A desktop application designed to centralize the management of AI coding agent skills across over 20 platforms, including Claude Code, Cursor, and Gemini CLI. It targets developers and power users seeking a unified interface to organize, discover, and deploy skills, offering a single source of truth to streamline workflows across diverse AI coding tools.

How It Works

This project utilizes Tauri v2 for its desktop framework, with a Rust backend and a React 19 frontend. It adheres to the Agent Skills open pattern, using ~/.agents/skills/ as a canonical directory. Skills are managed centrally and then installed to individual platforms via symlinks, enabling efficient updates and consistent skill deployment across multiple AI coding environments. The architecture prioritizes a local-first, privacy-focused approach with no telemetry.

Quick Start & Requirements

Latest prebuilt releases are available for Apple Silicon macOS (.dmg, .app.zip). For other platforms, users must run from source. Development requires Node.js (LTS), pnpm, and a Rust toolchain (stable). System dependencies for Tauri v2 are also necessary. The latest release can be found at https://github.com/iamzhihuix/skills-manage/releases/latest. Note that the macOS build is unsigned and may require manual Gatekeeper bypass (xattr -dr com.apple.quarantine "/Applications/skills-manage.app").

Highlighted Details

• Supports skill management for over 20 platforms, including major AI coding assistants and specialized "Lobster" tools.
• Features a rich, bilingual (English/Chinese) UI with Catppuccin themes, Markdown preview, raw source view, and AI-generated skill explanations.
• Includes advanced search capabilities for large skill libraries, employing deferred queries, lazy indexing, and virtualization for performance.
• Emphasizes privacy with local-first storage, no telemetry, and feature-driven network access.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or sponsorship were found in the provided README.

Licensing & Compatibility

The project is licensed under the Apache License 2.0. This license is generally permissive, allowing for commercial use and integration with closed-source projects.

Limitations & Caveats

The current prebuilt macOS release is unsigned, necessitating manual steps to bypass Gatekeeper security warnings. For platforms other than macOS, users are directed to run the application from source, indicating potential limitations in readily available precompiled binaries.