AWS open-sources 38 healthcare agent skills and measures a 51-62% drop in response variance

AWS Machine Learning Blog·medium signalXBlueskyLinkedInCopy link

AWS published 38 agent skills spanning 11 healthcare and life sciences domains (genomics, drug discovery, claims operations, medical imaging, clinical data, healthcare operations and more) at awslabs/hcls-agent-skills under MIT-0. Across 410 domain prompts, skilled agents beat baseline with a 69.5-85.9% overall win rate, 78-85% on critical thinking (Cohen's d 0.65-1.03), 69.3-86.2% on scientific accuracy, and 51-61.9% lower variance in response scores. The skills are structured markdown with YAML frontmatter encoding the decision procedure itself, not retrieval or fine-tuning, and the paper reports they work across 20+ services without customization.