Saved in:
Bibliographic Details
Main Authors: Xu, Gelei, Tang, Ningzhi, Li, Xueyang, Li, Toby Jia-Jun, Zheng, Zhi, Jin, Wei, Shi, Yiyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.02709
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915978215948288
author Xu, Gelei
Tang, Ningzhi
Li, Xueyang
Li, Toby Jia-Jun
Zheng, Zhi
Jin, Wei
Shi, Yiyu
author_facet Xu, Gelei
Tang, Ningzhi
Li, Xueyang
Li, Toby Jia-Jun
Zheng, Zhi
Jin, Wei
Shi, Yiyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02709
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
Xu, Gelei
Tang, Ningzhi
Li, Xueyang
Li, Toby Jia-Jun
Zheng, Zhi
Jin, Wei
Shi, Yiyu
Artificial Intelligence
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.
title An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
topic Artificial Intelligence
url https://arxiv.org/abs/2605.02709