claudeers.
// Other

skill-distill

Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task

// Other[ cli ][ api ][ web ][ claude ]#claude#other◷ MIT$open-sourceupdated 39 minutes ago

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.
// or clone
git clone https://github.com/sybil-solutions/skill-distill

// compatibility

Platformscli, api, web
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguagePython

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

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:

  1. reads the session and writes a skill for the student;
  2. starts the student in tmux, on a fresh copy of the starting state, with the original prompt and the skill;
  3. compares what the student produced with what the reference produced;
  4. finds the first place the student went wrong and fixes the skill there;
  5. 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

pathwhat
skills/skill-distill/SKILL.mdthe loop the teacher follows
skills/skill-distill/scripts/distill.pyrun bookkeeping: init, trial, status, wait, evidence, verdict, ledger, report, accept
skills/skill-distill/scripts/extract_session.pyClaude Code / Codex / omp session log → readable reference (drops system and AGENTS.md text)
skills/skill-distill/scripts/capture_web.pyserve 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

harnessstatus
omp (oh-my-pi)tested
Codex CLItested as the teacher; as a student needs a provider in STUDENT_ARGS
Claude Codewritten; open models need ANTHROPIC_BASE_URL to an Anthropic-compatible server
piwritten, untested
opencodewritten, 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.

0 views
★ 368 stars
unclaimed
updated 39 minutes ago

// embed badge

skill-distill on Claudeers
[![Claudeers](https://claudeers.com/api/badge/skill-distill.svg)](https://claudeers.com/skill-distill)

// retro hit counter

skill-distill hit counter
[![Hits](https://claudeers.com/api/counter/skill-distill.svg)](https://claudeers.com/skill-distill)

// reviews

// guestbook

0/500

// related in Other

🔓

符合nature论文学术表达和科研绘图的Skill

// otherYuan1z0825/⟨Python⟩★ 54,085◷ Apache-2.0[ claude ]
🔓

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

// otherNutlope/⟨CSS⟩★ 49,642◷ MIT[ claude ]
🔓

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

// otheralchaincyf/⟨HTML⟩★ 28,944◷ MIT[ claude ]
🔓

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

// othermanaflow-ai/⟨Swift⟩★ 28,842◷ NOASSERTION[ claude ]
→ see how skill-distill connects across the ecosystem