sybil-solutions/skill-distill
AI skill
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 2 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change yesterday.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A skill for Claude Code or Codex that distills a successful session into instructions an open-weight model can follow to reproduce the same task. It runs a loop in tmux: the student model attempts the task from a clean start, its output is compared with the reference, and the…
Who it's for
Developers who want cheaper open-weight models to reproduce tasks a frontier model completed well, using Claude Code or Codex
How to use it
Install
git clone https://github.com/sybil-solutions/skill-distillFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up sybil-solutions/skill-distill in my project. Follow its README: https://github.com/sybil-solutions/skill-distill. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/sybil-solutions/skill-distill?ref=badge)Similar repos
- dotslashsimran/simcraft
A collection of Claude Code skills, each a folder with a SKILL.md describing a method, judgement calls and tested scripts for one kind of work. Covers video, engineering, learning, design and planning
- sybil-solutions/inference-optimisation-skill
An agent skill that guides an AI agent through hill-climbing the serving speed of a local LLM: decode, speculative decoding, prefill, KV cache size, startup and time to first token. It provides a proc
- sous-labs/songe
A local training engine that records how a user works with a locally served model through agents such as opencode or pi. It turns corrections, stated preferences and tool errors into lessons, then upd
- ecapri-dev/simulab-skill
A Claude Code skill that turns any idea into a self-building interactive 3D lab in a single HTML page, explaining through chapters and then letting the user manipulate it. Numbers on screen come from
- guilhermealvestech/carrossel-skill
A Claude Code and Codex skill that creates branded Instagram-style carousels, from script to 2x PNG, with a gallery, slider, version comparison and ready caption. Uses brand onboarding and a taste fil
- Bil0000/Hill-Climb
A Claude Code and Codex skill with a single Python script that makes a coding agent work in small steps against a locked command or test score. A step is committed only if the score improves and the g