Refactor Ui logo

Refactor Ui

Community
gnurio
refactor-ui

Analyze a design against all 10 Refactoring UI skills and generate a comprehensive assessment with specific fixes

Overview

Publishergnurio
Repositoryrefactoring-ui-plugin
Skill namerefactor-ui
Stars
453
Forks
16
Bundled files
Instructions only
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 gnurio on GitHub. Read the source before you install it.

Installation

Install the Refactor Ui 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/gnurio/refactoring-ui-plugin/tree/main/skills/meta-refactor-ui
  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/gnurio/refactoring-ui-plugin.git /tmp/refactoring-ui-plugin
mkdir -p .claude/skills
cp -r /tmp/refactoring-ui-plugin/skills/meta-refactor-ui .claude/skills/refactor-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Refactor Ui 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 Refactor Ui 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 Refactor Ui 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.

Meta-Skill: /refactor-ui

Purpose

Run a complete UI design audit against all 10 Refactoring UI principles, generating a prioritized list of specific improvements.

Workflow

Phase 1: Load Skill Registry

Read skills.json
Validate all 10 skills available

Phase 2: Sequential Skill Application

Execute each skill in optimal order:

1. establish-visual-hierarchy
   ↓
2. apply-typography-scale
   ↓
3. build-color-palette
   ↓
4. apply-consistent-spacing
   ↓
5. design-button-hierarchy
   ↓
6. eliminate-visual-clutter
   ↓
7. design-empty-states
   ↓
8. use-shadows-appropriately
   ↓
9. manage-color-contrast
   ↓
10. group-related-elements

Phase 3: Consolidate Findings

Aggregate results from all skills:

  • Collect all FAIL assessments
  • Group by severity (Critical | High | Medium | Low)
  • Remove duplicates (same issue caught by multiple skills)
  • Prioritize by impact

Phase 4: Generate Report

Output structured assessment:

json
{
  "overall_score": "PASS | NEEDS_WORK | FAIL",
  "summary": "3 critical, 5 high, 2 medium priority fixes",
  "violations": [
    {
      "skill": "visual-hierarchy",
      "severity": "critical",
      "issue": "Primary CTA buried",
      "location": "Hero section",
      "fix": "Increase button to solid brand color, reduce surrounding contrast"
    }
  ],
  "priority_fixes": [
    "1. Make primary CTA prominent with brand color",
    "2. Consolidate font sizes from 12 to 6",
    "3. Add 8-10 grey shades to palette"
  ],
  "skill_breakdown": {
    "visual-hierarchy": { "status": "FAIL", "issues": 2 },
    "typography-scale": { "status": "PASS", "issues": 0 },
    "color-palette": { "status": "FAIL", "issues": 1 },
    ...
  }
}

Execution Modes

Mode: Quick Scan

  • Run all 10 skills
  • Report only FAILs
  • Time: ~30 seconds

Mode: Deep Analysis

  • Run all 10 skills
  • Report PASS with rationale
  • Cross-reference between skills
  • Suggest composition improvements
  • Time: ~2 minutes

Mode: Fix Mode

  • Run all 10 skills
  • Generate specific fix instructions
  • Provide before/after code examples
  • Time: ~5 minutes

Usage Examples

Example 1: Marketing Page

Input: Landing page description with hero, features, CTA

/refactor-ui
→ Overall: NEEDS_WORK
→ Critical: Visual hierarchy (CTA buried)
→ High: Typography (8 sizes, need 5)
→ Medium: Spacing (ambiguous grouping)
→ Priority fixes: [3 items]

Example 2: Dashboard

Input: Analytics dashboard screenshot

/refactor-ui --deep
→ Overall: PASS with suggestions
→ Visual hierarchy: PASS (clear primary)
→ Color palette: FAIL (only 4 greys)
→ Shadows: FAIL (decorative on cards)
→ Suggestions: [5 items]

Integration with Validation

This meta-skill can validate against NotebookLM:

For each skill assessment:
  Query: "According to Refactoring UI, is this correct?"
  Validate assessment matches expert
Report agreement rate

References

  • ../skills.json - Skill registry
  • ../examples/ - Before/after examples for all skills

Frequently asked questions

What does the Refactor Ui AI skill do?

Analyze a design against all 10 Refactoring UI skills and generate a comprehensive assessment with specific fixes

Why use Refactor Ui on TypingMind?

Because you install it once and use it with any model. Refactor Ui 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 Refactor Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gnurio/refactoring-ui-plugin/tree/main/skills/meta-refactor-ui. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Refactor Ui?

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 Refactor Ui?

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

Is the Refactor Ui AI skill free?

It is published on GitHub by gnurio. Check the repository for licensing terms. 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 👇