SkillKit CLI
A CLI skill manager for AI agents: install from repositories, translate between agent formats and deploy into their configs
- 1,578 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Reaches the network for repositories and writes to agent directories and configs
- Can run a local server and call external models
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/skillkitDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Reaches the network for repositories and writes to agent directories and configs
- Can run a local server and call external models
This is third-party code. Review the repository files before installing.
What it does
SkillKit is a command line tool that manages skills for AI agents. It installs skills from GitHub and GitLab repositories, a local folder or a gist, then lays them out in the formats and directories of specific agents. The translate command converts a single skill between agent formats, and recommend reads your project and suggests fitting skills. The core commands init, add, sync and list cover install and sync, while optional packages add a terminal UI, a REST server, agent messaging and a peer mesh. It also offers skill generation and session memory, features that rely on external models.
Who it is for. For developers who use several AI agents and want one shared set of skills in a single place.
Good fit when
- You need to install a skill into several agents at once
- You need to translate a skill from one agent's format to another
- You need skills matched to the current project's stack
Not a fit when
- You need a single specific skill that is simpler to install by hand
- You cannot run network operations or write to agent configs
Example request
Install the skills from the anthropics/skills repository into my Claude Code and CursorLimitations
The tool needs Node.js 18 or newer and installs via npm, pnpm or bun. Installing skills reaches the network for repositories and writes to agent directories and configs. The generate and memory commands rely on external models: Claude, GPT, Gemini, local Ollama or models via OpenRouter, some of which may be unavailable from Russia without a VPN. Extra features such as the terminal UI and REST server install as separate packages.
How to disable. Remove the package with npm uninstall -g skillkit. Installed skills stay in the agent directories; delete them there if needed.
FAQ
Do I need a global install?
No, you can run it via npx skillkit, but for frequent use a global install removes the refetch and the confirm prompt.
Are external models required?
No. Installing, translating and syncing skills work without models; they are only needed for skill generation and session memory.
Discussion
No questions or reviews yet.
Related
CLI toolsThe `askit` command line toolkit for agent skills: lint, security scan, tests, forging new ones and export to any agent.
A CLI and manager skill: one skills library distributed to 70+ agents, with management done from the agent conversation
A CLI installer and package manager for coding agent skills: one command installs skills into many runtimes and helps build your own
A desktop app and CLI to install, sync and organize agent skills across Claude Code, Codex, Cursor and other tools
A command-line skill manager: installs skills from a marketplace, GitHub, private Git and npm into 45 agents' folders and scans them first
A CLI and Python SDK to search, install, create and evaluate reusable agent skills from a shared library
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| SkillKit (this card) | no | 1,578 | |
| open-agent-hub | no | 997 | oah links 80-plus skills |
| OpenAgentSkill | no | 371 | a skill registry with a CLI and API |
| advai-cli | no | 284 | one advai command for local skills |
README in short
The README describes SkillKit as a package manager for AI agent skills that solves the problem of different formats across agents. The quick start is four commands: init, recommend, add and sync. Installation is via npm, pnpm, bun or a one-off npx, with full and slim variants, and extra features attach as separate packages. It separately shows installing from GitHub, GitLab, a local folder and a gist, translating between formats, stack-aware recommendations, a REST server and a Python client. Apache 2.0 licensed.