SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents

תקציר מקורי באנגליתarXiv:2607.15557v2 Announce Type: replace Abstract: Agent skills, $\texttt{SKILL.md}$ files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source $\texttt{SKILL.md}$ ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present $\textbf{SkillCorpus}$, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by