做智能体开发的团队终于有了靠谱的技能优化方案——SkillOpt 解决了手工调技能越调越差的痛点，而且最终产物是一个可读文件，部署零成本。做 prompt 工程或 Agent 框架的开发者值得细读。
微软提出 SkillOpt 方法，将智能体技能文档视为可训练的外部程序，而非手工编写或一次性生成。该方法通过一个更强的优化器模型，在智能体执行任务后分析成功与失败案例，对技能文档进行小幅度编辑，并仅在通过验证集测试时采纳修改。在 6 个基准、7 个目标模型和 3 种智能体设置（包括直接对话、Codex 和 Claude Code）的测试中，SkillOpt 在全部 52 个案例中表现最佳或持平，在 GPT-5.5 上直接对话准确率平均提升 23.5 个百分点。最终产出是一个可读、可移植、低成本复用的技能文件，无需重新训练模型即可提升智能体跨任务表现。
The problem is that agent skills are usually hand-…
The problem is that agent skills are usually hand-written, made once by an LLM, or revised in loose ways that can easily make them worse.
SkillOpt from Microsoft, argues that agent skills should be trained like small external programs, it teaches AI agents better task habits by editing a reusable skill document, not the model itself.
The paper’s core idea is to treat the skill document like the thing being trained, while the main AI model stays frozen and unchanged.
SkillOpt watches the agent try tasks, studies what worked and failed, then asks a stronger optimizer model to suggest small edits to the skill.
It only accepts an edit when the new skill improves on a held-out check set, so the skill does not drift just because an edit sounds good.
The authors tested this across 6 benchmarks, 7 target models, and 3 agent settings, including direct chat, Codex, and Claude Code.
SkillOpt was best or tied on all 52 tested cases, and on GPT-5.5 it raised average accuracy by 23.5 points in direct chat.
The final result is a small readable skill file that can improve agents across tasks and settings without retraining the model.
The best part is that the optimizer is used during training, but deployment only needs the final skill file.
That makes the artifact inspectable, portable, and cheap to reuse, which is exactly what most prompt-engineering systems lack.
----
Link – arxiv. org/abs/2605.23904
Title: "SkillOpt: Executive Strategy for Self-Evolving Agent Skills"