SkillCorpus：整合与评估面向现实世界大语言模型智能体的开放技能生态系统
SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
浏览论文内容
中文总结 AI 辅助
研究针对大语言模型智能体技能文件碎片化等问题，提出SkillCorpus框架，通过多阶段管道过滤技能并与检索选择堆栈配对，经多基准端到端评估，整合该框架能带来一致收益，明确了其对实际智能体任务的作用边界。
中文摘要 AI 辅助
智能体技能作为一种扩展智能体能力的流行机制，是为大语言模型智能体打包可复用过程性知识的文件。公共存储库中此类文件数量庞大且不断增加，但存在碎片化、冗余和质量参差不齐的问题，其实际价值不明。本文提出SkillCorpus框架，它能大规模聚合、整理、匹配和评估开放技能生态系统。通过多阶段管道过滤约82.1万个爬取技能，形成由16类分类法和三个质量方面（实用性、鲁棒性、安全性）组织的96401个技能，并与微调的检索和选择堆栈配对以匹配任务相关技能。通过三个基准进行端到端评估，整合SkillCorpus在所有三个基准上都带来了一致的收益，最大提升在SkillsBench上（提高7.5个百分点）。还进行了操作分析，追踪收益到覆盖边界和工具边界。SkillCorpus首次全面说明了经过整理、检索服务的社区语料库何时以及何处能改善实际智能体任务。数据集、模型和代码将在接受后发布。
英文摘要
Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code are available at https://github.com/EverMind-AI/SkillCorpus.
