GitSkills：GitHub上的智能体技能数据集
GitSkills: A Dataset of Agent Skills on GitHub
浏览论文内容
中文总结 AI 辅助
本文提出GitSkills数据集，包含从28.22万个公开GitHub代码库收集的379.7117万个智能体技能相关文件，为智能体技能的多维度研究提供了数据支撑。
中文摘要 AI 辅助
智能体技能是一个包含带有语言模型智能体指令的this http URL文件的文件夹，可选择性附带脚本和参考文件。当智能体判断任务与技能描述匹配时，会加载该技能。Anthropic于2025年10月推出该格式作为开放规范。九个月后，我们在公开GitHub代码库中发现了数百万个技能文件。技能与软件工程（SE）研究社区通常挖掘的工件不同：它们主要用自然语言编写，模型在运行时以概率方式选择它们，且没有编译器或类型检查器验证该选择；它们也没有中央注册中心或包管理器，因此通过在代码库之间复制文件夹来传播。因此，开发者如何编写、复用和维护技能是一个实证问题，且现有数据集未记录这一总体情况。我们提出GitSkills，这是一个2026年7月从282200个公开代码库中收集的包含3797117个this http URL文件的数据集。该数据集保留了每个文件的出现情况及其代码库、路径和内容哈希值，将相同文件归为1877981种不同内容，并为每组中的一个代表性文件补充了完整文本、解析后的前置 matter、文件夹内容、代码库元数据，以及部分文件的提交历史。一个独立的SQLite文件支持对智能体技能的采用、复用、结构、作者身份、维护和安全性的研究。
英文摘要
An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent loads the skill when it judges that a task matches the skill description. Anthropic introduced the format in October 2025 as an open specification. Nine months later, public GitHub repositories hold millions of skill files. Skills are unlike the artifacts that software engineering researchers usually mine: they are written mainly in natural language, a model selects them probabilistically at run time, and no compiler or type checker verifies the selection. Skills also have no central registry or package manager; developers reuse them by copying folders between repositories. How developers write, reuse, and maintain skills is therefore an empirical question, and no existing dataset records this population. We present GitSkills, a dataset of 3,797,117 SKILL.md files collected from 282,200 public repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. We group identical files into 1,877,981 distinct contents and enrich one representative per group with the full text, parsed front matter, folder contents, repository metadata, and, for a subset, the commit history of the file. A single self-contained SQLite file supports research on the adoption, reuse, structure, authorship, maintenance, and security of agent skills.
发表机构
- University College London（伦敦大学学院）
- University of Cagliari（卡利亚里大学）
机构由 AI 辅助整理，请以论文原文为准。
