Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health.
By leveraging Python SDK / OpenAI API, the application isolates runtime dependencies while maintaining low-latency execution traces across multi-step LLM operations.
High-throughput parsing of complex documents (PDFs, Word docs, spreadsheets, presentations)
Structured table, key-value, and metadata extraction directly into agent memory buffers
Automated report generation and document synthesis from multi-source repositories
{
"mcpServers": {
"design-extract": {
"command": "python",
"args": [
"-m",
"design_extract"
]
}
}
}
Paste into your client configuration file (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%/Claude/claude_desktop_config.json on Windows).
Clone Manavarya09/design-extract from GitHub
Install dependencies with pip install -r requirements.txt (or uv sync)
Copy .env.example to .env and add your API keys
Run the skill server and connect your AI client via stdio or HTTP
Keeps heavy parsing and raw file structures external to the LLM. Only sanitized excerpts and structured returns are injected into agent memory turns.
Enforce explicit directory allowlists and permission scopes in client configuration to ensure autonomous tool calls never breach system boundaries.
Executes in an isolated local child process communicating strictly over JSON-RPC via stdio with explicit process timeouts.
Design Extract is an open-source document capability designed for AI clients and autonomous agents. Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health.
Follow the step-by-step installation: 1) Verify your runtime (Python 3.10+), 2) Add the configuration snippet into your AI client settings (e.g. claude_desktop_config.json), 3) Restart the client to initialize tool execution.
Design Extract is compatible with all AI tools supporting tool-calling and the Model Context Protocol (MCP), including Claude Desktop, Cursor, Claude Code CLI, Windsurf, OpenCode, and custom agent runtimes.
Design Extract executes locally with strict directory allowlists and permission scopes. Heavy parsing and raw file structures stay external to the LLM context window to prevent memory saturation and unauthorized access.
Yes, Design Extract is published under the MIT open-source license. You can inspect the source code and contribute on GitHub at https://github.com/Manavarya09/design-extract.
Explore open-source implementation code, license, and community releases.
Anthropic's official Claude Skills for working with document formats — fill, merge, and extract data from PDFs, Word files, PowerPoint decks, and Excel spreadsheets inside agent workflows.
Reverse engineer anything with agents, from app behavior down to native binaries.
The AI Game Design Agent Team is a collaborative game design system powered by AG2(formerly AutoGen)'s AI Agent framework. This app generates comprehensive game concepts through the coordination of multiple specialized AI agents, each...
Advanced AI AgentsA Streamlit application that brings together a team of specialized AI teaching agents who collaborate like a professional teaching faculty. Each agent acts as a specialized educator: a curriculum designer, learning path expert, resource...
RAG Tutorials & PipelinesA Streamlit application that provides comprehensive design analysis using a team of specialized AI agents powered by Google's Gemini model. This application leverages multiple specialized AI agents to provide comprehensive analysis of...