SkillOpt 解决了智能体技能无法像深度学习权重那样可靠优化的问题，做智能体开发或技能自动生成的团队可以直接用这套方法替代手工调参，效果显著且部署零开销。
SkillOpt 提出了一种新方法，将智能体技能视为冻结模型的外部状态，通过独立的优化器模型对技能文档进行有界增删改编辑，并仅在严格提升验证集分数时接受修改。该方法引入了文本学习率预算、拒绝编辑缓冲区和逐轮慢/元更新机制，使技能训练稳定且部署时零额外模型调用。在 6 个基准、7 个目标模型和 3 种执行框架（直接对话、Codex、Claude Code）的 52 个测试单元中，SkillOpt 全部取得最佳或并列最佳，相比无技能基线在 GPT-5.5 上平均提升 19.1-24.8 个百分点。迁移实验表明，优化后的技能在不同模型规模、执行环境和相近数学基准间仍保持价值。
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization.