open-source · MIT · v0.6.2 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.

🏖️ Get started 🌐 Join public hub ★ GitHub

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

💎 SKILL.md canary ✓
v3·UX 8.7/10·winning

example — a Skill is a versioned git dir, kept by its UX score

greetings from  ~/.xskill/skill 🌅
🏷️v0.6.2current release
🌴0agents supported
🐍3.9+Python
🌊MITopen source
latest release

v0.6.2 adds identity-aware recommendations

The current README highlights user profiling, SkillHub retrieval, UX score APIs, and Windows scheduled-task persistence.

ID

Stable user identity

80

Hybrid recommendations

UX

UX score queries

WIN

Windows daemon

how it works

A few narrow agents, one self-growing library

Every Skill is its own git repository — every change versioned and reversible.

  1. 👀

    1 Watch

  2. 🔪🥥

    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>/
🛶 Codex CLIverified~/.codex/sessions/~/.agents/skills/<name>/
🐙 OpenCodeverifiedopencode.db (SQLite)~/.agents/skills/<name>/
🐚 OpenClawimplemented~/.openclaw/agents/~/.agents/skills/<name>/
💠 Cursorimplemented~/.cursor/.../agent-transcripts/~/.cursor/skills/<name>/
🚄 Traeimplementedstate.vscdb / trajectory_*.json~/.trae-cn/skills/, ~/.trae/skills/
Any other agentmanualxskill.adapters.submit_trajectorycopy / symlink SKILL.md

Status as of v0.6.2 · 🟡 implemented, with Claude Code / Codex / OpenCode verified.

vocabulary

Five words and you've got it

🧭

Trajectory

⚛️

Atom

💎

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> --name <user-id>
🪄

Silently distill your top performers

🔌

Any workflow plugs in

🔒

Trajectories stay private

🧪

A/B-driven evolution

🧑‍🏫

Experts can teach by hand

公网演示实例

一键粘贴，接入我们的公网实例

不用自己搭服务端。装好 xskill，粘贴下面这条连接命令，再填上你自己的用户名即可。

🌐

地址

https://hub.xskill.wiki

🔑

连接令牌

dd7f641c16ced6d1db43e754055fd2c8

📊
公网实例 
# 1）安装　2）把 YOUR_NAME 换成你的用户名
$ pip install -U xskill
$ xskill connect https://hub.xskill.wiki --token dd7f641c16ced6d1db43e754055fd2c8 --name YOUR_NAME
why xskill

Stop hand-maintaining a prompt library that rots

🥥

Distilled automatically

🌱

Grows itself

✋

Learns from your edits

⭐

UX-driven evolution

🌅

Start here if you're new

~/.xskill — bash
# install — Python 3.9+
$ pip install -U xskill
# 1. join public hub (fastest, no keys needed):
$ xskill connect https://hub.xskill.wiki --token dd7f641c16ced6d1db43e754055fd2c8 --name YOUR_NAME
# 2. or run standalone locally (private, bring your own key):
$ xskill serve
# 3. or host a team server:
$ xskill serve --server

Five commands people ask about first

xskill generate Ask in one sentence; the server writes or rewrites a skill. xskill upload Share a finished skill folder so teammates can search it. xskill import Bring an existing skill into xskill's own library. xskill search Search the shared library by keywords to get skill IDs or install matches. edit, then it uploads Change a skill file on your machine; the draft goes to the server by itself.
Read the command guide Add a docs page ★ Star on GitHub