首个实证研究揭示医疗AI技能在实际应用中的短板与治理盲区。
An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
- 基于58,159个公开技能筛选出557个医疗相关技能，系统分析其功能与部署特征。
- 多数技能聚焦患者流程自动化，缺乏诊断治疗等核心临床能力支持。
- 现有技术风险评估无法准确反映临床风险，需针对性治理框架。
医疗自动化受本地流程与组织约束影响，导致智能体能力难以直接迁移。代理技能（agent skills）作为可复用的程序封装层，正成为跨场景适配医疗智能体的新范式。本文首次对医疗代理技能进行实证研究，从ClawHub平台中筛选并标注了557个医疗相关技能，覆盖功能、部署环境、自主性与安全性等十个维度。结果发现：公开技能多聚焦患者端流程自动化与监测，而非研究中强调的诊断与治疗任务；医疗生命周期各阶段及专科临床输入覆盖不均；通用技术风险无法可靠映射临床风险。研究指出，当前基准与风险框架尚未涵盖这一关键程序层，亟需建立专门治理体系。
原文摘要 · Abstract (English)
Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained directories that package reusable procedures for AI agents, are emerging as a procedural layer for adapting healthcare agents across diverse healthcare settings. We present the first empirical analysis of healthcare agent skills, drawing on 557 healthcare-related skills filtered from 58,159 public skills on ClawHub and annotated along ten dimensions covering function, deployment context, autonomy, and safety. We find that public healthcare skills emphasize patient-facing workflow automation and monitoring rather than the diagnostic and treatment-oriented tasks foregrounded in healthcare-agent research; coverage of the healthcare lifecycle and specialized clinical inputs remains uneven; and general technical risk does not reliably capture clinical risk. These findings position healthcare skills as a procedural layer not yet addressed by current benchmarks and risk frameworks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。