Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and Antigravity.
# Agent Skills CLI š > **One CLI. 175,000+ skills. 45 AI agents.** [](https://www.npmjs.com/package/agent-skills-cli) [](LICENSE) Install skills from the world's largest marketplace and sync them to **45 AI agents** including Cursor, Claude Code, GitHub Copilot, Windsurf, Cline, Cursor CLI, Zed, and more ā all with a single command. **What's new in v1.1.7:** Glob matching (`--skill 'core-*'`), prune stale skills (`--prune`), branch targeting (`owner/repo#dev`), and 3 new agents (Lingma, Deep Agents, Ruler) š **Website:** [agentskills.in](https://agentskills.in) ```bash npm install -g agent-skills-cli skills install @anthropic/xlsx ``` --- ## ⨠Features - **175,000+ Skills** ā Access the largest collection of AI agent skills - **42 AI Agents** ā Cursor, Cursor, Cursor, Windsurf, Cline, Cursor CLI, Zed, and 35+ more - **FZF Interactive Search** ā Real-time search with keyboard navigation: `skills search -i` - **Conflict Detection** ā Find contradictions and overlaps across skills: `skills doctor --deep` - **Context Budget** ā Smart token-aware skill selection for your project: `skills budget -b 8000` - **Skill Diff** ā Section-aware comparison of two skills: `skills diff A B` - **Frozen Installs** ā Deterministic lockfile-based installs (like `npm ci`): `skills frozen` - **Skill Compose** ā Merge, chain, or conditionally combine skills: `skills compose A B -o C` - **Skill Testing** ā 10 built-in quality assertions + custom tests: `skills test --all` - **Sandbox Preview** ā Quality + conflicts check before install: `skills sandbox @owner/repo` - **Watch Mode** ā Auto-sync skills to agents on file changes: `skills watch` - **Skill Splitter** ā Split large skills into focused sub-skills: `skills split my-skill` - **Benchmarking** ā Compare skill quality across your collection: `skills bench --all` - **Private Git Repos** ā GitLab, Bitbucket, S
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.