An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
For researchers and practitioners building healthcare AI agents, this study identifies gaps in current skill repositories and risk frameworks.
The paper presents the first empirical analysis of 557 healthcare agent skills from 58,159 public skills, finding that they emphasize workflow automation and monitoring over diagnostic tasks, with uneven coverage of the healthcare lifecycle and clinical risk not captured by technical risk.
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.