SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks (opens in new tab)

arXiv:2602.12670v1 Announce Type: new Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurati...