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

2026-02-08

AI Summary

This study addresses the lack of systematic understanding regarding the types of skills employed by large language model agents, user adoption patterns, and associated risks. It presents the first quantitative analysis of the agent skill ecosystem, examining 40,285 publicly available Claude skills through data mining, statistical analysis, and content categorization to systematically investigate their trigger conditions, logical structures, tool interactions, and length distributions. The findings reveal that skill publication occurs in bursts closely aligned with community trends and is heavily concentrated in software engineering; however, user adoption predominantly favors information retrieval and content generation tasks. The research further uncovers significant mismatches between supply and demand, substantial intent redundancy, and notable security risks, offering empirical insights and risk warnings to inform the responsible development of agent infrastructure.

Technology Category

• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• agent skills
• large language models
• skill adoption
• safety risks
• marketplace analysis

Innovation

• agent skills
• large language models
• data-driven analysis
• skill ecosystem
• safety risks