Laws Of Ux Review logo

Laws Of Ux Review

Community
keysjoao
laws-of-ux-review

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".

Overview

Publisherkeysjoao
Repositorylaws-of-ux-skills
Skill namelaws-of-ux-review
Stars
12
Forks
0
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by keysjoao on GitHub. Read the source before you install it.

Installation

Install the Laws Of Ux Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/keysjoao/laws-of-ux-skills/tree/main/laws-of-ux-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/keysjoao/laws-of-ux-skills.git /tmp/laws-of-ux-skills
mkdir -p .claude/skills
cp -r /tmp/laws-of-ux-skills/laws-of-ux-review .claude/skills/laws-of-ux-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Laws Of Ux Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Laws Of Ux Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Laws Of Ux Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

ScoreMeaning
2Compliant — law is properly applied
1Partial — some application but incomplete or inconsistent
0Violation — 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:

markdown
# 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 lines — file.tsx:42 not "somewhere in the component"
  5. Score consistently — same violation in two components gets same score

Frequently asked questions

What does the Laws Of Ux Review AI skill do?

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".

Why use Laws Of Ux Review on TypingMind?

Because you install it once and use it with any model. Laws Of Ux Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Laws Of Ux Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/keysjoao/laws-of-ux-skills/tree/main/laws-of-ux-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Laws Of Ux Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Laws Of Ux Review?

As many as you like. As long as a model supports skills, you can use Laws Of Ux Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Laws Of Ux Review AI skill free?

Yes. It is published on GitHub by keysjoao under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇