
skill-distill
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
Install and set up skill-distill (git-clone project) into my current project. Found on https://claudeers.com/skill-distill Repo: https://github.com/sybil-solutions/skill-distill Homepage/docs: — Detected install method: git-clone → git clone https://github.com/sybil-solutions/skill-distill Category: other. Platforms: cli, api, web. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: unknown; community-verified: false. Confirm the source before running anything.
git clone https://github.com/sybil-solutions/skill-distill
// compatibility
| Platforms | cli, api, web |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | MIT |
| Pricing | open-source |
| Language | Python |
skill-distill
A frontier model did a task well. Can an open-weight model do the same task, given the right instructions?
skill-distill is a skill for Claude Code or Codex (the teacher). You call it at the end of a good
session and name a student: an agent harness plus a model, for example omp with DeepSeek-V4.1-Flash.
The teacher then loops:
- reads the session and writes a skill for the student;
- starts the student in tmux, on a fresh copy of the starting state, with the original prompt and the skill;
- compares what the student produced with what the reference produced;
- finds the first place the student went wrong and fixes the skill there;
- runs again, three trials per version, until the student matches the reference.
You make the final call: the teacher shows you the reference and the student's best results side by side, and the skill counts as done only when you accept it.
The result is two things: the reusable operator skill in this repo, and a produced skill for one task, one model and one harness.
Install
git clone https://github.com/sybil-solutions/skill-distill
ln -s "$PWD/skill-distill/skills/skill-distill" ~/.claude/skills/skill-distill # Claude Code
ln -s "$PWD/skill-distill/skills/skill-distill" ~/.agents/skills/skill-distill # Codex
Requirements: tmux, git, Python 3.10+, and the student harness installed and pointed at its model.
For web results, pip install playwright pillow && playwright install chromium.
Use
At the end of a session that went well:
distill this session into a skill for omp with deepseek-v4.1-flash on my local server
The teacher follows skills/skill-distill/SKILL.md. You can watch the
students work with tmux attach -t distill-<task>.
What's in it
| path | what |
|---|---|
skills/skill-distill/SKILL.md | the loop the teacher follows |
skills/skill-distill/scripts/distill.py | run bookkeeping: init, trial, status, wait, evidence, verdict, ledger, report, accept |
skills/skill-distill/scripts/extract_session.py | Claude Code / Codex / omp session log → readable reference (drops system and AGENTS.md text) |
skills/skill-distill/scripts/capture_web.py | serve a web app, drive it in headless Chromium, save screenshots and errors |
skills/skill-distill/adapters/ | one script per student harness: omp, pi, Codex, Claude Code, opencode |
skills/skill-distill/templates/student-skill/ | the starting shape of a produced skill |
examples/ | finished runs: the prompt, the produced skill, the ledger, screenshots |
Rules the teacher follows
- The student gets the reference's prompt verbatim, a clean starting state, and the skill. Nothing else: the student harness's own global context files and skills are turned off where the harness allows it.
- The skill may not contain the reference's finished output or a script that writes it. It teaches the steps, decisions, traps and checks; short snippets only where the student can't get a part right otherwise.
- Three trials per skill version. One lucky run proves nothing.
- Checks are tested on the reference first. A check that fails on the reference is a broken check.
- Raw session logs stay in
runs/, which is git-ignored: they contain your machine's paths and context.
Adapters
| harness | status |
|---|---|
| omp (oh-my-pi) | tested |
| Codex CLI | tested as the teacher; as a student needs a provider in STUDENT_ARGS |
| Claude Code | written; open models need ANTHROPIC_BASE_URL to an Anthropic-compatible server |
| pi | written, untested |
| opencode | written, untested; its JSON log has no parser in extract_session.py yet |
License
MIT
// faq
What is skill-distill?
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task. It is open-source on GitHub.
Is skill-distill free to use?
skill-distill is open-source under the MIT license, so it is free to use.
What category does skill-distill belong to?
skill-distill is listed under other in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/skill-distill)
// retro hit counter
[](https://claudeers.com/skill-distill)
// reviews
// guestbook
// related in Other
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.