Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.
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.
Repository statistics
Indexed skills
2
Skill groups
2
GitHub stars
19,153
Forks
1,835
Skills by folder
2 totalPlugins
1 skillSkills
1 skillUse when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated CLAUDE.md/SKILL.md behind a held-out gate.
Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
<a href="https://skilld.dev/gh/microsoft/skillopt">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/microsoft/skillopt?theme=dark">
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/microsoft/skillopt?theme=light">
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/microsoft/skillopt?theme=light">
</picture>
</a>