Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
2026-03-02 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed AgentSkillOS, a system to better organize and use many different AI skills quickly and effectively. They created a two-step process: first, organizing skills into a tree to make them easier to find, and second, building pipelines to connect and run multiple skills together. They tested this on 30 diverse tasks like data work and design, showing their approach works well even with huge numbers of skills. Their experiments suggest that organizing and combining skills thoughtfully helps AI perform tasks better than using skills one by one.
AgentSkillOSskill orchestrationcapability treeDAG pipelineskill retrievalLLM evaluationBradley-Terry modelskill ecosystemartifact-rich tasksAI skill management
Authors
Hao Li, Chunjiang Mu, Jianhao Chen, Siyue Ren, Zhiyao Cui, Yiqun Zhang, Lei Bai, Shuyue Hu
Abstract
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill selection, orchestration, and ecosystem-level management. AgentSkillOS comprises two stages: (i) Manage Skills, which organizes skills into a capability tree via node-level recursive categorization for efficient discovery; and (ii) Solve Tasks, which retrieves, orchestrates, and executes multiple skills through DAG-based pipelines. To evaluate the agent's ability to invoke skills, we construct a benchmark of 30 artifact-rich tasks across five categories: data computation, document creation, motion video, visual design, and web interaction. We assess the quality of task outputs using LLM-based pairwise evaluation, and the results are aggregated via a Bradley-Terry model to produce unified quality scores. Experiments across three skill ecosystem scales (200 to 200K skills) show that tree-based retrieval effectively approximates oracle skill selection, and that DAG-based orchestration substantially outperforms native flat invocation even when given the identical skill set.Our findings confirm that structured composition is the key to unlocking skill potential. Our GitHub repository is available at:https://github.com/ynulihao/AgentSkillOS.