AI/智能体/模型工具 · Python
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 bestskill.md artifacts.
项目解读
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 bestskill.md artifacts. 主题标签包括 agent-skills、self-evolving-agents。 README 重点章节包括：SkillOpt: Executive Strategy for Self-Evolving Agent Skills、News 🔥🔥🔥、Overview、🎬 Demo Video、Extensibility & WebUI。
README / GitHub 亮点
- GitHub 描述：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 bestskill.md artifacts.
- 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, the full configuration reference, and framework internals, see the Documentation & Reproduction Guide (rendered on GitHub Pages).
- 2026-06-03 🎉 gbrain, gbrain-evals, and darwin-skill have all integrated SkillOpt.
适用场景
适合评估 AI 应用、智能体工作流、模型工具链、RAG/提示词工程或 AI 辅助开发场景。
采用前核查
采用前仍需核查许可证、维护节奏、issue 质量、release 记录和生产适配成本。
README 摘要
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, the full configuration reference, and framework internals, see the Documentation & Reproduction Guide (rendered on GitHub Pages). 2026-06-15 😴 SkillOpt-Sleep (preview) — a nightly offline self-evolution companion for local coding agents (Claude Code / Codex / Copilot): review past sessions, r…
