智能体技能：基于数据驱动的Claude技能分析在扩展大语言模型功能中的应用

摘要

智能体技能通过可复用的类程序模块扩展了大语言模型（LLM）智能体的能力，这些模块定义了触发条件、程序逻辑及工具交互。随着此类技能在公共市场的激增，其类型分布、用户采用模式及潜在风险尚不明确。为探究这些问题，我们对某主流市场的40,285个公开技能进行了大规模数据驱动分析。研究发现：技能发布呈现与社区关注度变化同步的短期爆发趋势；技能内容高度集中于软件开发工作流，而信息检索与内容创作类技能占据实际采用的重要份额。除内容趋势外，我们发现了显著的类别供需失衡现象，并证明尽管技能长度呈重尾分布，大多数仍处于典型提示预算范围内。最后，我们观察到生态系统存在高度同质化，意图级冗余普遍存在，同时识别出不容忽视的安全风险——包括支持状态变更或系统级操作的技能。总体而言，本研究为智能体技能这一新兴基础设施层提供了量化图谱，为未来技能复用、标准化及安全感知设计的研究奠定了基础。

English

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what types are available, how users adopt them, and what risks they pose. To answer these questions, we conduct a large-scale, data-driven analysis of 40,285 publicly listed skills from a major marketplace. Our results show that skill publication tends to occur in short bursts that track shifts in community attention. We also find that skill content is highly concentrated in software engineering workflows, while information retrieval and content creation account for a substantial share of adoption. Beyond content trends, we uncover a pronounced supply-demand imbalance across categories, and we show that most skills remain within typical prompt budgets despite a heavy-tailed length distribution. Finally, we observe strong ecosystem homogeneity, with widespread intent-level redundancy, and we identify non-trivial safety risks, including skills that enable state-changing or system-level actions. Overall, our findings provide a quantitative snapshot of agent skills as an emerging infrastructure layer for agents and inform future work on skill reuse, standardization, and safety-aware design.

智能体技能：基于数据驱动的Claude技能分析在扩展大语言模型功能中的应用

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

摘要

Support