agentleFS
Sign inStart free
memi-designmemi-design/design-skills/skills/design-extract/SKILL.md

design-extract

Skill7 starsChanged 4 months agoMITView on GitHub

Extract a public website's design system when a task needs evidence about its colors, typography, spacing, radii, shadows, components, or Tailwind tokens.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Does not work on pure client-side rendered apps (CSR) that inject all styles via JS at runtime

    line 57

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design Extract

Extract any website's design system from its public URL. No login, no API key, no Figma.

When to use

  • User pastes a URL and wants to understand its visual design
  • User wants to replicate a site's look and feel
  • User asks "what design system does X use?"
  • User wants a DESIGN.md for AI context
  • User wants to match an existing site's tokens in their own project

How it works

  1. Fetch the URL's HTML and all linked stylesheets
  2. Parse CSS for: custom properties, colors, fonts, spacing, radii, shadows
  3. Send extracted raw data to Claude for structured synthesis
  4. Output a DESIGN.md with: color system, typography, spacing, borders, component patterns, Tailwind config sketch

Usage

# CLI
memi design-doc https://linear.app
memi design-doc https://stripe.com --spec    # also write a DesignSpec JSON
memi extract https://vercel.com              # alias

# MCP tool
design_doc({ url: "https://linear.app" })

Output format

The DESIGN.md contains:

  • Color System -- palette with semantic names (primary, bg, fg, muted, accent)
  • Typography -- font stacks, size scale, weight usage
  • Spacing -- scale (4px/8px grid or other rhythm)
  • Borders & Surfaces -- radii, shadows, border styles
  • Component Patterns -- inferred from DOM (buttons, cards, inputs, nav)
  • Tailwind Config Sketch -- partial tailwind.config.js with extend values

Success criteria

  • Extraction completes in under 30 seconds for any public URL
  • Output contains at least 10 distinct design tokens
  • Tailwind config sketch is valid JavaScript
  • DESIGN.md is immediately usable as AI prompt context

Limitations

  • Does not work on pure client-side rendered apps (CSR) that inject all styles via JS at runtime
  • Works on: static sites, SSR (Next.js, Remix, SvelteKit), and any site that serves CSS in <link> or <style> tags

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free