# GitSkills：GitHub 上 380 万份智能体技能数据集

- 来源：DAIR.AI (@dair_ai)
- 发布时间：2026-08-18 05:00
- AIHOT 分数：51
- AIHOT 链接：https://aihot.virxact.com/items/cmsyqyit40128roidowreaw5v
- 原文链接：https://x.com/dair_ai/status/2089457322833936598

## AI 摘要

Anthropic 将 SKILL.md 格式发布为开放规范九个月后，GitHub 上已有约 380 万份 SKILL.md 文件，分布于 28.22 万个公共仓库。研究将其全部挖掘为数据集 GitSkills，按内容去重后得到 187.8 万条不同技能，并以单个 SQLite 文件发布，包含 front matter、文件夹内容和提交历史。

## 正文

How many agent skills are actually out there?

There are ~3.8M SKILL.md files across 282,200 public GitHub repositories, nine months after Anthropic published the format as an open spec.

This research mined all of them into a dataset.

Skills resist the usual software mining. They are written in natural language, an agent picks them probabilistically at run time, and no compiler or type checker verifies the choice. There is no registry and no package manager, so they spread by copying folders between repos.

GitSkills groups them into 1,877,981 distinct contents and ships as a single SQLite file with front matter, folder contents, and commit history.

Paper: https://arxiv.org/abs/2608.10906

Track more trending AI papers in our academy: https://academy.dair.ai/