sybil-solutions/skill-distill
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task
- Stars441
- Forks40
- LanguagePython
- LicenseMIT
GitHub counts sampled
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task
GitHub counts sampled
24 hours Rising board · Reached #2 on Nov 21 and appeared on 2 days in the last week. At the Nov 22, 17:16 UTC check, Trendoday estimated a gain of 199 stars over 24 hours.
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to reproduce the task
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:
Description and README excerpt from sybil-solutions/skill-distill on GitHub ↗.
sybil-solutions/skill-distill was first seen on GitHub · Rising today on Nov 21, 2026. Since then it has appeared in 63 checks on 2 different days. Its best position was #2 of 30, reached on Nov 21, 23:46 UTC. It is #21 right now, slipping from #17 to #21 over the last 6 checks.
Position on GitHub · Rising today at every check (lower is better).
Best rank per day (UTC).
Estimated stars gained over 24 hours at each check.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 22, 17:16 UTC it is #21, slipping from #17 to #21 over the last 6 checks.
#2 on GitHub · Rising today, on Nov 21, 23:46 UTC.
It was first seen on Nov 21, 2026 and has been on the list on 2 days (63 checks) since.
Mostly Python; it is licensed under MIT. It has 441 stars and 40 forks.