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.
- agent-skills
- self-evolving-agents
47,133 repositories indexed
1–3 of 3 · Most stars
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.
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
A Python toolkit for generating human-readable timetables from GTFS data; uses PANDAS and gtfs_kit