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.
★ 19,088⑂ 1,830👁 67⑃ 295● 116▤ 2
More from this author
+10
Daily
19,088
stars
1,830
forks
67
watchers
295
prs
116
issues
2
releases
README
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.
📖 For installation, data preparation, training/eval commands, configuration, and framework internals, start with the versioned SkillOpt documentation. A concise rendered overview is available in the Documentation & Reproduction Guide, and longer-form engineering analysis appears on the Technical Blog. We also maintain a Changelog for released and unreleased changes.
---
News 🔥🔥🔥
- [2026-11] 🎤 SkillOpt is accepted to NeurIPS 2026 as a Spotlight! See you in Sydney!
- [2026-11] 🏆 SkillOpt won 1st Place in the Executive Challenge at the Microsoft Global Hackathon 2026 (badge, issued by The Microsoft Garage).
- [2026-07-24] 📰 SkillOpt in the news. Read the official Microsoft Research feature, along with recent coverage from VentureBeat, Synced (机器之心), Flowtivity, and The Decoder.
- [2026-07-02] 🚀 SkillOpt v0.2.0 is out on PyPI! Headline feature: SkillOpt-Sleep, a nightly offline self-evolution engine (harvest → mine → replay → consolidate behind a held-out validation gate), now shipped as the skillopt-sleep CLI. It also includes experimental multi-objective, replay, and dream-rollout controls; the main CLI keeps conservative defaults and does not expose every experiment-harness control as a flag. The release source adds integration shells for Claude Code, Codex, Copilot, and Devin, plus an OpenClaw reference adaptation; these plugin/MCP files live in the repository rather than the PyPI wheel. It also adds SearchQA split materialization, Windows robustness, and hardened JSON parsing. See the release notes for full release details and contributor acknowledgements.
- [2026-06-15] 😴 SkillOpt-Sleep (preview) — a nightly offline self-evolution companion for local coding agents (Claude Code / Codex / Copilot): review past sessions, replay recurring tasks, and consolidate validated skills behind a held-out gate. See docs/sleep/README.md for what it is, how to use it, and results.
- [2026-06-03] 🎉 gbrain, gbrain-evals, and darwin-skill have all integrated SkillOpt.
- [2026-06-02] 🎉 SkillOpt v0.1.0 is now available on PyPI! Install with pip install skillopt. This initial release includes the full training loop (rollout → reflect → aggregate → select → update → evaluate), multi-backend support (OpenAI / Azure / Claude / Qwen / MiniMax), six built-in benchmarks, and WebUI dashboard.
---
Overview
Modern agent skills are usually hand-crafted, generated one-shot by a strong
LLM, or evolved through loosely controlled self-revision — none of which
behaves like a deep-learning optimizer for the skill itself, and none of
which reliably improves over its starting point under feedback.
SkillOpt treats the skill document as the trainable state of a frozen
agent, and trains it with the discipline that makes weight-space
optimizTop issues
#132Help wanted: integrate SkillOpt with Superpowers for measurable agent efficiency12 comments · 2026-07-13#154Mining is limited to programmatic success checks — intent-level improvements get dropped or Goodharted into shallow proxy rules11 comments · 2026-07-19#158Several reported scores are incompatible with the released test split sizes7 comments · 2026-07-19#286skillopt-sleep Codex harvest ingests its own headless replay sessions6 comments · 2026-09-20#155Proposal: AgenticReplayBackend — replay mined tasks with a real agentic CLI in a throwaway worktree, gate on the diff6 comments · 2026-07-19#288Release cut for the Aug adopt/webui hardening + 2 residual staging gaps4 comments · 2026-09-20#247skillopt-sleep: adopt() writes a backup that nothing can restore — add a `revert` command4 comments · 2026-08-22#97SkillOpt-Sleep: Support harvest from Vscode/ Visual studio copilot sessions4 comments · 2026-07-02
Latest release
SkillOpt v0.2.0 — SkillOpt-Sleep v0.2.0 2026-07-02[0.2.0] — 2026-07-02 The headline of this release is SkillOpt-Sleep: a nightly offline self-evolution engine that harvests a coding agent's real session transcripts, mines recurring tasks, replays them offline, and consolidates short-term experience into long-term memory and skills — all behind the same held-out validation gate that keeps SkillOpt training honest. It ships as a decoupled top-level package (skillopt_sleep/, zero dependency on the research code) and as the new skillopt-sleep CLI. Added - SkillOpt-Sleep engine — nightly offline self-evolution cycle (harvest → mine → replay →