Metraipolis › archive › dc_2d167b4cd480
SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale — arXiv:2609.38822
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38822
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:39:39.704Z
- SHA-256 of the archived text
f8aeb27488d8cc2aebc9d84f9582fcb7053348c4d38f9432ac045e3045b574e1- Stable URL of this page
https://metraipolis.com/documento/dc_2d167b4cd480
How to cite
SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale — arXiv:2609.38822 — arXiv (en), https://arxiv.org/abs/2609.38822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d167b4cd480 (Metraipolis archive dc_2d167b4cd480, sha256 f8aeb27488d8cc2aebc9d84f9582fcb7053348c4d38f9432ac045e3045b574e1)
BibTeX
@misc{dc2d167b4cd480,
title = {SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale — arXiv:2609.38822},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38822},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d167b4cd480; sha256 f8aeb27488d8cc2aebc9d84f9582fcb7053348c4d38f9432ac045e3045b574e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into this http URL directories, and open-source aggregations have grown past 230,000 skills, making selection rather than authoring the bottleneck. The standing answer in the literature outsources selection to the agent itself: an LLM-mediated retrieval loop that rewrites queries and refines candidates inside the agent's decision loop, paying LLM tokens on every task. We present SkillSeek, an open-source two-stage skill retriever built from the standard IR recipe (a BGE-base bi-encoder feeding a small cross-encoder, exposed over MCP). Across a $4 \times 11$ grid of pool, backbone, and method on the 89-task SkillsBench benchmark, SkillSeek reaches observed parity with the LLM-mediated loop of Liu et al. at essentially no extra cost: plain bm25 alone records a pass rate at or above their refined loop on three of four settings, and a small cross-encoder covers the remaining difference on the fourth. A first-stage recall ceiling explains the pattern, and total per-trial spend drops from USD 51.30 to USD 27.54 (within fifty cents of the no-skill baseline). Under the SkillsBench tasks and OpenHands harness we tested, this positions the standard IR recipe as a strong default for agent-skill retrieval, with LLM-mediated alternatives a natural fit for cases where deterministic methods fall short. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.38822 — 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 2026-10-07T12:12:18.648Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).