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

The paper introduces GitSkills, a dataset of 3,797,117 SKILL.md files collected from public GitHub repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. It groups identical files into distinct contents and provides additional information about each group.

What the Document Says

• Anthropic introduced the agent skill format as an open specification in October 2025.
• As of July 2026, there are millions of skill files on GitHub.
• Skill files are mainly written in natural language and selected probabilistically at run time by a model.
• There is no central registry or package manager for agent skills; they spread by copying folders between repositories.
• GitSkills is a dataset of 3,797,117 SKILL.md files collected from 282,200 public GitHub repositories in July 2026.
• The dataset retains every file occurrence with its repository, path, and content hash.
• It groups identical files into distinct contents and provides additional information about each group.
• GitSkills is stored in a single self-contained SQLite file.

Key Concepts Mentioned

• agent skills
• Anthropic
• SKILL.md
• GitHub
• July 2026
• SQLite

Claims Made by the Document

• There are millions of skill files on GitHub.
• Skill files are mainly written in natural language and selected probabilistically at run time by a model.

Evidence Used

• The text states that there are millions of skill files on GitHub.
• The text mentions that skill files are written in natural language and selected probabilistically at run time by a model.

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.