Design System Analyzer logo

Design System Analyzer

Community
NakanoSanku
design-system-analyzer

Analyze any website's UI style using ChromeDevTools to extract precise CSS tokens, animations, and interaction states. Handles complex sites and anti-bot measures by guiding the user. Triggers on "analyze this site", "extract UI style", "create design system from [URL]", or "learn visual style".

Overview

PublisherNakanoSanku
RepositoryOhMySkills
Skill namedesign-system-analyzer
Stars
163
Forks
14
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Design System Analyzer 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.
  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/NakanoSanku/OhMySkills.git /tmp/OhMySkills
mkdir -p .claude/skills
cp -r /tmp/OhMySkills/design-system-analyzer .claude/skills/design-system-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design System Analyzer 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 Design System Analyzer 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 Design System Analyzer 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.

Design System Analyzer

Analyze websites via ChromeDevTools to extract deep CSS logic (keyframes, transitions, tokens) and generate comprehensive Design System System Prompts.

Critical Rules

  1. MUST output the final prompt using EXACTLY the structure in references/design-system-template.md
  2. MUST limit extraction data to prevent context overflow (see analysis-guide.md for limits)
  3. MUST fill ALL template placeholders with extracted or observed values
  4. NEVER skip sections - use "Not observed" if data unavailable

Best Practice: Use Your Own Chrome

For the best experience (no CAPTCHAs, shared login cookies), advise the user to run Chrome with: chrome.exe --remote-debugging-port=9222 (See references/setup-guide.md for details)


Workflow Overview

[1. Navigate] → [2. Anti-Bot Check] → [3. Deep Extraction] → [4. Synthesize to Template]

IMPORTANT: Do NOT take screenshots. Screenshots consume excessive context and are unnecessary - all visual data is extracted from CSS.


Step 1: Navigate & Anti-Bot Check

mcp__chrome-devtools__navigate_page (url: "<target-url>")

Immediately check for bot challenges:

javascript
() => {
  const text = document.body.innerText.toLowerCase();
  const title = document.title.toLowerCase();
  if (text.includes('cloudflare') || text.includes('verify you are human') || title.includes('just a moment')) {
    return 'CHALLENGE_DETECTED';
  }
  return 'OK';
}

IF CHALLENGE_DETECTED:

  1. PAUSE all actions.
  2. Tell the user: "Bot protection detected. Please manually solve the CAPTCHA in the browser, then confirm here."
  3. Wait for user confirmation before proceeding.

Step 2: Deep CSS Extraction

Run the extraction scripts from references/analysis-guide.md in order:

OrderScriptPurposeMax Items
1CSS Variables & TokensColors, spacing, typography variables50 tokens
2Animation & Keyframes@keyframes, animation usage, transitions10 KF, 15 trans
3Interaction States:hover, :focus, :active rules15 rules
4TypographyFont stacks from key elements7 elements
5Layout & SpacingBorder radius, gaps, shadows5 each
6Tech StackFramework detection-

IMPORTANT: Each script has built-in limits. Do NOT modify to extract more data.


Step 3: Synthesize to Template

MANDATORY: Generate output using EXACTLY the template structure from references/design-system-template.md.

Template Mapping Table

Extracted DataTemplate SectionNotes
tokens.colorsDesign Token System > ColorsFormat as table
tokens.spacingSpacing, Radius & BordersInclude radius values
tokens.typographyTypographyInclude font stacks
Typography scriptTypography > Font Stacks, Type ScaleComputed styles
keyframesAnimation & Motion > Key AnimationsFull keyframe definitions
animationUsageAnimation & Motion > TimingDuration, easing
transitionsAnimation & Motion > TimingCommon patterns
interactionsComponent Styling > State TransitionsHover/focus effects
Layout samplerLayout PrinciplesSpacing system
Tech stackImplementation NotesTailwind/CSS notes

Output Format Checklist

Before outputting, verify ALL these sections are present:

  • <role> block (copy exactly from template)
  • <design-system> wrapper
  • ## Design Philosophy with Core Principles, Vibe, Historical Context
  • ## Design Token System with Colors table, Typography, Spacing
  • ## Component Styling Principles with Buttons, Cards, Form Inputs
  • ## Layout Principles with Spacing System, Grid, Responsive
  • ## The "Signature" Factor with 3 mandatory elements
  • ## Animation & Motion with Philosophy, Timing, Key Animations
  • ## Accessibility Constraints
  • ## Anti-Patterns with Visual and Interaction no-nos
  • ## Implementation Notes with tech-specific guidance
  • ## Aesthetic Checklist with 4 verification items
  • Closing </design-system>

Resources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Design System Analyzer AI skill do?

Analyze any website's UI style using ChromeDevTools to extract precise CSS tokens, animations, and interaction states. Handles complex sites and anti-bot measures by guiding the user. Triggers on "analyze this site", "extract UI style", "create design system from [URL]", or "learn visual style".

Why use Design System Analyzer on TypingMind?

Because you install it once and use it with any model. Design System Analyzer 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 Design System Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NakanoSanku/OhMySkills/tree/main/design-system-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Design System Analyzer?

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 Design System Analyzer?

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

Is the Design System Analyzer AI skill free?

It is published on GitHub by NakanoSanku. 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 👇