SkillEval: Decomposing Agent Skill Quality into Interpretable Signals
cs.AI
Submitted: 2026-08-07
Updated: 2026-10-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
- SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
- From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
- From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
- SkillNet: Create, Evaluate, and Connect AI Skills
- Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
- A Framework for Evaluating Agentic Skills at Scale
- Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
- OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
- SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
- SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
- SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems