Chops is a native macOS application designed to centralize and manage AI agent skills across various coding tools like Claude Code, Cursor, Codex, Windsurf, and Amp. It targets developers who use multiple AI assistants, offering a unified interface to discover, organize, edit, and search skills, eliminating the need to navigate scattered dotfiles.

How It Works

The application employs a native macOS architecture using SwiftUI and SwiftData, avoiding web views for a responsive user experience. It leverages FSEvents for real-time file system monitoring, ensuring instant updates as skills change on disk. Skills are identified by their resolved symlink paths, enabling deduplication and displaying multiple tool associations for a single skill file. A built-in editor with frontmatter parsing and full-text search capabilities further enhances skill management.

Quick Start & Requirements

• Prerequisites: macOS 15 (Sequoia) or later, Xcode with command-line tools (xcode-select --install), and Homebrew are required. xcodegen must be installed (brew install xcodegen).
• Installation: Clone the repository, navigate to the directory, run xcodegen generate to create the Xcode project, then open Chops.xcodeproj in Xcode.
• Running: Build and run the application directly from Xcode using Cmd+R. A command-line build option is also available via xcodebuild.

Highlighted Details

• Multi-tool Support: Integrates with Claude Code, Cursor, Codex, Windsurf, Amp, Copilot, and Aider, with support for custom paths.
• Built-in Editor: Features a monospaced editor with Cmd+S saving and frontmatter parsing for direct skill modification.
• Real-time File Watching: Utilizes FSEvents for immediate detection and synchronization of file changes.
• No Sandbox: The application intentionally disables the macOS sandbox to grant unrestricted filesystem access necessary for managing dotfiles.
• Deduplication: Skills are uniquely identified by their resolved symlink path, consolidating multiple tool references.

Maintenance & Community

The provided README does not detail specific community channels (e.g., Discord, Slack), notable contributors, sponsorships, or a public roadmap.

Licensing & Compatibility

The project is released under the MIT license, which is permissive and generally compatible with commercial use and integration into closed-source projects.

Limitations & Caveats

The project currently lacks an automated test suite, requiring manual validation of changes. Its core functionality relies on disabling the macOS sandbox, which may pose security considerations for some users. The application is exclusively for macOS and requires the latest version, macOS 15 (Sequoia) or newer.