Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
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.
- Stars
- 19,179
- +7 days
- —
- Forks
- 1,833
- Language
- Python
- License
- MIT
- Last push
- 21 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This framework optimizes reusable natural-language skills for frozen LLM agents without modifying model weights. It turns scored execution trajectories into bounded text edits on markdown documents, accepting changes only when they pass validation gates. The final output is a compact markdown skill file ready to deploy in agents like Claude Code.
Use it when
- Optimize agent skill prompts using validation feedback without fine-tuning underlying model weights
- Generate a compact markdown skill artifact to boost task performance in Claude Code or Codex
- Run offline nightly evolution loops to learn skills from recorded developer agent sessions
Install
pip install -e ".[webui]"Commands quoted from the repo's README. Read the README before running them.
Includes hooks that run shell commands on your machine. Read them before installing.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.