谁在维护Agent技能？人类主导与AI辅助维护的纵向研究
原标题：Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance
AI 摘要
本研究对五个公开AI技能仓库的873次提交、143个技能文件和254次实质性编辑进行了纵向分析，发现所有编辑均由具名人类账户完成，其中62%带有AI合著者标记，表明技能维护目前是“人类主导、AI辅助”的循环，而非自主流程。研究还发现多数编辑为内容增补和修正，但规则相似性编码因可靠性不足而失败。作者发布了语料库、编码手册和重放协议，以支持自动化技能维护系统的评估。
正文节选
Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance Abstract Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usually portable Markdown files such as SKILL.md) describe when and how to apply a capability and must be corrected, expanded, and consolidated as tools and usage patterns shift over deployment. Recent work seeks to automate skill curation, but it