AI 技能越攒越臃肿，这篇让它瘦身还不掉功能
自进化 AI 会不断把成功做法和修过的坑存成「技能」，但攒多了就乱：同一规则散落多处、重复动作被复制粘贴，技能包越来越重、越来越难维护。现有压缩法要么不管用——技能不是一段平铺的文字，名字、触发条件、执行流程、工具约束各有各的职责；要么得靠跑测试来验证压缩没压坏，又贵又依赖测试集。SkillZip 换了个思路：不跑测试，直接找技能里「最短的忠实结构」——重复的规则只写一次、重复的动作抽成共用流程、只把差异留成例外，同时硬性保证每个触发条件、流程边、工具要求、输出字段都还在。它还能在 AI 边学边存时实时压缩，不用重放历史。这不是你明天能上手用的工具，但它指向一个真问题：AI 的长期记忆正在变成没人想维护的屎山，而这篇给出了第一把像样的铲子。
📄 原文摘要(英文)
Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essential even when no sampled task activates them. Evaluation-guided compression can test these behaviors, but it introduces rollouts, cost, and dependence on the compression-time evaluation set. We present SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation. The intuition is explain once, reference many: state a repeated rule once at the scope where it applies, factor a repeated action sequence into a shared procedure, and keep only the differences as explicit exceptions. We formalize this intuition as a typed minimum description-length objective over a skill contract and a residual, subject to a hard coverage constraint for every extracted trigger, workflow edge, tool requirement, obligation, and output field. The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates. SkillZip has a one-shot mode with one structured extraction call and deterministic optimization, and a continual Zip-on-Write mode that integrates each self-evolution patch without replaying tasks or reparsing the full history. Through comprehensive experimental evaluations, we demonstrate the effectiveness and superiority of SkillZip in compression performance, generalizability, and cost overhead.