Skip to content
Back to search

agent-skills-cli

Universal CLI for Agent Skills. Access 200,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and Antigravity.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/karanjot786--agent-skills-cli/badge.svg)](/listings/karanjot786--agent-skills-cli)

HTML

<a href="/listings/karanjot786--agent-skills-cli"><img src="/api/listings/karanjot786--agent-skills-cli/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npm install -g agent-skills-cli

**Requirements:** Node.js 18+

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 327 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Agent Skills CLI
  2. Install, update and manage AI agent skills across 45 coding agents from one command line.
  3. [![npm version](https://img.shields.io/npm/v/agent-skills-cli)](https://www.npmjs.com/package/agent-skills-cli)
  4. [![npm downloads](https://img.shields.io/npm/dm/agent-skills-cli)](https://www.npmjs.com/package/agent-skills-cli)
  5. [![license](https://img.shields.io/npm/l/agent-skills-cli)](LICENSE)
  6. [![node](https://img.shields.io/node/v/agent-skills-cli)](https://www.npmjs.com/package/agent-skills-cli)
  7. [![GitHub stars](https://img.shields.io/github/stars/Karanjot786/agent-skills-cli?style=social)](https://github.com/Karanjot786/agent-skills-cli)
  8. `skills` finds skills in the [agentskills.in](https://agentskills.in) marketplace, in GitHub and private Git repositories, and in npm packages. It installs them into the skill directory of each agent you choose, such as Claude Code, Cursor, GitHub Copilot or Windsurf.
  9. The marketplace indexes over 222,000 skills from more than 21,000 authors.
  10. ## Highlights
  11. - **Every source.** Marketplace, GitHub, private Git (SSH or token), and npm registries.
  12. - **45 agents.** One install can write to every agent you select, or to all of them with `--all`.
  13. - **Scanned before install.** Every command that installs skills checks them for security issues before copying them.
  14. - **Built for teams.** Project config with `.skillsrc`, lockfile installs with `skills frozen`, and quality scoring.
  15. ## Contents
  16. - [Installation](#installation)
  17. - [Quick start](#quick-start)
  18. - [Commands](#commands)
  19. - [Installing skills](#installing-skills)
  20. - [MCP servers, subagents and plugins](#mcp-servers-subagents-and-plugins)
  21. - [Security](#security)
  22. - [Context budget and token cost](#context-budget-and-token-cost)
  23. - [Supported agents](#supported-agents)
  24. - [Configuration](#configuration)
  25. - [Environment variables and telemetry](#environment-variables-and-telemetry)
  26. - [Creating a skill](#creating-a-skill)
  27. - [Contributing](#contributing)
  28. - [License](#license)
  29. ## Installation
  30. ```bash
  31. npm install -g agent-skills-cli
  32. ```
  33. Requires Node.js 18 or later. Run `skills --version` to confirm the install.
  34. ## Quick start
  35. ```bash
  36. # Search the marketplace and pick skills interactively
  37. skills search python
  38. # Install a skill to the agents detected on this machine
  39. skills install @facebook/verify
  40. # Install to specific agents
  41. skills install @facebook/verify -a claude,cursor
  42. # See what is installed, then keep it up to date
  43. skills list
  44. skills update --all
  45. ```
  46. ## Commands
  47. | Command | What it does |
  48. |---------|--------------|
  49. | `skills search <query>` | Find skills in the marketplace. Add `-i` for an interactive picker. |
  50. | `skills install <source>` | Install from the marketplace, a GitHub repo, a Git URL, an npm package or a local folder. `skills add` is an alias. |
  51. | `skills list` | List discovered skills. Use `--table` for token costs or `--json` for scripts. |
  52. | `skills check` | Show installed skills with their source and version. |
  53. | `skills update [skills...]` | Update skills from their source. Use `--all`, and `--prune` to remove stale ones. |
  54. | `skills remove [skills...]` | Remove skills. Use `-a <agent>` to remove from one agent only. |
  55. | `skills doctor` | Diagnose the setup. Add `--deep` to detect conflicting skills. |
  56. | `skills audit [path]` | Security-scan installed skills, or a folder you specify. |
  57. | `skills score <path>` | Score a skill's quality from 0 to 100. |
  58. | `skills budget -b <tokens>` | Load only the skills that fit a context budget. |
  59. | `skills submit-repo <owner/repo>` | Submit a GitHub repository for marketplace indexing. |
  60. Run `skills --help` or `skills <command> --help` for the full list of commands and options.
  61. ### Install options
  62. ```bash
  63. skills install <source> -a claude,cursor # Specific agents (comma-separated or space-separated)
  64. skills install <source> --all # Every supported agent
  65. skills install <source> -g # Global install (your home directory)
  66. skills install <source> -s <name> # Install one skill from a multi-skill repo
  67. skills install <source> -y # Non-interactive; installs every skill found
  68. skills install <source> --dry-run # Show what would be installed
  69. skills install <source> --skip-audit # Install even when the scan finds critical issues
  70. ```
  71. ## Installing skills
  72. ### Marketplace
  73. ```bash
  74. skills install @anthropics/xlsx
  75. skills search react -a cursor claude # Search, then install the results to agents
  76. skills search python -a claude -y # Install every result without prompting
  77. ```
  78. ### GitHub and Git
  79. ```bash
  80. skills add owner/repo # GitHub shorthand
  81. skills add owner/repo@skill-name # One skill from a repo
  82. skills add owner/repo --list # List the skills a repo contains
  83. skills add https://gitlab.com/org/repo # Any Git host
  84. skills add owner/repo#dev # A specific branch
  85. ```
  86. ### Private repositories
  87. ```bash
  88. skills install git@github.com:team/private-repo.git # SSH, uses your keys
  89. skills install https://git.company.com/team/repo --token $GIT_TOKEN
  90. GITLAB_TOKEN=xxx skills install https://gitlab.com/team/repo
  91. ```
  92. Credentials are resolved in this order: the `--token` flag, then environment variables (`GH_TOKEN`, `GITLAB_TOKEN`, `BITBUCKET_TOKEN`, `GIT_TOKEN`), then SSH keys, then the Git credential helper, then `.netrc`.
  93. ### npm packages
  94. ```bash
  95. skills install npm:@company/skills
  96. skills install npm:@company/skills@1.1.2
  97. skills install npm:@company/skills --registry https://npm.company.com
  98. ```
  99. ### Submitting a repository
  100. ```bash
  101. skills submit-repo owner/repo # Index every SKILL.md in the repo on the marketplace
  102. ```
  103. ## MCP servers, subagents and plugins
  104. Marketplace items can also be MCP servers, subagents or plugins. The CLI detects the type from the slug, or you can set it.
  105. ```bash
  106. skills install github--github-mcp-server # Type is detected automatically
  107. skills install acme--weather --type mcp -a cursor # Force a type: skill, mcp, agent or plugin
  108. skills install acme--weather -e API_KEY=xxx # Set an environment variable for the server
  109. skills install acme--reviewer --type agent # Install a subagent to .claude/agents/
  110. skills remove acme--weather # Removes the MCP entry from each client config
  111. ```
  112. MCP config files are merged, never overwritten. Other servers and keys are kept, a `.bak` copy is written first, and a config file with comments (JSONC) is refused rather than rewritten. Quit the client, such as Claude Code, before a global (`-g`) install.
  113. ## Security
  114. Every command that installs skills from a source (`install`, `add`, `search`, `update`, `frozen`, `install-url` and the interactive installers) scans each skill and subagent before copying it. Critical findings block the install, and high findings print a warning. The scan is an automated signal, not a verdict, so read a skill before you run it.
  115. ```bash
  116. skills audit # Audit installed skills against agentskills.in advisories
  117. skills audit ./my-skill # Audit one folder
  118. skills audit --fail-on high # Exit with code 1 at high severity or above (for CI)
  119. skills audit --json --offline # JSON output without downloading advisories
  120. ```
  121. To report a vulnerability, see [SECURITY.md](SECURITY.md).
  122. ## Context budget and token cost
  123. Each skill costs context tokens. Two commands help manage that:
  124. ```bash
  125. skills list --table # Estimated token cost per skill
  126. skills budget -b 8000 # Pick the most relevant skills for a project, within 8,000 tokens
  127. skills budget -b 4000 --format xml # Agent-ready output
  128. ```
  129. ## Supported agents
  130. `skills install` supports 45 agents. Pass any key from the table to `-a`.
  131. <details>
  132. <summary>All 45 agents</summary>
  133. | Agent | Key | Project directory |
  134. |-------|-----|-------------------|
  135. | Cursor | `cursor` | `.cursor/skills/` |
  136. | Claude Code | `claude` | `.claude/skills/` |
  137. | GitHub Copilot | `copilot` | `.github/skills/` |
  138. | Codex | `codex` | `.codex/skills/` |
  139. | Antigravity | `antigravity` | `.agent/skills/` |
  140. | OpenCode | `opencode` | `.opencode/skill/` |
  141. | Amp | `amp` | `.agents/skills/` |
  142. | Kilo Code | `kilo` | `.kilocode/skills/` |
  143. | Roo Code | `roo` | `.roo/skills/` |
  144. | Goose | `goose` | `.goose/skills/` |
  145. | Cline | `cline` | `.cline/skills/` |
  146. | CodeBuddy | `codebuddy` | `.codebuddy/skills/` |
  147. | Command Code | `command-code` | `.commandcode/skills/` |
  148. | Continue | `continue` | `.continue/skills/` |
  149. | Crush | `crush` | `.crush/skills/` |
  150. | Clawdbot | `clawdbot` | `skills/` |
  151. | Droid | `droid` | `.factory/skills/` |
  152. | Gemini CLI | `gemini-cli` | `.gemini/skills/` |
  153. | Kiro CLI | `kiro-cli` | `.kiro/skills/` |
  154. | MCPJam | `mcpjam` | `.mcpjam/skills/` |
  155. | Mux | `mux` | `.mux/skills/` |
  156. | OpenHands | `openhands` | `.openhands/skills/` |
  157. | Pi | `pi` | `.pi/skills/` |
  158. | Qoder | `qoder` | `.qoder/skills/` |
  159. | Qwen Code | `qwen-code` | `.qwen/skills/` |
  160. | Trae | `trae` | `.trae/skills/` |
  161. | Windsurf | `windsurf` | `.windsurf/skills/` |
  162. | Zencoder | `zencoder` | `.zencoder/skills/` |
  163. | Neovate | `neovate` | `.neovate/skills/` |
  164. | Ara | `ara` | `.ara/skills/` |
  165. | Aide | `aide` | `.aide/skills/` |
  166. | Alex | `alex` | `.alex/skills/` |
  167. | BB | `bb` | `.bb/skills/` |
  168. | CodeStory | `codestory` | `.codestory/skills/` |
  169. | Helix AI | `helix-ai` | `.helix/skills/` |
  170. | Meekia | `meekia` | `.meekia/skills/` |
  171. | Pear AI | `pear-ai` | `.pearai/skills/` |
  172. | Adal | `adal` | `.adal/skills/` |
  173. | Pochi | `pochi` | `.pochi/skills/` |
  174. | Sourcegraph Cody | `sourcegraph-cody` | `.sourcegraph/skills/` |
  175. | Void AI | `void-ai` | `.void/skills/` |
  176. | Zed | `zed` | `.zed/skills/` |
  177. | Lingma | `lingma` | `.lingma/skills/` |
  178. | Deep Agents | `deep-agents` | `.deepagents/skills/` |
  179. | Ruler | `ruler` | `.ruler/skills/` |
  180. </details>
  181. Global installs (`-g`) go to each agent's user-level directory, such as `~/.claude/skills/`.
  182. `skills list` searches the canonical store (`~/.skills/` and `./.skills/`) and every agent's directories, so a skill installed by `skills install` stays discoverable.
  183. ## Configuration
  184. Put a `.skillsrc` or `.skillsrc.json` file in your project or home directory to set private sources and defaults:
  185. ```json
  186. {
  187. "sources": [
  188. {
  189. "name": "company-gitlab",
  190. "type": "git",
  191. "url": "https://gitlab.company.com",
  192. "auth_env": "COMPANY_GIT_TOKEN"
  193. },
  194. {
  195. "name": "company-npm",
  196. "type": "npm",
  197. "registry": "https://npm.company.com",
  198. "scope": "@company"
  199. }
  200. ],
  201. "defaults": {
  202. "agent": "cursor",
  203. "global": false
  204. }
  205. }
  206. ```
  207. The project `.skillsrc` is used first. If there is none, the file in your home directory is used.
  208. ## Environment variables and telemetry
  209. | Variable | Purpose |
  210. |----------|---------|
  211. | `GH_TOKEN` or `GITHUB_TOKEN` | Authenticate to private GitHub repositories |
  212. | `GITLAB_TOKEN` or `GL_TOKEN` | Authenticate to private GitLab repositories |
  213. | `BITBUCKET_TOKEN` or `BB_TOKEN` | Authenticate to private Bitbucket repositories |
  214. | `GIT_TOKEN` | Authenticate to any other Git host |
  215. | `DISABLE_TELEMETRY` or `DO_NOT_TRACK` | Turn off anonymous telemetry |
  216. The CLI sends one anonymous count per command run to `https://www.agentskills.in/api/telemetry`. The count includes the command name (for example `install` or `list`) and the CLI version. It never includes command arguments, skill names, search text, file paths or private repository URLs. The server stores only daily counters, with no IP addresses. The first run prints this notice once.
  217. Telemetry is off in CI environments. Set `DISABLE_TELEMETRY=1` or `DO_NOT_TRACK=1` to turn it off everywhere.
  218. ## Creating a skill
  219. A skill is a folder with a `SKILL.md` file:
  220. ```markdown
  221. ---
  222. name: my-skill
  223. description: What this skill does
  224. ---
  225. # Instructions
  226. Your skill instructions here.
  227. ```
  228. Check it and export it to your agents:
  229. ```bash
  230. skills validate ./my-skill
  231. skills score ./my-skill
  232. skills export
  233. ```
  234. ## Links
  235. - Website: [agentskills.in](https://agentskills.in)
  236. - Marketplace: [agentskills.in/marketplace](https://agentskills.in/marketplace)
  237. - Documentation: [agentskills.in/docs](https://agentskills.in/docs)
  238. - npm: [npmjs.com/package/agent-skills-cli](https://www.npmjs.com/package/agent-skills-cli)
  239. - Release notes: [CHANGELOG.md](CHANGELOG.md)
  240. ## Contributing
  241. Bug reports, feature requests and pull requests are welcome. Read [CONTRIBUTING.md](CONTRIBUTING.md) first.
  242. To work on the CLI from source:
  243. ```bash
  244. git clone https://github.com/Karanjot786/agent-skills-cli.git
  245. cd agent-skills-cli
  246. npm install
  247. npm run build
  248. npm test
  249. ```
  250. ## License
  251. MIT. See [LICENSE](LICENSE).
  252. Maintained by [Karanjot Singh](https://github.com/Karanjot786).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.