after code examples

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UX Heuristic Audit Skill

Description

Audits an interface or component according to scientific UX principles (Nielsen Heuristics + Laws of UX). Generates a report with identified issues and prioritized recommendations.

Usage

/ux-heuristic-audit [file_path_or_component_name]

Workflow

  1. Reading the Component/Page
    • Reads the source code
    • Analyzes structure, props, states
    • Identifies UI elements (buttons, inputs, cards, etc.)
  2. Audit According to Nielsen's 10 Heuristics
    • #1 Visibility of System Status
    • #2 Match Between System & Real World
    • #3 User Control & Freedom
    • #4 Consistency & Standards
    • #5 Error Prevention
    • #6 Recognition Rather Than Recall
    • #7 Flexibility & Efficiency
    • #8 Aesthetic & Minimalist Design
    • #9 Help Users Recognize, Diagnose & Recover from Errors
    • #10 Help & Documentation
  3. Audit According to Laws of UX
    • Miller's Law (7±2 visible elements)
    • Hick's Law (number of choices)
    • Fitts's Law (size of interactive targets)
    • Tesler's Law (distribution of complexity)
    • Information Scent (descriptive labels)
  4. Report Generation
    • Lists issues by severity (Critical, High, Medium, Low)
    • Specific recommendations
    • Before/after code examples
    • Overall UX score (0-100)

Output Format

# UX Audit Report - [Component Name]

**Date**: [Date]
**Auditor**: Claude (Scientific UX Framework)
**Overall UX Score**: [X]/100

---

## Executive Summary

[Summary of the main findings]

---

## Critical Issues (Severity 5/5)

### Issue #1: [Title]
- **Heuristic Violated**: Nielsen #X or Law of UX
- **Current State**: [Description of the problem]
- **User Impact**: [Impact on the user]
- **Recommendation**: [Proposed solution]
- **Code Example**:
  ```tsx
  // Before (problematic)
  [current code]

  // After (fixed)
  [corrected code]

High Priority Issues (Severity 4/5)

[...]


Medium Priority Issues (Severity 3/5)

[...]


Low Priority Issues (Severity 2/5)

[...]


Strengths (What works well)

  • [Identified strengths]

Recommendations Summary

PriorityIssueEstimated EffortImpact
P0[Issue][Effort][Impact]

Next Steps

  1. [Priority action]
  2. [Next action]

## Examples

### Example 1: Audit of a filter sidebar

```bash
/ux-heuristic-audit components/explore/FilterSidebar.tsx

Findings:

  • ❌ Miller's Law violated: 25+ checkboxes visible (> 7±2)
  • ❌ Information Scent weak: Label "Options" too vague
  • ✅ Consistency good: Uniform icons

Example 2: Audit of a full page

/ux-heuristic-audit app/seeker/explore/page.tsx

Findings:

  • ❌ Visibility: No feedback on the number of results
  • ❌ Hick's Law: Too many simultaneous choices (paralysis)
  • ✅ Aesthetic & Minimalist: Clean design

Configuration

The skill uses the references in docs/ux-guidelines/:

  • ux-checklist-before-feature.md
  • ux-scientific-research-complex-interfaces.md

Output Location

Reports are saved in:

docs/ux-audits/[component-name]-audit-[date].md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.