wps-skills  by lc2panda

AI assistant for controlling WPS Office via natural language

Created 4 months ago
258 stars

Top 98.0% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides an AI-powered assistant framework for controlling WPS Office functionalities using natural language. It targets developers and power users seeking to automate document creation and manipulation tasks across Excel, Word, and PowerPoint, offering a bridge between AI programming assistants and WPS Office's extensive toolset.

How It Works

The architecture comprises a Skills layer for natural language interpretation, an MCP Server layer that exposes 243 WPS Office MCP tools, and an execution layer that interfaces with WPS Office via platform-specific scripts. The MCP Server implements a standard stdio protocol, ensuring compatibility with various AI clients like Claude Code and Cursor, translating AI commands into actionable WPS Office operations.

Quick Start & Requirements

  • Primary install/run command: Clone the repository, navigate to wps-office-mcp, run npm install, and then npm run build. Configuration involves writing specific JSON/TOML files for your AI tool (e.g., ~/.claude/settings.json, .cursor/mcp.json) with the absolute path to the project's dist/index.js.
  • Non-default prerequisites: WPS Office (download from wps.cn or wps.com), Node.js >= 18.0.0, and Git are required.
  • Manual Steps: Installation of WPS add-ons requires running platform-specific scripts (scripts/auto-install-mac.sh, scripts/install.ps1, scripts/install.sh) and restarting WPS Office. Claude Code users also need to create symbolic links for skills.
  • Links: WPS Office download pages are provided.

Highlighted Details

  • Provides access to 243 MCP tools (231 professional + 12 built-in).
  • Supports Excel (82 tools), Word (28 tools), and PPT (112 tools), along with general utilities.
  • Cross-platform compatibility for macOS, Windows, and Linux.

Maintenance & Community

The project emphasizes synchronizing documentation updates with any functional or architectural changes. No specific community channels (like Discord or Slack) or details on notable contributors were found in the provided README.

Licensing & Compatibility

  • License type: MIT.
  • Compatibility notes: The MIT license generally permits commercial use and integration within closed-source projects.

Limitations & Caveats

Users must manually install WPS add-ons and restart the application for changes to take effect. Tool invocation may fail if the relevant WPS document type is not currently open. Specific installation instructions for Linux may require consulting additional documentation.

Health Check
Last Commit

1 week ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
7
Star History
80 stars in the last 30 days

Explore Similar Projects

Starred by Paul Stamatiou Paul Stamatiou(Cofounder of Limitless), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
5 more.

claude-task-master by eyaltoledano

0.3%
27k
AI-powered task management system for code editors
Created 1 year ago
Updated 4 weeks ago
Feedback? Help us improve.