SkillKit
Universal skill management for AI coding agents
SkillKit
Skills make AI coding agents smarter. But every agent uses a different format — Claude Code wants .claude/skills/, Cursor uses .mdc, Copilot expects .github/skills/. You end up rewriting the same skill three times, or locking into one platform.
SkillKit fixes this. Write a skill once, deploy it to all 44 agents.
Get Started
npx skillkit@latestThat's it. No global install needed. Or if you prefer:
npm install -g skillkit
skillkit init
skillkit install anthropics/skills
skillkit syncFour commands. Your agents now have skills for PDF processing, code review, and more.
What Can You Do?
Install skills from anywhere
skillkit install anthropics/skills # GitHub
skillkit install gitlab:team/skills # GitLab
skillkit install ./my-local-skills # LocalTranslate between agents
Write for Claude, deploy to Cursor:
skillkit translate my-skill --to cursor
skillkit translate --all --to windsurf # All skills at onceGet smart recommendations
SkillKit reads your package.json, detects your stack, and suggests relevant skills:
skillkit recommend
# 92% vercel-react-best-practices
# 87% tailwind-v4-patterns
# 85% nextjs-app-routerDiscover skills at runtime
Start an API server and let agents find skills on demand:
skillkit serve
# Server running at http://localhost:3737curl "http://localhost:3737/search?q=react+performance"Or use MCP for native agent integration:
{
"mcpServers": {
"skillkit": { "command": "npx", "args": ["@skillkit/mcp"] }
}
}REST API | MCP Server | Python Client
How It Works
SkillKit sits between your skills and your agents. It handles format translation, discovery, and synchronization automatically.
| Layer | What It Does |
|---|---|
| CLI + TUI | Install, translate, recommend, sync |
| APIs | REST server on :3737, MCP via stdio |
| Core | Translation engine, relevance ranker, skill parser |
| Data | 15,000+ skills from 31 curated sources |
Supported Agents
44 agents and counting:
Claude Code | Cursor | Codex | Gemini CLI | OpenCode | GitHub Copilot | Windsurf | Amp | Antigravity | Clawdbot | Cline | CodeBuddy | CommandCode | Continue | Crush | Droid | Factory | Goose | Kilo Code | Kiro CLI | MCPJam | Mux | Neovate | OpenHands | Pi | Qoder | Qwen | Roo Code | Trae | Vercel | Zencoder | Universal
Security scanning
Every skill is scanned for threats before installation — prompt injection, hardcoded secrets, command injection, and more:
skillkit scan ./my-skill # 46+ detection rules
skillkit scan ./my-skill --format sarif # GitHub Code Scanning
skillkit scan ./my-skill --fail-on high # CI gateBeyond Basic Skills
Session Memory
Your AI agents learn patterns during sessions, then forget everything. SkillKit captures those learnings and makes them permanent.
skillkit memory compress
skillkit memory search "auth patterns"
skillkit memory export auth-patternsSession Intelligence
Track skill executions, generate handoff documents for agent switching, and view skill impact lineage:
skillkit timeline # Unified event stream
skillkit session handoff # Agent-to-agent context
skillkit lineage # Skill impact graphPrimer
Auto-generate CLAUDE.md, .cursorrules, and agent instructions by analyzing your codebase:
skillkit primer --all-agentsMesh Network
Distribute agents across machines with encrypted P2P:
skillkit mesh init
skillkit mesh discoverTeam Collaboration
Share skills via a Git-committable .skills manifest:
skillkit manifest init
skillkit manifest add anthropics/skills
git commit -m "add team skills"Team members run skillkit manifest install and they're in sync.
Next Steps
- Installation — Install and configure
- Quick Start — First project setup
- Security Scanner — Threat detection for skills
- Commands — Full CLI reference
- REST API — Runtime discovery server
- MCP Server — Agent-native discovery
- Python Client — Python SDK