microsoft/SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
About the project
A text-space optimizer that trains reusable natural-language skills for frozen LLM agents via trajectory-driven edits, validation-gated updates, and a deployable best_skill.md artifact. Model weights stay untouched.
Useful for
- Train an agent skill on your own dataset and get best_skill.md without fine-tuning the model
- Run nightly self-evolution via skillopt-sleep for Claude Code or Codex
- Evaluate transfer of a trained skill across different models and harnesses
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 46 stars so far today, about 96 expected by the end of the day. The usual pace is 40 per day, so that's 2.4× as much.
- Over the last two days the pace is 2.6× that of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- GitHub Trending Python today: #6, +111 stars.
- About 13 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 17,738
- Today
- 46 · ≈ 96 by evening
- Forks
- 1,658
- Issues and pull requests
- 292
- Watchers
- 69
- Language
- Python
- License
- MIT
- Latest release
- v0.2.0 · July 2, 2026
- Created
- May 8, 2026
- Last push
- September 5, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 28, 2026GitHub Trending Python today: #6, +111 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/microsoft/SkillOpt)Similar by description
-
0.0
flybook-git/flm
A research project that trains a small adapter on top of a frozen LFM2.5-1.2B LLM; the adapter reads the state of the full MaleCNS v1.0 fly connectome (166,700 nodes, 25.5M edges) and adjusts next-token logits. Only…
-
1.9
microsoft/agent-lightning
A lightweight (~3,500 LOC) reinforcement-learning framework for training AI agents with their real harnesses: agents run unchanged while a proxy gateway captures training data. Includes Kubernetes support and…
-
4.6
Human-Agent-Society/reef
Continual learning infrastructure for self-improving agents: connects agent inference, feedback collection, learning, and versioned delivery of updates. Lets you train model weights or improve an agent's harness…