leemysw

feishu-docx

39
7
# Install this skill:
npx skills add leemysw/agent-kit

Or install specific skill: npx add-skill https://github.com/leemysw/agent-kit/tree/main/.skills/feishu-docx

# Description

Export Feishu/Lark cloud documents to Markdown. Supports docx, sheets, bitable, and wiki. Use this skill when you need to read, analyze, or reference content from Feishu knowledge base.

# SKILL.md


name: feishu-docx
description: Export Feishu/Lark cloud documents to Markdown. Supports docx, sheets, bitable, and wiki. Use this skill when you need to read, analyze, or reference content from Feishu knowledge base.


Feishu Docx Exporter

Export Feishu/Lark cloud documents to Markdown format for AI analysis.

Instructions

Setup (One-time)

  1. Install the tool:
pip install feishu-docx
  1. Configure Feishu app credentials:
feishu-docx config set --app-id YOUR_APP_ID --app-secret YOUR_APP_SECRET
# or use environment variables
  1. Authorize with OAuth (opens browser):
feishu-docx auth

Export Documents

Export any Feishu document URL to Markdown:

feishu-docx export "<FEISHU_URL>" -o ./output

The exported Markdown file will be saved with the document's title as filename.

Supported Document Types

  • docx: Feishu cloud documents β†’ Markdown with images
  • sheet: Spreadsheets β†’ Markdown tables
  • bitable: Multidimensional tables β†’ Markdown tables
  • wiki: Knowledge base nodes β†’ Auto-resolved and exported

Examples

Export a wiki page

feishu-docx export "https://xxx.feishu.cn/wiki/ABC123" -o ./docs

Export a document with custom filename

feishu-docx export "https://xxx.feishu.cn/docx/XYZ789" -o ./docs -n meeting_notes

Export spreadsheet as Markdown table

feishu-docx export "https://xxx.feishu.cn/sheets/DEF456" --table md
# Output content to stdout instead of saving to file
feishu-docx export "https://xxx.feishu.cn/wiki/ABC123" --stdout
# or use short flag
feishu-docx export "https://xxx.feishu.cn/wiki/ABC123" -c

Read content without saving to file (Python)

from feishu_docx import FeishuExporter

exporter = FeishuExporter(app_id="xxx", app_secret="xxx")
content = exporter.export_content("https://xxx.feishu.cn/wiki/xxx")
print(content)

Command Reference

Command Description
feishu-docx export <URL> Export document to Markdown
feishu-docx auth OAuth authorization
feishu-docx config set Set credentials
feishu-docx config show Show current config
feishu-docx config clear Clear token cache

Tips

  • Images are automatically downloaded to a folder named after the document
  • Use --table md for Markdown tables instead of HTML
  • Token is cached and auto-refreshed, no need to re-authorize
  • For Lark (overseas), add --lark flag

# README.md

Agent Kit Logo

Production-Ready AI Agent Development Framework Powered by Claude Agent SDK
基于 Claude Agent SDK ζž„ε»Ίηš„η”ŸδΊ§ηΊ§ AI ζ™Ίθƒ½δ½“εΌ€ε‘ζ‘†ζžΆ

[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![Python](https://img.shields.io/badge/Python-3.11%2B-blue.svg)](https://www.python.org/downloads/) [![FastAPI](https://img.shields.io/badge/FastAPI-Latest-green.svg)](https://fastapi.tiangolo.com/) [![Next.js](https://img.shields.io/badge/Next.js-24.0%2B-black.svg)](https://nextjs.org/) [![Docker Pulls](https://img.shields.io/docker/pulls/leemysw/agent-kit.svg)](https://hub.docker.com/r/leemysw/agent-kit) **[English](./README.md) | [δΈ­ζ–‡](./README-zh.md)**

πŸ“– Introduction

Agent Kit is a comprehensive AI agent development framework that integrates Claude Agent SDK, providing a complete solution from frontend to backend. This project aims to help developers quickly build, deploy, and scale production-grade AI Agent applications.

Agent Kit Screenshot Agent Kit Screenshot

✨ Core Features

#### πŸš€ High-Performance Architecture - FastAPI asynchronous backend - Next.js frontend framework - WebSocket real-time communication - SQLite + Alembic database migrations #### 🎯 Complete AI Integration - Deep Claude Agent SDK integration - Streaming response support - Custom tools system (in development) - MCP support (in development) - Skill support (in development) #### πŸ› οΈ Developer Friendly - TypeScript type safety - Zustand state management - Complete session management - Comprehensive documentation

πŸ—οΈ Architecture

Architecture Diagram

πŸ“‹ Table of Contents


πŸš€ Quick Start

Prerequisites

  • Python: 3.11 or higher
  • Node.js: 24.0 or higher
  • Docker & Docker Compose: Latest version
  • Agent API Key: Get from Anthropic or Bigmodel

Installation

1️⃣ Clone the repository

git clone https://github.com/leemysw/agent-kit.git
cd agent-kit

2️⃣ Configure environment variables

# Copy environment variable template
cp example.env .env
# Edit .env file and add your API key

3️⃣ Start services

make start
╰─ make start
TAG=0.1.2 docker compose -f deploy/docker-compose.yml up -d
[+] Running 3/3
 βœ” Container deploy-agent-kit-1  Started                                                                                                                                           1.8s 
 βœ” Container deploy-web-1   Started                                                                                                                                           0.9s 
 βœ” Container deploy-nginx-1      Running                                                                                                                                           0.0s 

βœ… Agent Kit is running!
🌐 Web UI: http://localhost
πŸ“‹ Logs: run 'make logs' to view service logs

4️⃣ Access the application


Option 2: Local Development

1️⃣ Clone the repository

git clone https://github.com/leemysw/agent-kit.git
cd agent-kit

2️⃣ Backend setup

# Install Python dependencies
pip install -r agent/requirements.txt

# Configure environment variables
cp example.env .env
# Edit .env file and add your API key

Configure .env file:

# Claude API configuration
ANTHROPIC_API_KEY=your_api_key_here
ANTHROPIC_BASE_URL=https://api.anthropic.com or https://open.bigmodel.cn/api/anthropic
ANTHROPIC_MODEL=claude-3-5-sonnet-20241022 or glm-4.7

# Server configuration
HOST=0.0.0.0
PORT=8010
DEBUG=true
WORKERS=1

Initialize database:

# Run database migrations to create tables
alembic upgrade head

3️⃣ Frontend setup

cd web

# Install dependencies
npm install

# Configure environment variables
cp example.env .env.local
# Edit .env.local file

Configure .env.local file:

# Development environment configuration
NEXT_PUBLIC_API_URL=http://localhost:8010/agent/v1
NEXT_PUBLIC_WS_URL=ws://localhost:8010/agent/v1/chat/ws
NEXT_PUBLIC_DEFAULT_CWD=/opt/app/playground
NEXT_PUBLIC_DEFAULT_MODEL=glm-4.7

4️⃣ Run the project

# Start backend (in project root directory)
python main.py

# Start frontend (in web directory)
npm run dev

5️⃣ Access the application


πŸ“ Project Structure

agent-kit/
β”œβ”€β”€ agent/                         # Backend service
β”‚   β”œβ”€β”€ api/                       # API routes
β”‚   β”œβ”€β”€ core/                      # Core configuration
β”‚   β”œβ”€β”€ service/                   # Business logic
β”‚   β”‚   β”œβ”€β”€ websocket_handler.py   # WebSocket handler
β”‚   β”‚   └── session_manager.py     # Session management
β”‚   β”œβ”€β”€ shared/                    # Shared modules
β”‚   └── utils/                     # Utility functions
β”œβ”€β”€ web/                           # Frontend application
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ app/                   # Next.js pages
β”‚   β”‚   β”œβ”€β”€ components/            # React components
β”‚   β”‚   β”œβ”€β”€ hooks/                 # Custom Hooks
β”‚   β”‚   β”œβ”€β”€ lib/                   # Utility library
β”‚   β”‚   β”œβ”€β”€ store/                 # Zustand state management
β”‚   β”‚   └── types/                 # TypeScript types
β”œβ”€β”€ alembic/                       # Database migrations
β”œβ”€β”€ deploy/                        # Deployment files
β”œβ”€β”€ docs/                          # Documentation
β”‚   β”œβ”€β”€ websocket-session-flow.md  # WebSocket flow
β”‚   └── guides/                    # Claude Agent SDK guides
β”œβ”€β”€ main.py                        # Application entry point
└── README.md                      # This file

🎯 Core Features

1. Real-time Conversation System

  • βœ… WebSocket real-time communication
  • βœ… Streaming response support
  • βœ… Session persistence
  • βœ… Message history management

2. Intelligent Session Management

  • βœ… Multi-session support
  • βœ… Session search and filtering

3. Powerful AI Capabilities

  • βœ… Claude Agent SDK integration
  • ❌ Custom tool calling (in development)
  • ❌ Slash command system (in development)
  • ❌ Skills system (in development)
  • ❌ MCP protocol support (in development)

4. Permissions & Security

  • βœ… Fine-grained tool permission control
  • βœ… User confirmation mechanism

βš™οΈ Configuration

Backend Configuration

Config Item Description Default Value
ANTHROPIC_API_KEY Claude API key -
ANTHROPIC_BASE_URL API base URL https://api.anthropic.com
ANTHROPIC_MODEL Model to use glm-4.7
HOST Server host 0.0.0.0
PORT Server port 8010
DEBUG Debug mode false
WORKERS Number of workers 1

Frontend Configuration

Config Item Description Default Value
NEXT_PUBLIC_API_URL Backend API URL http://localhost:8010/agent/v1
NEXT_PUBLIC_WS_URL WebSocket URL ws://localhost:8010/agent/v1/chat/ws
NEXT_PUBLIC_DEFAULT_CWD Working directory /opt/app/playground
NEXT_PUBLIC_DEFAULT_MODEL Default model glm-4.7

πŸ“š Documentation

For detailed guides and API documentation, please visit:

Development Guides


🀝 Contributing

All forms of contributions are welcome!

Bug Reports & Feature Requests

If you find a bug or have a new feature suggestion, please submit it through GitHub Issues.


πŸ“„ License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.


πŸ™ Acknowledgments


### Made with ❀️ by [leemysw](https://github.com/leemysw) **If this project helps you, please give it a ⭐️ Star!**

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.