Extract Design System

What it does

When your agent uses it

• Tasks that involve Design systems
• Tasks that involve Design tokens
• Tasks that involve Typography

Example prompts

• “extract design system from [url]”
• “reverse-engineer the styles from [site]”
• “build a design system based on [website]”
• “/extract-design-system”

Requirements

• Node.js

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Run the Extraction Script
2. 2CSS Source Analysis (supplementary)
3. 3Organize Raw Data into Tokens
4. 4Compile Token File
5. 5Seed Penpot (optional)
6. 6Generate Tailwind Config (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 79d019b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • node
  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Extract Design System loads about 2k tokens when it runs. Until then it costs about 205 tokens; SKILL.md has 592 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~205

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from espennilsen/pi at commit 79d019b, republished under its MIT licence (© espennilsen). 592 words, ~1,991 tokens.

name

extract-design-system

description

Reverse-engineer a design system from a live website (public URL or localhost). Extracts colors, typography, spacing, shadows, radii, breakpoints, and component patterns using a headed Playwright browser. Captures screenshots of pages, components, and interactive states at real device resolutions. Produces structured design tokens and optionally seeds a Penpot project. **Triggers — use this skill when:** - User says "extract design system from [url]" - User asks to "reverse-engineer the styles from [site]" - User says "build a design system based on [website]" - User asks to "pull the design tokens from [url]" - User says "analyze the design of [site]" - User asks to "import styles from [website] into Penpot" - User points at a URL and asks about its colors, fonts, spacing, or components

node scripts/extract.mjs <url> [outDir] [subpage1,subpage2,...]

node scripts/extract.mjs https://example.com
node scripts/extract.mjs https://example.com ./my-tokens "/about,/pricing,/docs"
node scripts/extract.mjs http://localhost:3000 extracted "/dashboard,/settings"

{outDir}/
├── screenshots/
│   ├── pages/               — full-page at 4 breakpoints × each page
│   │   ├── home-mobile.png
│   │   ├── home-desktop.png
│   │   ├── home-dark-mode.png
│   │   └── ...
│   └── components/          — isolated component + hover/focus states
│       ├── nav.png
│       ├── button-primary.png
│       ├── button-primary-hover.png
│       ├── button-primary-focus.png
│       ├── nav-mobile-open.png
│       └── ...
└── raw/
    ├── colors.json          — CSS custom properties + computed colors
    ├── colors-dark.json     — dark mode variables (if detected)
    ├── typography.json      — font families, type styles, @font-face
    ├── spacing.json         — spacing, radii, shadows, borders, max-widths
    └── components.json      — component manifest + responsive layout data

node scripts/extract.mjs "TARGET_URL" "extracted-design-system" "/about,/pricing"

# Fetch stylesheets identified in the HTML
web_fetch <stylesheet-url>

# Look for things the computed pass might miss:
# - Media query breakpoints
# - Keyframe animations
# - CSS custom property definitions with fallbacks
# - Commented-out or unused styles that reveal design intent

4px grid: 4, 8, 12, 16, 20, 24, 32, 40, 48, 64, 80, 96
8px grid: 8, 16, 24, 32, 40, 48, 56, 64, 80, 96

{
  "$schema": "extracted-design-tokens",
  "source": "https://example.com",
  "extracted": "2026-03-09",
  "framework_detected": "tailwind|bootstrap|custom|none",
  "dark_mode": true,
  "colors": {
    "light": {
      "primary": { "50": "#...", "500": "#...", "900": "#..." },
      "neutral": { "50": "#...", "950": "#..." }
    },
    "dark": { }
  },
  "typography": {
    "fontFamilies": { "sans": "...", "mono": "..." },
    "scale": { "h1": { "size": "36px", "weight": 700, "lineHeight": 1.2 } }
  },
  "spacing": { "grid": "4px", "scale": [0, 4, 8, 12, 16, 24, 32, 48, 64, 96] },
  "radii": { "sm": "4px", "md": "8px", "lg": "12px" },
  "shadows": { "sm": "...", "md": "...", "lg": "..." },
  "components": { "buttons": { "variants": ["primary", "secondary"] } }
}

© espennilsen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/extract-design-system of espennilsen/pi.

• SKILL.md
• scripts/extract.mjs

Open the folder on GitHubat commit 79d019b