microsoft/SkillOpt sits at 19.0k stars on GitHub, written primarily in Python. 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.
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
WHY NO REVIEW YET
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
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
optimization reproducible. A separate optimizer model turns scored rollouts
into bounded add / delete / replace edits on a single skill document; in the
default paper-style path, a candidate edit is accepted only when it strictly
improves a held-out validation score. A textual learning-rate budget, a rejected-edit buffer,
and an epoch-wise slow / meta update make skill training stable while
adding zero inference-time model calls at deployment.
The deployed artifact is a compact best_skill.md (typically 300–2,000
tokens) that runs against the unchanged target model. Across six
benchmarks, seven target models, and three execution harnesses (direct
chat, Codex CLI, Claude Code CLI), SkillOpt is best or tied-best on all
52 evaluated (model, benchmark, harness) cells and on GPT-5.5 lifts the
average no-skill accuracy by +23.5 points in direct chat, +24.8 inside
the Codex agentic loop, and +19.1 inside Claude Code. Optimized skill
artifacts transfer across model scales, between Codex and Claude Code
harnesses, and to nearby benchmarks without further optimization.
For the full method, ablations, and per-cell results see the paper; for a visual walkthrough of the loop see the project page; for deeper API / backend / benchmark docs see docs/.
A backend = a chat / exec target (e.g. openai_chat, claude_chat,
qwen_chat, minimax_chat, copilot_chat, openai_compatible, codex_exec,
claude_code_exec, cursor_exec, copilot_exec). If a provider implements the OpenAI Chat Completions
protocol, try the built-in openai_compatible backend before adding code. See
docs/guide/new-backend.md for the full
contract. Chat backends add a skillopt/model/<name>_backend.py module;
target-only exec backends use the shared harness in codex_harness.py.
Both register through common.py, backend_config.py, and
skillopt/model/__init__.py.
Adding a new benchmark
A benchmark = a skillopt/envs/<name>/ package with an adapter, a data loader,
a scored rollout helper, a YAML config, and optionally an initial seed skill.
See
docs/guide/new-benchmark.md for the full
contract; the simplest reference is skillopt/envs/searchqa/.
The default host is loopback-only. Exposing the dashboard (--host 0.0.0.0 or --share) requires
--auth-user/--auth-pass (or SKILLOPT_WEBUI_USER/SKILLOPT_WEBUI_PASS).
Citation
@article{yang2026skillopt,
title={Skillopt: Executive strategy for self-evolving agent skills},
author={Yang, Yifan and Gong, Ziyang and Huang, Weiquan and Yang, Qihao and Zhou, Ziwei and Huang, Zisu and Li, Yan and Gao, Xuemei and Dai, Qi and Liu, Bei and others},
journal={arXiv preprint arXiv:2605.23904},
year={2026}
}
The most recent commit recorded on microsoft/SkillOpt was 7 days ago, based on the GitHub push timestamp. The repository has 1.8k forks — one of the better signals of community interest.
How many stars does microsoft/SkillOpt have?
microsoft/SkillOpt has 19.0k GitHub stars — refresh the page for the live number, or check github.com/microsoft/SkillOpt. TopGit mirrors GitHub's count but does not claim minute-by-minute accuracy.
Is microsoft/SkillOpt open source?
Yes — microsoft/SkillOpt ships under the MIT license, which makes its source code freely readable (and, depending on license terms, forkable and reusable). Source: github.com/microsoft/SkillOpt.
What else is in the AI Tools space?
microsoft/SkillOpt is tracked by TopGit under the AI Tools category, alongside 2 GitHub-tagged topics. Trending and Topics pages list peer repositories of comparable stars and language.
What topics is microsoft/SkillOpt associated with?
GitHub's repository topics for microsoft/SkillOpt: "agent-skills", "self-evolving-agents". TopGit's editorial category is AI Tools.
Where can I see microsoft/SkillOpt in action?
The project maintains a homepage at https://aka.ms/skillopt. The README tab on this page also usually contains screenshots and a quickstart.
Where do I read more about microsoft/SkillOpt?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/microsoft/SkillOpt is the definitive source.
Read full README in the tab above.
Want a second opinion on SkillOpt?
Ask an AI that can read this page — one click and you get its take on SkillOpt.