Minimal faithful re-implementation of Microsoft SkillOpt: a text-space optimizer that trains a deployable natural-language skill for a frozen LLM agent on HotpotQA.
1 file for Claude Code: skillopt-qa CLAUDE.md — 1,281 tokens loaded in every session.
CLAUDE.md A 1,281 tok These files are joshhu/skillopt-qa's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.