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

TL;DR

This paper provides a comprehensive data-driven analysis of over 40,000 agent skills in a large marketplace, revealing trends, content focus, supply-demand imbalances, ecosystem homogeneity, and safety risks associated with skill proliferation.

Contribution

It offers the first large-scale quantitative analysis of agent skills, highlighting content trends, ecosystem characteristics, and safety concerns to inform future development and standardization.

Findings

Skills are published in short bursts aligned with community attention shifts.

Content is concentrated in software engineering, retrieval, and content creation.

Most skills stay within typical prompt budgets despite long-tail length distribution.

Abstract

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.