stitch::extract-design-md

stitch::extract-design-md is a skill for Claude Code from google-labs-code/stitch-skills. It costs 140 tokens per session (3,263 once invoked), scanned A, original, Apache-2.0.

A tool that reads frontend source code and writes a DESIGN.md document describing its visual system. It examines components, styles, themes, and design tokens such as colors, fonts, and spacing.

In plain words
What is it for?
Auditing frontend styling, documenting a design system, preparing a project for Stitch, or finding inconsistent visual patterns in React, Vue, Svelte, Angular, or HTML/CSS code.
Why use it?
It documents an interface's existing visual language even when the application cannot be built or rendered.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Auditing frontend styling, documenting a design system, preparing a project for Stitch, or finding inconsistent visual patterns in React, Vue, Svelte, Angular, or HTML/CSS code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/google-labs-code/stitch-skills/extract-design-md
About the project

Stitch Design Skills is a collection of Agent Skills and plugins for Google Stitch, a design tool accessed through the Stitch MCP server. It is for coding agents such as Codex, Antigravity, Gemini CLI, Claude Code, Cursor, and OpenCode, with catalogue entries covering Stitch design, build, and utility workflows.

google-labs-code/stitch-skills · 8,270 stars · on GitHub · stitch.withgoogle.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add google-labs-code/stitch-skills --skill extract-design-md
Clone the repo
git clone --depth 1 https://github.com/google-labs-code/stitch-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for stitch::extract-design-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/extract-design-md.svg)](https://agentmods.dev/skills/google-labs-code/stitch-skills/extract-design-md)
Your own site
<a href="https://agentmods.dev/skills/google-labs-code/stitch-skills/extract-design-md"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/extract-design-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.03263
Opus 5 $0.00070 $0.01631
Sonnet 5 $0.00028 $0.00653
Haiku 4.5 $0.00014 $0.00326

Measured 9d ago against content hash f9c32b30acd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

stitch::extract-design-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/stitch-design/skills/extract-design-md/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Design System from Frontend Code

Analyze frontend source code to extract a comprehensive design system document (DESIGN.md) that captures the project's visual language — colors, typography, spacing, component patterns, and layout principles — directly from the source files, without needing to build or render the application.

Why This Exists

The design-md skill works from rendered HTML. But often you have a codebase and want to understand its design system before you can even run the app — maybe dependencies are missing, the build is broken, or you just want a quick audit. This skill reads the source files themselves: stylesheets, component files, theme configs, and Tailwind setups. It's faster and works anywhere.

When to Use

  • User has a frontend codebase and wants to extract or document its design system
  • User wants to migrate a project's visual identity into Stitch
  • User asks to "audit the styling" or "understand the design language" of a repo
  • User wants to create a DESIGN.md from existing source code
  • The app can't be built/rendered but the source is available
  • User wants to unify or reconcile inconsistent styles across a codebase

Prerequisites

  • Access to the frontend project's source directory
  • No build or runtime dependencies needed — this skill reads source files only

Workflow

Phase 1: Project Discovery

Start by understanding what you're working with. This determines which extraction patterns to use.

1. Detect the Framework and Stack

Scan the project root for telltale files:

Signal File Framework / Tool
package.json with react React / Next.js
package.json with vue Vue / Nuxt
package.json with svelte Svelte / SvelteKit
package.json with @angular/core Angular
tailwind.config.js/ts Tailwind CSS
postcss.config.js PostCSS pipeline
styled-components or @emotion in deps CSS-in-JS
.css / .scss / .less files only Plain CSS / SASS
theme.js / theme.ts / tokens.js Design token files

Read the full file on GitHub · 366 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 366 lines · 140 tokens per session scan A f9c32b30acd9

Subscribe to this mod's changes

stitch::extract-design-md is a skill published in the GitHub repository google-labs-code/stitch-skills (8,270 stars, last pushed 21d ago), licensed Apache-2.0. It adds 140 tokens to every session and 3,263 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens

animation-principles

Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.

Owl-Listener/designer-skills · 59 tokens

refactoring-ui

Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…

wondelai/skills · 132 tokens