Metraipolis › archive › dc_2bc61eb29dcb

GitSkills: A Dataset of Agent Skills on GitHub — arXiv:2608.10906

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.10906
License (as archived): CC0-1.0
Archived: 2026-10-19T06:09:32.278Z
SHA-256 of the archived text: 398abde6e237097a6d4d09c474876f86593ca2d2d4eb662acd8037e8fc621318
Stable URL of this page: https://metraipolis.com/documento/dc_2bc61eb29dcb

How to cite

GitSkills: A Dataset of Agent Skills on GitHub — arXiv:2608.10906 — arXiv (en), https://arxiv.org/abs/2608.10906 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bc61eb29dcb (Metraipolis archive dc_2bc61eb29dcb, sha256 398abde6e237097a6d4d09c474876f86593ca2d2d4eb662acd8037e8fc621318)

BibTeX

@misc{dc2bc61eb29dcb,
  title = {GitSkills: A Dataset of Agent Skills on GitHub — arXiv:2608.10906},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10906},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bc61eb29dcb; sha256 398abde6e237097a6d4d09c474876f86593ca2d2d4eb662acd8037e8fc621318},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10906. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An agent skill is a folder containing a this http URL 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 this http URL 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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.10906 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:57:28.413Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).