handoff-protocols

One skill. Every agent. 46 of them.

Quick nav

Quick start · Install · Commands · Agents · Sources · API · Website

---

https://github.com/user-attachments/assets/b1843a07-2c54-422d-8903-f30a790cfb37

The problem

Every AI coding agent wants skills. Every agent invented a different format.

You rewrite the same skill for each agent. Or you lock in to one.

The fix

SkillKit is the package manager for AI agent skills. Install from 400K+ skills across 31 sources. Auto-translate between formats. Persist session learnings. Ship to 46 agents at once.

npx skillkit add anthropics/skills

That is the whole first-run. Pick your agent (your detected agent is pre-selected), confirm, done.

Quick start

npx skillkit init                     # detect agent, create dirs
skillkit recommend                    # stack-aware suggestions
skillkit add anthropics/skills        # install from marketplace
skillkit sync                         # deploy to agent config

Four commands. Your agent now has PDF processing, code review, auth patterns, and whatever you need.

What the first install looks like

$ npx skillkit add anthropics/skills

 ◇ Detected 32 agents
 │
 ◆ Install to
 │  ● Just Claude Code (detected)      claude-code
 │  ○ Select specific agents           space to toggle
 │  ○ All supported agents             32 agents, writes to every adapter
 └

 ◇ Cloning anthropics/skills
 ◇ Security scan: 42/42 skills pass
 ◇ Installed 42 skills to Claude Code
 │
 └ Done in 3.1s. Run `skillkit list` to see them.

Install

Pick one. All three do the same thing.

npm install -g skillkit       # npm
pnpm add -g skillkit          # pnpm
bun add -g skillkit           # bun

Both skillkit and sk work as the binary name.

Full vs slim

Four features ship as optional packages so a bare CLI stays small. The default install pulls everything. Add --omit=optional if you only want the core.

Cold install numbers on a fresh npm cache:

Skipped optional? Add just the one you want later:

npm i -g @skillkit/tui         # enables: skillkit ui
npm i -g @skillkit/api         # enables: skillkit serve
npm i -g @skillkit/mesh        # enables: skillkit mesh
npm i -g @skillkit/messaging   # enables: skillkit message

The CLI catches missing optional packages and prints a one-line hint. No stack trace.

Using npx

npx skillkit add <owner/repo> works with zero install. First call caches the package under ~/.npm/_npx/. Every run after that is instant until a new version ships.

npx skillkit add anthropics/skills                    # full
npx --omit=optional skillkit add anthropics/skills    # slim

If you reach for npx skillkit more than twice, switch to a global install. Kills the prompt-to-proceed and the per-release refetch.

What you can do

skillkit add anthropics/skills           # GitHub
skillkit add gitlab:team/skills          # GitLab
skillkit add ./my-local-skills           # local path
skillkit add https://gist.github.com/... # gist

Write once for Claude, ship everywhere:

skillkit translate my-skill --to cursor
skillkit translate --all --to windsurf,codex
skillkit translate my-skill --to copilot --dry-run

SkillKit reads your repo, spots your stack, ranks skills:

$ skillkit recommend

  92% vercel-react-best-practices
  87% tailwind-v4-patterns
  85% nextjs-app-router
  81% shadcn-ui-components

Start the server, let agents fetch skills on demand:

skillkit serve
# http://localhost:3737

curl "http://localhost:3737/search?q=react+performance"

Or wire it up with MCP:

{
  "mcpServers": {
    "skillkit": { "command": "npx", "args": ["@skillkit/mcp"] }
  }
}

Or call from Python:

from skillkit import SkillKitClient

async with SkillKitClient() as client:
    results = await client.search("react performance", limit=5)

REST docs · MCP docs · Python client