Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale

TL;DR

This paper introduces AgentSkillOS, a framework for managing and orchestrating agent skills at ecosystem scale, demonstrating that structured skill organization and DAG-based orchestration significantly improve task performance.

Contribution

The paper presents the first principled framework for skill selection and orchestration at ecosystem scale, including a capability tree organization and DAG-based execution, validated by a comprehensive benchmark.

Findings

Tree-based skill retrieval approximates oracle selection.

DAG-based skill orchestration outperforms flat invocation.

Structured composition enhances skill utilization and task quality.

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.