Metraipolis › archive › dc_4bc20b7142bd
How Agent Skills Evolve: A Large-Scale Empirical Study of Skills on GitHub — arXiv:2611.04456
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04456
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:53:39.176Z
- SHA-256 of the archived text
958fa1297ac7558f89de9525c8ee5d21f8d83941c9c61ef0954482ea70d0e0fc- Stable URL of this page
https://metraipolis.com/documento/dc_4bc20b7142bd
How to cite
How Agent Skills Evolve: A Large-Scale Empirical Study of Skills on GitHub — arXiv:2611.04456 — arXiv (en), https://arxiv.org/abs/2611.04456 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bc20b7142bd (Metraipolis archive dc_4bc20b7142bd, sha256 958fa1297ac7558f89de9525c8ee5d21f8d83941c9c61ef0954482ea70d0e0fc)
BibTeX
@misc{dc4bc20b7142bd,
title = {How Agent Skills Evolve: A Large-Scale Empirical Study of Skills on GitHub — arXiv:2611.04456},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04456},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bc20b7142bd; sha256 958fa1297ac7558f89de9525c8ee5d21f8d83941c9c61ef0954482ea70d0e0fc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04456. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model-based agents increasingly rely on external skills to reuse task-specific knowledge without retraining the model. As skills become common for extending agent capabilities, understanding creation and evolution is critical for reliable agent systems. However, existing studies mainly examine agent skills from a static perspective, leaving their evolution in real-world repositories largely unexplored. This limits our understanding of the patterns and motivations behind skill changes. To fill this gap, we present a large-scale empirical study of agent skills, capturing 84,200 skills and 750,898 commits from GitHub. We manually construct taxonomies of skill components, change patterns, and evolution motivations, and build an automated annotation pipeline to label changes at scale. Based on the taxonomy, we conduct quantitative analyses of skill composition and post-creation evolution frequency, together with qualitative assessments of modified components, change patterns, and motivations. Our findings reveal five implications: (i) reliability receives less attention in skill composition and change, motivating execution-contract skill design that incorporates verification and recovery mechanisms; (ii) evolution changes concentrate in project-coupled skills, calling for automated just-in-time skill updating mechanisms; (iii) change patterns are dominated by incremental enrichment and refinement, motivating pattern-guided skill enhancers that diagnose and improve incomplete skill components; (iv) redundancy is a practical maintenance issue, highlighting the need for context-efficient skill representation; (v) security-motivated changes show limited risk reduction, suggesting skill regression testing methods that objectively verify skill functionality and security. Beyond these insights, our dataset provides a basis for future studies on automated skill techniques. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2611.04456 — 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 2026-11-04T21:39:04.518Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).