{"paper":{"title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Agent skills defined as reusable procedures are key to scalable and maintainable LLM agents.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Wang Shu, Wenchuan Du, Xuemin Lin, Yaodong Su, Yingli Zhou, Yixiang Fang","submitted_at":"2026-05-08T07:10:26Z","abstract_excerpt":"Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code exemplify a broader shift from passive response generation to action-oriented task execution. Yet as agents move toward open-ended, real-world deployment, relying on from-scratch reasoning and low-level tool calls for every task become increasingly inefficient, error-prone, and hard to maintain. This survey examines this challenge through the lens of \\emph{agent"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Skills are therefore central to the scalability, robustness, and maintainability of modern agent systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed definition of agent skills as reusable procedural artifacts and the four-stage lifecycle accurately capture the key challenges and organize the relevant literature without significant omissions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Agent skills defined as reusable procedures are key to scalable and maintainable LLM agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7a42ee802e31c39dc2ae318a4535641db2691badeeb6eb3b10e5de36521001dd"},"source":{"id":"2605.07358","kind":"arxiv","version":2},"verdict":{"id":"b8a9d1f2-ea8c-4f3b-9800-c60091ee25e1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:44:15.333735Z","strongest_claim":"Skills are therefore central to the scalability, robustness, and maintainability of modern agent systems.","one_line_summary":"The paper surveys agent skills for LLM agents, organizing the literature into a four-stage lifecycle of representation, acquisition, retrieval, and evolution while highlighting their role in system scalability.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed definition of agent skills as reusable procedural artifacts and the four-stage lifecycle accurately capture the key challenges and organize the relevant literature without significant omissions.","pith_extraction_headline":"Agent skills defined as reusable procedures are key to scalable and maintainable LLM agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07358/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.505738Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:53:09.297595Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"19a094f5c0802ebf7d722d95b6131fccd2f834e5c9d4a846081928e8ee5017d9"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}