An automated tool for extracting and documenting UI/UX design systems from frontend codebases while stripping away business logic.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install frontend-design-extractor
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install frontend-design-extractor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Frontend Design Extractor is a specialized utility within the Openclaw Skills ecosystem designed to reverse-engineer comprehensive design systems from existing frontend repositories. It focuses exclusively on UI/UX elements—such as design tokens, global styles, and component patterns—while intentionally ignoring domain-specific business logic. This makes it an essential asset for developers looking to document legacy systems, migrate to new frameworks, or establish a clean design foundation for greenfield projects.
By automating the discovery of UI sources, this skill allows teams to create a single source of truth for their design language. Whether you are working with React, Vue, Angular, or Vite, the tool adapts to the target stack to generate a standardized specification that can be used for refactoring or as a starter kit for new development. Utilizing Openclaw Skills like this ensures that design consistency is maintained throughout the software development lifecycle.
To begin using this tool among your Openclaw Skills, follow these steps:
./scripts/scan_ui_sources.sh <repo_root> [out_file]
./scripts/generate_output_skeleton.sh [out_root]
The skill organizes extracted data into a dedicated directory with a standardized taxonomy to ensure clarity and reusability:
| Folder | Description |
|---|---|
| 01_Foundation | Design tokens (colors, type, spacing, shadows) and global styles. |
| 02_Components | Detailed catalog of UI components with variants, states, and slots. |
| 03_Patterns | Reusable interaction patterns, loading strategies, and layout rules. |
| 04_Pages | Skeleton templates and module ordering for page-level views. |
| 05_A11y | Accessibility documentation, focus-visible rules, and compliance gaps. |
| 06_Assets | References to icons, images, brand assets, and i18n sources. |
| 07_Engineering_Constraints | Framework-specific implementation notes, naming conventions, and CSS architecture. |
Loading
A professional AI tool for generating high-resolution images via Alibaba's wan2.6-t2i model with automated local storage and cloud hosting.

A sophisticated memory integration that enables AI agents to remember user preferences, facts, and conversation history across multiple sessions.

A minimal HTTP service providing Elon Musk news briefings and demonstration payment integration for AI agents.

A three-tier memory architecture combining Baidu-powered vector recall, structured Git-Notes, and local workspace search.

A powerful integration for Google Gemini that enables end-to-end multimodal workflows including image generation, video synthesis, and speech-to-text capabilities.

A comprehensive tool for generating professional AI images and videos using Seedream 4.5 and Kling models via the LiblibAI API.








































