Agent skill

Web Style Extractor

by Lucent-Snow in Lucent-Snow/style-extractor

Extracts evidence-backed style guides and motion appendices from websites, keeping reusable visual language and stripping product-specific content.

No licenceAuto-check passedFrontend & Design

Install Web Style Extractor

skills CLI
$ npx skills add Lucent-Snow/style-extractor --skill style-extractor -a claude-code

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

GitHub CLI
$ gh skill install Lucent-Snow/style-extractor style-extractor --agent claude-code

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

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

Facts

Skill name
style-extractor
GitHub stars
453
Token cost
~3.8k tokens
SKILL.md length
1,586 words
Files
47 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Extracts evidence-backed style guides and motion appendices from websites, keeping reusable visual language and stripping product-specific content.

  • Works in 5 steps: Inputs → 5 — Read the reference package (REQUIRED) → Abstraction and de-productization… → …
  • Capturing a website's colors, typography and spacing as semantic tokens
  • SKILL.md covers Output location (REQUIRED), References (quality bar), Required reference… and Workflow, plus 2 more sections
  • Documenting component states and hover behavior from a live site

What it does

The agent pulls a reusable design system out of web UIs: colors, typography, spacing, components, states and, when relevant, motion such as timings, keyframes and delay chains. The core principle is to keep visual language and interaction rules and drop the source product's information architecture, copy, app logic and marketing claims.

Each extraction creates its own project folder under a style-extractor directory in the user's profile, never inside the skill folder. It holds a style guide, an evidence manifest and, if motion matters, a motion guide, plus evidence subfolders for screenshots, downloaded assets and raw notes. Templates define the required sections, and two included reference packages, a visual novel site and a design system, set the quality bar.

When your agent uses it

  • Capturing a website's colors, typography and spacing as semantic tokens
  • Documenting component states and hover behavior from a live site
  • Recording runtime animation timings and keyframes in a motion appendix
  • Building a style reference without copying a product's content

Example prompts

  • “Extract a style guide from https://example.com with screenshots as evidence.”
  • “Document the motion on the hero section of this landing page.”
  • “Write semantic tokens for the buttons and navigation of this web app.”

Requirements

  • A browser able to open the target site

Workflow steps

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

  1. Inputs
  2. 5 — Read the reference package (REQUIRED)
  3. Abstraction and de-productization (REQUIRED)
  4. Semantic tokenization (REQUIRED)
  5. Write the deliverables

What it can do on your machine

Read from SKILL.md and the folder at commit 10bd355. 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/, which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Web Style Extractor loads about 3.8k tokens when it runs, and up to ~2.9M if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 1,586 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9M

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,586 words (~3,791 tokens).

“Extract a reusable design system from web UIs: colors, typography, spacing, components, states, and, when relevant, motion (timings, keyframes, delay chains, JS-driven behavior).”

— opening of SKILL.md by Lucent-Snow
name
style-extractor

Read the full SKILL.md on GitHub

Files

SKILL.md and 46 other files (scripts, references) in the repository root of Lucent-Snow/style-extractor.

  • SKILL.md
  • .gitignore
  • README.md
  • media/duck.gif
  • media/nine.gif
  • references/9nine-visual-novel/evidence/assets/google-fonts.css
  • references/9nine-visual-novel/evidence/assets/style.css
  • references/9nine-visual-novel/evidence/assets/yakuhanjp.min.css
  • references/9nine-visual-novel/evidence/screenshots/01-homepage-viewport.png
  • references/9nine-visual-novel/evidence/screenshots/02-homepage-fullpage.png
  • references/9nine-visual-novel/evidence/screenshots/03-nav-hover.png
  • references/9nine-visual-novel/evidence/screenshots/04-button-hover.png
  • references/9nine-visual-novel/evidence/screenshots/05-footer.png
  • references/9nine-visual-novel/evidence/screenshots/06-character-section.png
  • references/9nine-visual-novel/evidence/screenshots/07-news-section.png
  • … and 32 more

Open the folder on GitHubat commit 10bd355

Compare with similar skills

Web Style Extractor 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.

Web Style Extractor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Web Style Extractor this skillLucent-Snow/style-extractor453—~3.8kAutomated safety check: PassNone
Design System AnalyzerNakanoSanku/OhMySkills163—~1.2kAutomated safety check: PassNone
Transitions PolishJakubantalik/transitions.dev4.6k2 repos~3.2kAutomated safety check: PassCustom licence
Tailwind Design SystemSuFxGIT/scoutarr1145 repos~5.6kAutomated safety check: PassNone
Extract DesignManavarya09/design-extract4.2k—~786Automated safety check: NotesMIT
Tailwind Design Systemjh941213/my-cc-harness1269 repos~4.7kAutomated safety check: PassNone

Similar skills

  • Design System Analyzer

    NakanoSanku/OhMySkills

    Inspects a live website through Chrome DevTools and turns its CSS tokens, animations and hover states into a design system prompt.

    163 GitHub stars~1.2k tokensUpdated 9 mo ago
    Frontend & DesignAuto-check passed
  • Transitions Polish

    Jakubantalik/transitions.dev

    Audits existing UI animations against the transitions.dev motion-token scale and suggests tokens for duration, distance, scale, blur and easing.

    4.6k GitHub starsUsed in 2 repos~3.2k tokens
    Frontend & DesignAuto-check passed
  • Tailwind Design System

    SuFxGIT/scoutarr

    Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns.

    114 GitHub starsUsed in 5 repos~5.6k tokens
    Frontend & DesignAuto-check passed
  • Extract Design

    Manavarya09/design-extract

    Extract the full design language from any website URL. An agent skill from Manavarya09/design-extract.

    4.2k GitHub stars~786 tokensUpdated 8 days ago
    Frontend & DesignAuto-check: notes
  • Tailwind Design System

    jh941213/my-cc-harness

    Build scalable design systems with Tailwind CSS, design tokens, component libraries, and responsive patterns.

    126 GitHub starsUsed in 9 repos~4.7k tokens
    Frontend & DesignAuto-check passed
  • Tailwind V4 Shadcn

    ever-works/ever-works

    Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React.

    158 GitHub starsUsed in 2 repos~3.8k tokens
    Frontend & DesignAuto-check passed

Questions about Web Style Extractor

What does Web Style Extractor do?

Extracts evidence-backed style guides and motion appendices from websites, keeping reusable visual language and stripping product-specific content. The agent pulls a reusable design system out of web UIs: colors, typography, spacing, components, states and, when relevant, motion such as timings, keyframes and delay chains. The core principle is to keep visual language and interaction rules and drop the source product's information architecture, copy, app logic and marketing claims.

When should I use Web Style Extractor?

Web Style Extractor fits situations like: capturing a website's colors, typography and spacing as semantic tokens; documenting component states and hover behavior from a live site; recording runtime animation timings and keyframes in a motion appendix; building a style reference without copying a product's content.

How do I install Web Style Extractor in Claude Code?

Run `npx skills add Lucent-Snow/style-extractor --skill style-extractor -a claude-code`. Or copy the skill folder (the Lucent-Snow/style-extractor repository) into .claude/skills/style-extractor in your project. Claude Code loads it when a task matches its description.

How do I install Web Style Extractor in Codex?

Run `npx skills add Lucent-Snow/style-extractor --skill style-extractor -a codex`. Or copy the skill folder (the Lucent-Snow/style-extractor repository) into .agents/skills/style-extractor in your project. Codex loads it when a task matches its description.

Can I use Web Style Extractor 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 Lucent-Snow/style-extractor --skill style-extractor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/style-extractor, .gemini/skills/style-extractor, .github/skills/style-extractor and .opencode/skills/style-extractor in your project.

What does Web Style Extractor need to run?

SKILL.md names no scripts, command-line tools or credentials: Web Style Extractor is instructions for the agent only. Our summary lists: A browser able to open the target site.

Does Web Style Extractor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Web Style Extractor 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 Web Style Extractor use?

No licence was found for Web Style Extractor or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Web Style Extractor use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9M tokens, read only when the agent opens those files.

What are the alternatives to Web Style Extractor?

Skills that share tags, products or a category with Web Style Extractor: Design System Analyzer (NakanoSanku/OhMySkills, 163 stars), Transitions Polish (Jakubantalik/transitions.dev, 4.6k stars), Tailwind Design System (SuFxGIT/scoutarr, 114 stars) and Extract Design (Manavarya09/design-extract, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Web Style Extractor?

Lucent-Snow (a GitHub user) maintains it in Lucent-Snow/style-extractor, which has 453 GitHub stars. The repository was last updated on March 13, 2026.

Source: Lucent-Snow/style-extractor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.