Laws of ux review

Skill keysjoao/laws-of-ux-skills/laws-of-ux-review

Three Claude Code skills bringing the 30 Laws of UX into your frontend workflow — advisor, audit, pre-ship checklist.

Install

npx -y skills add keysjoao/laws-of-ux-skills --skill laws-of-ux-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Audit existing UI code against all 30 Laws of UX, scoring compliance 0-60 with prioritized code fixes. Use when user says "review UX", "UX audit", "audit this page", "check UX compliance", "score this UI", "how good is the UX", or "laws-of-ux review".

SKILL.md

3.4 KB, as published. Nobody here has run it

Laws of UX — Review & Audit

Score existing UI code against all 30 Laws of UX and deliver prioritized, code-level fixes.

Process

Step 1: Read the Target

Read the component/page file(s) the user wants audited. If no file specified, ask which file or component to review.

Step 2: Score Each Law

Load references/ux-laws-complete.md from the parent laws-of-ux skill.

For each of the 30 laws, score:

Score	Meaning
2	Compliant — law is properly applied
1	Partial — some application but incomplete or inconsistent
0	Violation — law is broken or not addressed where it should be
—	N/A — law doesn't apply to this component type

Maximum score: 60 (all 30 laws fully compliant)

Step 3: Classify Findings

Group all non-compliant laws into severity tiers:

CRITICAL (score 0, high-impact laws): Laws that directly cause usability failures:

Fitts's Law (unreachable/tiny targets)
Doherty Threshold (no loading feedback)
Hick's Law (overwhelming choices)
Cognitive Load (too much at once)
Jakob's Law (breaks conventions)

WARNING (score 0-1, medium-impact laws): Laws that degrade experience:

Proximity, Common Region, Similarity (grouping issues)
Miller's Law, Chunking (information overload)
Goal-Gradient, Zeigarnik (missing progress)
Von Restorff (nothing stands out)

SUGGESTION (score 1, polish laws): Laws that improve quality:

Aesthetic-Usability (visual polish)
Peak-End Rule (celebration states)
Flow (minor interruptions)
Parkinson's Law (time cues)

Step 4: Generate Report

Output this exact format:

# UX Audit: [Component/Page Name]

**Score: [X]/60** | **Grade: [A/B/C/D/F]**

| Grade | Range |
|-------|-------|
| A | 50-60 |
| B | 40-49 |
| C | 30-39 |
| D | 20-29 |
| F | 0-19 |

## Critical Issues ([count])

### [Law Name] — Score: 0/2
**Problem:** [What's wrong, referencing specific lines]
**Fix:**
```[language]
// Before (line XX)
[current code]

// After
[fixed code]

Warnings ([count])

[Law Name] — Score: [0-1]/2

Problem: [description] Fix: [code change]

Suggestions ([count])

[Law Name] — Score: 1/2

Improve: [description] Code: [enhancement]

Compliant ([count])

[List of laws scoring 2/2 — no action needed]

N/A ([count])

[List of laws not applicable to this component]


### Step 5: Prioritized Action Plan

After the report, provide a numbered action plan:

```markdown
## Action Plan (do in this order)

1. **[Critical fix]** — [1-line description] → [file:line]
2. **[Critical fix]** — [1-line description] → [file:line]
3. **[Warning fix]** — [1-line description] → [file:line]
...

Rules

Always read the actual code — never score based on assumptions
Every violation needs a code fix — no fix = not a real finding
Be honest about N/A — don't force-apply laws that don't fit
Reference specific lines — file.tsx:42 not "somewhere in the component"
Score consistently — same violation in two components gets same score