SkillOpt Project Page

Official Microsoft project site for SkillOpt — a text-space optimizer that trains reusable natural language skills for frozen language model agents.

Design principles

  • Skill as parameter: The markdown skill document is the optimization target; target model, backend, and harness stay fixed
  • Validation-gated edits: Plausible-sounding text changes are rejected unless held-out validation improves
  • Deep-learning discipline: Rollout evidence (forward pass), reflection (backward pass), bounded textual learning rate
  • Deployment efficiency: No extra inference calls; portable best_skill.md artifact

Key components

ComponentRole
Optimizer modelProposes structured skill edits from scored rollouts
Validation gateStrict held-out performance check before accepting edits
Edit budgetTextual learning rate controlling per-step change magnitude
Rejected-edit bufferNegative memory preventing repeated failed edits
Slow/meta updateEpoch-wise comparison stabilizes long training runs

Transfer experiments

Optimized skills retain value when moved across:

  • Model scales (frontier → smaller models)
  • Execution harnesses (Codex CLI ↔ Claude Code)
  • Related benchmarks without re-optimization

Resources

  • Paper: arXiv:2605.23904
  • Code: github.com/microsoft/SkillOpt
  • PyPI: pip install skillopt

Authors

Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue Yang, Chong Luo (Microsoft Research Asia and academic collaborators).