crossoverJie/SkillDeck

Native macOS SwiftUI app for managing multiple AI code agent skills

What it solves

SkillDeck eliminates the need for manual file editing, symlink management, and YAML parsing when managing "skills" (capabilities/instructions) across various AI code agents. It provides a centralized graphical interface to handle these configurations instead of relying on command-line manual labor.

How it works

It acts as a macOS-native GUI layer over the filesystem, where skills are stored as directories containing SKILL.md files. The app monitors the filesystem for changes and uses Swift actors for thread-safe access. It manages the installation of skills from GitHub or local folders by automatically creating the necessary symlinks in the specific skills directories of supported AI agents (such as Claude Code, Cursor, and Gemini CLI).

Who it’s for

Developers using multiple AI coding assistants on macOS who want a streamlined way to discover, install, and synchronize skills across different agents.

Highlights

  • Multi-Agent Support: Compatible with a wide range of agents including Claude Code, Codex, Gemini CLI, Copilot CLI, Cursor, and others.
  • Registry Integration: Built-in browser for the skills.sh leaderboard and ClawHub catalog.
  • Unified Dashboard: A three-pane macOS-native view for managing all installed skills.
  • Skill Management: One-click updates for remote changes and a split-pane editor for SKILL.md files with live preview.
  • Agent Assignment: Ability to toggle which specific agents have access to a particular skill via symlink management.
  • Natural Language Control: Includes a built-in skilldeck skill that allows users to manage their skills using natural language within any AI agent.

Related

  • Project
    EvotecIT/OfficeIMO

    A family of COM-free .NET libraries for creating, reading, editing, and converting Office and document formats without requiring Microsoft Office or LibreOffice.

  • Project
    87owo/PYAS

    A hybrid Windows endpoint security platform that combines machine learning, YARA rules, and a kernel-level minifilter driver for malware detection and prevention.

  • Project
    defendend/Claude-ast-index-search

    A structural, AST-aware code navigation CLI that builds a local SQLite index of symbols and dependencies to help humans and AI agents navigate large repositories precisely.

  • Project
    maquina-app/rails-mcp-server

    A Ruby implementation of the Model Context Protocol (MCP) server that allows LLMs to analyze and interact with Rails projects through structured tools and documentation.