SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focuse...
| Authors | Xiangyi Li, Yimin Liu, Wenbo Chen et al. |
|---|---|
| Primary category | cs.AI |
| Published | 13 February 2026 |
| Last updated at source | 14 June 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- benchflow/skillsbenchDataset · cited by
Models and datasets referencing this paper
- benchflow/skillsbenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.