GitSkills: A Dataset of Agent Skills on GitHub

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Giuseppe Destefanis, Daniel Graziotin, Matteo Vaccargiu, Marco Ortu
• Venue: arXiv: cs.SE
• Published: 2026-08-11
• Collected: 2026-08-12
• URL: http://arxiv.org/abs/2608.10906v1
• PDF: https://arxiv.org/pdf/2608.10906v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

Researchers present GitSkills, a dataset containing over 3 million skill files for language-model agents found in public GitHub repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash, and provides additional information such as commit history for a subset.

What the Document Says

• Anthropic introduced an open specification for agent skills in October 2025.
• Skill files are written mainly in natural language and are selected probabilistically at run time by a model.
• There is no central registry or package manager for skills, they spread by copying folders between repositories.
• GitSkills is a dataset of 3,797,117 SKILL.md files collected from 282,200 public repositories in July 2026.
• The dataset groups identical files into 1,877,981 distinct contents and provides additional information for one representative per group.
• The data includes repository metadata, commit history of the file for a subset, and is stored in an SQLite file.

Key Concepts Mentioned

• agent skills
• SKILL.md files
• GitHub repositories
• natural language
• open specification
• Anthropic

Claims Made by the Document

• There are skill files in the millions on GitHub.
• Skills are not verified by a compiler or type checker.
• There is no central registry or package manager for skills.

Evidence Used

• The dataset contains 3,797,117 SKILL.md files.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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, we find that skill files in the millions sit in public GitHub repositories. Skills are unlike the artifacts the SE research community usually mines: they are written mainly in natural language, a model selects them probabilistically at run time, and no compiler or type checker verifies the selection. They also have no central registry or package manager, so they spread 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. It groups identical files into 1,877,981 distinct contents and enriches 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.