runkids/skillshare

📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

What it solves

Skillshare prevents the need to rebuild your AI coding setup every time you switch between different AI tools. It provides a centralized, user-controlled home for skills, agents, rules, and MCP connections, allowing users to sync their configurations across multiple platforms like Claude Code, Codex, Pi, and OpenCode.

How it works

Skillshare maintains a local source directory (in ~/.config/skillshare/ on macOS/Linux or %AppData%\skillshare\ on Windows) containing your skills, agents, and extras. It uses symlinks (or copies) to sync these resources to the target AI tools. This declarative approach allows you to version your setup via Git, share project-specific skills with teammates, and manage everything through a CLI or a desktop application.

Who it’s for

Developers who use multiple AI coding assistants and want a single source of truth for their custom instructions, agent configurations, and tool connections to avoid repetitive manual setup.

Highlights

  • Multi-tool Sync: Sync skills and agents to Claude Code, Codex, Pi, OpenCode, and more.
  • Security Auditing: Built-in audit command to scan skills before they are applied to your agents.
  • Project-specific Skills: Ability to initialize skills per-repository, allowing them to be committed to code and shared with teams.
  • MCP Management: Centralized configuration for Model Context Protocol (MCP) connections across different tools.
  • Desktop & CLI: Offers both a visual dashboard and a powerful command-line interface for management.
  • Git Integration: Install skills directly from Git hosts (GitHub, GitLab) and version your own configuration.

Related

  • Project
    knoxgraeme/skillfish

    A CLI skill manager for AI coding agents that allows users to install, update, and sync portable prompt packages across tools like Claude Code, Cursor, and Copilot.

  • Project
    xingkongliang/skills-manager

    Skills Manager is a cross‑platform desktop and CLI tool for collecting, organising, and deploying AI‑agent skill packages (prompt‑code bundles) across many coding assistants. It offers a unified library, marketplace, presets, global/project workspaces, multi‑tool sync, Git‑backed backup, and agent‑aware management, all built with React/Tauri (frontend) and Rust/SQLite (backend).

  • Project
    mxyhi/ok-skills

    OK Skills is a library of 31 ready‑to‑use *skill packs* for AI coding agents (Codex, Claude Code, Cursor, etc.). Each skill lives in its own directory with a `SKILL.md` that tells the agent how to run the underlying script (e.g., browser automation, docs lookup, planning, design). Install by cloning into `~/.agents/skills` (or the Autohand equivalent), copy the `CLAUDE_AGENTS.md` sections into your agent’s config, and then ask the agent to “Use <skill‑name> …”. The repo provides categories such as Research, Planning, Automation, Frontend, and Utilities, and serves developers who want portable, repeatable AI‑agent capabilities instead of ad‑hoc prompts.

  • Project
    vercel-labs/skills

    A CLI that discovers, installs, updates, and runs reusable prompt bundles (“skills”) for many AI coding assistants (Claude Code, Cursor, OpenCode, etc.), pulling them from any Git repository or direct URL.

  • Project
    cisco-ai-defense/skill-scanner

    Skill Scanner is an open‑source security scanner for AI‑agent skill packages (e.g., OpenAI Codex, Cursor, Claude). It combines signature‑based YARA/YAML rules, AST‑based data‑flow analysis, optional LLM‑as‑a‑judge, and a CEL decision layer to detect prompt‑injection, data‑exfiltration, and malicious code patterns. Install via pip, run from the CLI or Python SDK, and integrate with CI/CD via GitHub Actions or a pre‑commit hook. Findings are reported with severity levels; a clean scan is best‑effort only and does not guarantee safety.