SkillOpt — Microsoft Open Source Repository
MIT-licensed framework from Microsoft Research for optimizing AI agent skill markdown documents without modifying underlying model weights.
Core concept
Agent skills are stored as .md files containing procedural knowledge — domain heuristics, tool-use policies, output constraints, failure modes. SkillOpt treats these documents as trainable external state of a frozen LLM agent.
Optimization loop
- Run frozen target model on scored task batches
- Separate optimizer model proposes bounded add/delete/replace edits
- Held-out validation gate accepts edits only when performance strictly improves
- Textual learning-rate budget limits edit magnitude per step
- Rejected-edit buffer prevents repeated failed modifications
- Epoch-wise slow/meta update for long-horizon stability
Output artifact
Exports compact best_skill.md (~300–2,000 tokens, median ~920) with zero additional inference-time model calls at deployment.
Quick start
pip install skillopt
python scripts/train.py --config configs/searchqa/default.yaml \
--split_dir /path/to/split --optimizer_model gpt-5.5 --target_model gpt-5.5Benchmark results (paper)
- Best or tied on all 52 (model, benchmark, harness) cells evaluated
- GPT-5.5: +23.5 average absolute points vs no-skill baseline (direct chat)
- Cross-harness transfer: Codex-trained spreadsheet skill → +59.7 points in Claude Code
- Training cost: ~$1–5 per single-task skill via community frameworks (GBrain)
License
MIT — compatible with commercial deployment and modification.