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.
SkillOpt is a tool for improving reusable natural-language skills used by fixed-weight language-model agents through training runs, trajectory-based edits, validation checks, and generated best_skill.md files. It is intended for developing, evaluating, and deploying agent skills without changing the underlying model weights. Catalogue add-ons support SkillOpt workflows and integrations with coding agents.
▶ SkillOpt: How Microsoft Rewrites skills.md Files To Boost LLM Agents 25% AwesomeFOSS · about microsoft/SkillOpt · on YouTube → Skill Claude CodeCodex ✓ vendor
Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.