extract-design-system

Extract design tokens from public websites and generate starter token files.

Updated Sep 3, 2026
One-click install
npx skills add https://github.com/xzedm/clipplic-landing --skill extract-design-system-xzedm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-design-system
Source: https://github.com/xzedm/clipplic-landing/tree/main/.agents/skills/extract-design-system
Command: npx skills add https://github.com/xzedm/clipplic-landing --skill extract-design-system-xzedm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, extract-design-system.

What problem does it solve? Reverse-engineering a website's visual style by hand is slow and error-prone. This Skill automates the extraction of design primitives like colors, fonts, spacing, radii, and shadows from a public website and turns them into starter token files for your project. ## Core Features & Use Cases - Automated Token Extraction: Runs a Playwright-based CLI against a public URL to capture colors, fonts, spacing, radius, and shadow scales into raw and normalized JSON artifacts. - Starter File Generation: Produces design-system/tokens.json and design-system/tokens.css so you can bootstrap a design system without starting from scratch. - Regeneration Mode: Reuses an existing .extract-design-system/normalized.json to regenerate starter files without re-crawling the site. - Use Case: You are starting a new client project and want to match the look of their existing marketing site. Point the Skill at the public URL, review the normalized tokens, and generate starter CSS variables to seed your theme. ## Quick Start Ask the assistant to extract the design system from a public website URL and generate starter token files for the project.

Frequently Asked Questions about extract-design-system

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract design tokens from a website?▼

Run npx extract-design-system followed by the public URL after installing Chromium via npx playwright install chromium. The tool writes raw and normalized JSON artifacts, then generates design-system/tokens.json and tokens.css starter files.

How to regenerate design token files without re-crawling a site?▼

Run npx extract-design-system init if you already have .extract-design-system/normalized.json from a previous extraction. This regenerates the starter token files from the cached normalized data without fetching the website again.

What does the extract-design-system tool output?▼

It produces .extract-design-system/raw.json and .extract-design-system/normalized.json as extraction artifacts, plus design-system/tokens.json and design-system/tokens.css as starter token files for your project.

Can I extract tokens without generating starter files?▼

Yes, pass the --extract-only flag to the CLI to produce only the extraction artifacts. This is useful when you want to review the normalized tokens before generating any project files.

What are the limitations of website design token extraction?▼

Extraction from a single page does not prove a complete product design system, especially for dynamic or partial sites. Results are starter tokens for initialization, not pixel-perfect reproductions, and should be reviewed before use.