MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills
On the map: LLM agents and tool use → Agent skill learning and evolution
Abstract (arXiv)
As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development and distribution. However, the academic community lacks a structured framework for systematically analyzing and evaluating skills. Drawing on information gain and behavioral constraint, we propose the four-dimensional MCRI Framework and operationalize it as MCRI-Eval, a large language model-based evaluation method. We evaluate MCRI-Eval using 63,812 public skills from the OpenClaw skill Hub, with 58,275 skill-conditioned model executions across BigCodeBench, BFCL-Fundamental, and Mind2Web. MCRI-Eval scores are positively associated with community popularity signals and achieve the highest downstream ranking agreement among the evaluated methods. MCRI-Eval also improves top-1 skill selection across all three benchmarks: compared with the strongest baseline on each benchmark, the skills selected by MCRI-Eval advance by 17.7, 22.8, and 19.6 percentile points in downstream performance rank on BigCodeBench, BFCL-Fundamental, and Mind2Web, respectively. These results indicate that MCRI-Eval provides a useful pre-execution signal for prioritizing promising skills before costly execution-based evaluation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use. Builds on 12 of its 30 references that are in the map. First posted on arXiv 1 Oct 2026.
Builds on
12 of 30 references.
Closest ancestors · 4
Same direction, newest first
- 2026A Framework for Evaluating Agentic Skills at Scale16 Jun
- 2026How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings6 Apr
- 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills26 Mar
- 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks13 Feb
Other references · 8
- 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
- 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
- 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
- 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 218
- 2025Survey on Evaluation of LLM-based Agentscited by 190
- 2025Evaluation and Benchmarking of LLM Agents: A Surveycited by 145
- 2026SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skillscited by 18
- 2026SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skillscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment
- 2026SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
- 2026Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
- 2026Skill Coverage: A Test Adequacy Metric for Agent Skills
- 2026OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
- 2026SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
- 2026OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
- 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward