microsoft

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.

10.3K stars 965 forks 10.3K watchers Python MIT License
agent-skills self-evolving-agents
View on GitHub Website
2 Open Issues Need Help Last updated: Jul 1, 2026

Open Issues Need Help

View All on GitHub
Help wanted: integrate SkillOpt with Superpowers for measurable agent efficiency about 2 hours ago
enhancement help wanted
microsoft/SkillOpt
10.3K

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.

Python
#agent-skills#self-evolving-agents
Strengthen verifier-discipline test to assert held-out scores and gate_action (follow-up to #87) 6 days ago
enhancement good first issue
microsoft/SkillOpt
10.3K

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.

Python
#agent-skills#self-evolving-agents