πŸ“ open-source Β· MIT Β· v0.5.1 on PyPI

Trajectories in.
Reusable skills out.

One solves it. Everyone gets it.

Your coding agent re-derives the same solution every time it hits a familiar problem. xskill distills the patterns that actually worked into Skill files your agent loads automatically.

MIT-licensed Β· Python 3.9+ Β· no model weights touched.

πŸ’Ž SKILL.md canary βœ“
v3Β·UX 8.7/10Β·winning

example β€” a Skill is a versioned git dir, kept by its UX score

greetings from  ~/.xskill/skill πŸŒ…
🏷️v0.5.1current release
🌴0agents supported
🐍3.9+Python
🌊MITopen source
how it works

A few narrow agents, one self-growing library

Every Skill is its own git repository β€” every change versioned and reversible.

  1. πŸ‘€

    1 Watch

  2. πŸ”ͺπŸ₯₯

    2 Split into Atoms

  3. 🧭

    3 Route to a Skill

  4. ✍️

    4 Rewrite SKILL.md

  5. 🐀

    5 Canary A/B + UX score

works with your agents

Plug into the agent you already use

Trajectory ingest and Skill install are wired up per ecosystem.

Agent Status Trajectory ingest Skill install
🌴 Claude Codeverified~/.claude/projects/~/.claude/skills/<name>/
πŸ›Ά Codex CLIverified~/.codex/sessions/~/.agents/skills/<name>/
πŸ™ OpenCodeverifiedopencode.db (SQLite)~/.agents/skills/<name>/
🐚 OpenClawnot well tested~/.openclaw/agents/~/.agents/skills/<name>/
πŸ’  Cursornot well tested~/.cursor/.../agent-transcripts/~/.cursor/skills/<name>/
Any other agentmanualxskill.adapters.submit_trajectorycopy / symlink SKILL.md

Status as of v0.5.x · 🟑 implemented but not well tested yet.

vocabulary

Five words and you've got it

🧭

Trajectory

βš›οΈ

Atom

πŸ’Ž

Skill

🐀

Canary

⭐

UX score

the killer use case

Team mode: one library, the whole team

One machine is the server; everyone else joins as a thin client.

team
# Start a server, then join from any machine:
$ xskill serve --server
$ xskill connect <host:port> --token <token>
πŸͺ„

Silently distill your top performers

πŸ”Œ

Any workflow plugs in

πŸ”’

Trajectories stay private

πŸ§ͺ

A/B-driven evolution

πŸ§‘β€πŸ«

Experts can teach by hand

why xskill

Stop hand-maintaining a prompt library that rots

πŸ₯₯

Distilled automatically

🌱

Grows itself

βœ‹

Learns from your edits

⭐

UX-driven evolution

πŸŒ…

Distill your first Skill in two lines.

~/.xskill β€” bash
# install β€” Python 3.9+
$ pip install xskill
# writes ~/.xskill/config.yaml, then exits β€” add your model keys
$ xskill serve
# run again: auto-detects your agents and starts watching
$ xskill serve