Hcls Agent Skills
Curated collection of 39 agent skills for healthcare and life sciences workflows, installable via the Agent Skills standard.
awslabs · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add awslabs/hcls-agent-skills技能说明
Agent Skills for Healthcare & Life Sciences
A curated collection of agent skills for healthcare and life sciences (HCLS) workflows, following the Agent Skills open standard. These 39 domain skills make any AI agent measurably better at HCLS questions. In a 410-prompt pairwise evaluation (380 single-skill + 30 cross-skill) judged by Claude Opus 4.7, skills win 70–86% of head-to-head comparisons depending on harness, with up to 85% critical thinking and up to 87% scientific accuracy win rates. Skills work on 20+ platforms including Kiro, Amazon Quick, Amazon Bedrock AgentCore, AWS Strands SDK, Claude Code, OpenAI Codex, CrewAI, LangChain, and more.
Skills fall into two categories: reasoning skills encode methodology, decision frameworks, and domain expertise to guide the agent's thinking (e.g., ACMG variant classification, target trial emulation, HEDIS measure specification); pipeline skills encode tool-specific commands, code patterns, and parameter tables that produce runnable artifacts (e.g., GATK4 variant calling, RDKit cheminformatics, HL7v2 parsing). Together they make any AI agent a competent collaborator across genomics, single-cell analysis, medical imaging, protein structure, translational research, pharmacoepidemiology, clinical data, drug discovery, proteomics, clinical data review, [multi-omi