Agent skill

Extract Design

by danielvm-git in danielvm-git/bigpowers

Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose.

MITAuto-check passedFrontend & Design

Install Extract Design

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/extract-design .claude/skills/extract-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .claude/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/extract-design .agents/skills/extract-design && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .agents/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/extract-design .cursor/skills/extract-design && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .cursor/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/danielvm-git/bigpowers.git --path skills/extract-design

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/extract-design .gemini/skills/extract-design && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .gemini/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/extract-design .github/skills/extract-design && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .github/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add danielvm-git/bigpowers --skill extract-design -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install danielvm-git/bigpowers extract-design --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/extract-design .opencode/skills/extract-design && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "extract-design" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/extract-design into .opencode/skills/extract-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extract-design", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: extract-design
GitHub stars: 256
Token cost: ~1k tokens
SKILL.md length: 327 words
Files: 30 (incl. scripts)
Skills in repo: 39
Repo updated: Sep 21, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose.

Works in 6 steps: Launch Puppeteer — dual-pass (light +… → Collect styles — page.evaluate()… → Classify tokens — modular pipeline:… → …
The user has an HTML prototype and wants a DESIGN.md to anchor their projects visual identity
SKILL.md covers Quick Start, Flow, Inputs and Output, plus 3 more sections
Runs JavaScript scripts from its folder; calls node and npx

What it does

Extract Design is an agent skill from danielvm-git/bigpowers. Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a new project.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 31 other files, including scripts (for example `REFERENCE.md`, `scripts/classify-colors.js` and `scripts/classify-rounded.js`).

It sits in Frontend & Design, covering Design tokens, Project scaffolding and Logo and visual identity. It works with Puppeteer. The repository describes itself as: Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers. The licence is MIT.

When your agent uses it

The user has an HTML prototype and wants a DESIGN.md to anchor their projects visual identity
Seed-conventions has just scaffolded a new project

Example prompts

“/extract-design”

Requirements

Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Launch Puppeteer — dual-pass (light + dark) with retry + timeout. CI flags: --headless=new --no-sandbox --disable-gpu --disable-dbus…
Collect styles — page.evaluate() collects computed styles from every element. Returns raw JSON to Node.js. Browser = sensor; Node = brain.
Classify tokens — modular pipeline: colors (Material 3 roles), typography (scale detection), spacing (tolerance GCD), rounded…
Generate prose — AI heuristics produce all 8 DESIGN.md sections. Overview and Do's/Don'ts flagged with agent notes.
Write + validate — serialize to specs/tech-architecture/DESIGN_LATEST.md, run npx @google/design.md lint, report to terminal.
Handoff — writes handoff.next_skill: grill-me to specs/state.yaml with uncertain decisions context.

What it can do on your machine

Read from SKILL.md and the folder at commit 812d57a. 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 15 files in scripts/ (JavaScript, from the files we listed), 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 loads about 1k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 327 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~87
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 danielvm-git/bigpowers at commit 812d57a, republished under its MIT licence (© danielvm-git). 327 words, ~1,017 tokens.

Download SKILL.mdSave it as .claude/skills/extract-design/SKILL.md (or your agent's skills folder). This skill also uses 29 other files; get the full folder from GitHub.

name: extract-design
description: Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a new project.
model: sonnet
effort: standard

Extract DESIGN.md from HTML

HARD GATE — Do NOT write DESIGN.md without Puppeteer dual-pass extraction. Tokens from static HTML (Cheerio, regex, string scanning) are invalid — they miss cascade, custom properties, and Tailwind resolution.

HARD GATE — Do NOT claim certainty where evidence is thin. Low-confidence color roles, component classifications, and prose assertions MUST be flagged with .

HARD GATE — Do NOT ship DESIGN.md without running npx @google/design.md lint. Unvalidated output is unverified output. If lint is unavailable (offline), flag prominently in terminal and in DESIGN.md prose.

Quick Start

bash

# First run — extract from HTML prototype
node extract-design/scripts/extract.js --source ./prototype.html

# From a published URL
node extract-design/scripts/extract.js --source https://my-prototype.example.com

# With a custom name
node extract-design/scripts/extract.js --source ./proto.html --name "My Design System"

# Update — re-extract from new HTML, diff against existing
node extract-design/scripts/extract.js --source ./proto-v2.html

# Lint-only — validate existing DESIGN.md without re-extraction
node extract-design/scripts/extract.js --lint-only

Flow

Launch Puppeteer — dual-pass (light + dark) with retry + timeout. CI flags: --headless=new --no-sandbox --disable-gpu --disable-dbus --use-gl=angle --use-angle=swiftshader.
Collect styles — page.evaluate() collects computed styles from every element. Returns raw JSON to Node.js. Browser = sensor; Node = brain.
Classify tokens — modular pipeline: colors (Material 3 roles), typography (scale detection), spacing (tolerance GCD), rounded (clustering), components (visual signature + pseudo-state variants).
Generate prose — AI heuristics produce all 8 DESIGN.md sections. Overview and Do's/Don'ts flagged with agent notes.
Write + validate — serialize to specs/tech-architecture/DESIGN_LATEST.md, run npx @google/design.md lint, report to terminal.
Handoff — writes handoff.next_skill: grill-me to specs/state.yaml with uncertain decisions context.

Inputs

Parameter	Required	Description
`--source <file\|url>`	First run: yes. Update: optional	HTML prototype path or URL
`--name <string>`	No	Design system name (defaults to `<title>` or directory name)
`--lint-only`	No	Validate existing DESIGN.md without re-extraction

Output

specs/tech-architecture/DESIGN_LATEST.md — replaces DESIGN_PLAN_LATEST.md as the canonical design artifact
Terminal summary: token counts, component count, lint result, uncertain decisions
Structured JSON log to stderr: extraction events, timing, counts
specs/state.yaml → handoff.next_skill: grill-me with context

Error Tiers

Tier	Condition	Response
Fatal	No Chrome, page load timeout after retries	Exit non-zero, suggest fixes
Degraded	Zero colors, zero typography, SPA shell	Write DESIGN.md with degradation warning
Warned	Lint errors, uncertain decisions	Write DESIGN.md, flag in terminal, hand off to grill-me

Dependencies

Puppeteer (Chrome binary) — wrapped behind BrowserExtractor interface for testability
@google/design.md (soft, via npx) — wrapped behind DesignValidator interface. Warns and skips if offline.

verify

bash

node extract-design/tests/test-extraction.js

See REFERENCE.md for extraction algorithms and heuristics.

Files

SKILL.md and 29 other files (scripts) in skills/extract-design of danielvm-git/bigpowers.

SKILL.md
REFERENCE.md
extract-design.feature
scripts/classify-colors.js
scripts/classify-rounded.js
scripts/classify-spacing.js
scripts/classify-typography.js
scripts/collect-styles.js
scripts/detect-components.js
scripts/extract.js
scripts/generate-prose.js
scripts/lib/browser.js
scripts/lib/constants.js
scripts/lib/logging.js
scripts/lib/retry.js
scripts/lib/state.js
scripts/lib/validator.js
scripts/write-designd.js
tests
… and 11 more

Open the folder on GitHubat commit 812d57a

Compare with similar skills

Extract Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Extract Design compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Extract Design this skilldanielvm-git/bigpowers	256	—	~1k	Automated safety check: Pass	MIT	16 days ago
DesignOhh-889/skyroc	795	9 repos	~3.1k	Automated safety check: Pass	MIT	1 mo ago
Cavekit Design SystemJuliusBrussee/caveman-code	940	—	~4.5k	Automated safety check: Pass	MIT	1 mo ago
Figma Codegenawdr74100/figwright	977	—	~4.2k	Automated safety check: Pass	MIT	today
Replica DesignJakeschincariol/replica-skill	734	—	~994	Automated safety check: Pass	MIT	4 days ago
Frontend UI Foundryjiushiwon/wg-skills	110	—	~1.4k	Automated safety check: Pass	Apache-2.0	3 days ago

Similar skills

Design
Ohh-889/skyroc
Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations…
795 GitHub starsUsed in 9 repos~3.1k tokens
Frontend & DesignAuto-check passed
Cavekit Design System
JuliusBrussee/caveman-code
How to write and maintain DESIGN.md as the visual specification layer for Cavekit projects.
940 GitHub stars~4.5k tokensUpdated 1 mo ago
Frontend & DesignAuto-check passed
Figma Codegen
awdr74100/figwright
Generate framework-aware code from a Figma design. An agent skill from awdr74100/figwright.
977 GitHub stars~4.2k tokensUpdated today
Frontend & DesignAuto-check passed
Replica Design
Jakeschincariol/replica-skill
Rebuilds an app's design system for a clone: colour roles, type scale, spacing, radius, shadows and every component with its states, as design tokens plus component specs, with original assets…
734 GitHub stars~994 tokensUpdated 4 days ago
Frontend & DesignAuto-check passed
Frontend UI Foundry
jiushiwon/wg-skills
A skill your agent uses when generating UI for a specific scenario (mobile/PC/官网/管理端/营销页/文档/金融/原生/3D), when refactoring an existing HTML/Vue/React project to a unified design system, when extracting…
110 GitHub stars~1.4k tokensUpdated 3 days ago
Frontend & DesignAuto-check passed
Shadcn Tailwind UI
LiarMTTT/TavernWeave
Build, restyle, or review accessible React interfaces that use shadcn/ui, Radix UI primitives, and Tailwind CSS.
148 GitHub stars~1.7k tokensUpdated 3 days ago
Frontend & DesignAuto-check passed

Questions about Extract Design

What does Extract Design do?

Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Extract Design is an agent skill from danielvm-git/bigpowers.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose.

When should I use Extract Design?

Extract Design fits situations like: the user has an HTML prototype and wants a DESIGN.md to anchor their projects visual identity; seed-conventions has just scaffolded a new project.

How do I install Extract Design in Claude Code?

Run `npx skills add danielvm-git/bigpowers --skill extract-design -a claude-code`. Or copy the skill folder (skills/extract-design in danielvm-git/bigpowers) into .claude/skills/extract-design in your project. Claude Code loads it when a task matches its description.

How do I install Extract Design in Codex?

Run `npx skills add danielvm-git/bigpowers --skill extract-design -a codex`. Or copy the skill folder (skills/extract-design in danielvm-git/bigpowers) into .agents/skills/extract-design in your project. Codex loads it when a task matches its description.

Can I use Extract Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add danielvm-git/bigpowers --skill extract-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extract-design, .gemini/skills/extract-design, .github/skills/extract-design and .opencode/skills/extract-design in your project.

What does Extract Design need to run?

Going by SKILL.md and its folder, Extract Design needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npx). Our summary lists: Node.js.

Does Extract Design access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Extract Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Extract Design use?

Extract Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Extract Design use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Extract Design?

Skills that share tags, products or a category with Extract Design: Design (Ohh-889/skyroc, 795 stars), Cavekit Design System (JuliusBrussee/caveman-code, 940 stars), Figma Codegen (awdr74100/figwright, 977 stars) and Replica Design (Jakeschincariol/replica-skill, 734 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Extract Design?

danielvm-git (a GitHub user) maintains it in danielvm-git/bigpowers, which has 256 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on September 21, 2026.

Source: danielvm-git/bigpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Extract Design

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Extract DESIGN.md from HTML

Quick Start

Flow

Inputs

Output

Error Tiers

Dependencies

verify

Files

Compare with similar skills

Similar skills

More from danielvm-git/bigpowers

Related

Questions about Extract Design