AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Laws Of Ux Review

skill-keysjoao-laws-of-ux-skills-laws-of-ux-review · by keysjoao

>

No reviews yet
0 installs
30 views
0.0% view→install

Install

$ agentstack add skill-keysjoao-laws-of-ux-skills-laws-of-ux-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-keysjoao-laws-of-ux-skills-laws-of-ux-review)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Laws Of Ux Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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

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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.