extract-design

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get design system', 'design language', 'design tokens', 'what colors/fonts does this site use', or '/extract-design'.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "extract-design" with this command: npx skills add manavarya09/design-extract/manavarya09-design-extract-extract-design

Extract Design Language

Extract the complete design language from any website URL. Generates 8 output files covering colors, typography, spacing, shadows, components, breakpoints, animations, and accessibility.

Prerequisites

Ensure designlang is available. Install if needed:

npm install -g designlang

Or use npx (no install required):

npx designlang <url>

Process

  1. Run the extraction on the provided URL:
npx designlang <url> --screenshots

For multi-page crawling: npx designlang <url> --depth 3 --screenshots For dark mode: npx designlang <url> --dark --screenshots

  1. Read the generated markdown file to understand the design:
cat design-extract-output/*-design-language.md
  1. Present key findings to the user:

    • Primary color palette with hex codes
    • Font families in use
    • Spacing system (base unit if detected)
    • WCAG accessibility score
    • Component patterns found
    • Notable design decisions (shadows, radii, etc.)
  2. Offer next steps:

    • Copy *-tailwind.config.js into their project
    • Import *-variables.css into their stylesheet
    • Paste *-shadcn-theme.css into globals.css for shadcn/ui users
    • Import *-theme.js for React/CSS-in-JS projects
    • Import *-figma-variables.json into Figma for designer handoff
    • Open *-preview.html in a browser for a visual overview
    • Use the markdown file as context for AI-assisted development

Output Files (8)

FilePurpose
*-design-language.mdAI-optimized markdown — the full design system for LLMs
*-preview.htmlVisual HTML report with swatches, type scale, shadows, a11y
*-design-tokens.jsonW3C Design Tokens format
*-tailwind.config.jsReady-to-use Tailwind CSS theme
*-variables.cssCSS custom properties
*-figma-variables.jsonFigma Variables import format
*-theme.jsReact/CSS-in-JS theme object
*-shadcn-theme.cssshadcn/ui theme CSS variables

Additional Commands

  • Compare two sites: npx designlang diff <urlA> <urlB>
  • View history: npx designlang history <url>

Options

FlagDescription
--out <dir>Output directory (default: ./design-extract-output)
--darkAlso extract dark mode color scheme
--depth <n>Crawl N internal pages for site-wide extraction
--screenshotsCapture component screenshots (buttons, cards, nav)
--wait <ms>Wait time after page load for SPAs
--framework <type>Generate only specific theme (react or shadcn)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

pet-breed-individual-recognition-analysis

Accurately identifies cat and dog breeds and supports distinguishing between different individuals in multi-pet households; an essential assistant for intelligent pet butlers. | 宠物品种个体识别技能,精准识别猫狗宠物品种,支持多宠家庭区分不同独立个体,智能宠物管家好帮手

Archived SourceRecently Updated
General

familiar-person-recognition-analysis

Identifies acquaintances in videos or images through face photo comparison. Supports database enrollment, and the recognition results tell you who is at which location. Suitable for identity verification in homes and office areas. | 熟人识别分析技能,通过人脸图片比对识别视频/图片中的熟人,支持底库录入,识别结果告诉你哪个位置是谁,适用于家庭、办公区域身份核验

Archived SourceRecently Updated
General

fire-detection-analysis

Real-time detection of flames and smoke in video and image scenes. Suitable for fire early warning in industrial parks, forests, warehouses, and other locations. | 火情烟雾检测技能,实时检测视频/图片场景中的火焰、烟雾,适用于工业园区、森林、仓库等场所火情预警

Archived SourceRecently Updated
General

focus-analysis

Real-time detection of gaze direction and facial pose to quantify states of focus, distraction, or mind-wandering. Suitable for scenarios such as classroom learning, office meetings, and driving attention monitoring. | 专注度分析技能,实时检测视线方向、面部姿态,量化专注/分心/走神状态,适用于课堂学习、办公会议、驾驶专注度监测等场景

Archived SourceRecently Updated