SkillsBench

Warning: The leaderboard above is generated by Hugging Face eval-results and may be incomplete until evaluation_framework: benchflow is accepted and deployed. The audited SkillsBench v1.1 result archive is https://huggingface.co/datasets/benchflow/skillsbench-leaderboard, with all retained submissions normalized under

Papers using SkillsBench (15)

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills2026 · 1 citesSkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale2026AIP: A Graph Representation for Learning and Governing Agent Skills2026What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents2026SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement2026SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior2026SkillsInjector: Dynamic Skill Context Construction for LLM Agents2026SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents2026SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering2026Coevoskills: Self-evolving Agent Skills Via Co-evolutionary Verification2026SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents2026SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces2026ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation2026