Tooluniverse Infectious Disease

Built for rapid infectious disease outbreak work where the agent should compute, not just describe an analysis plan. It directs Claude to use ToolUniverse data retrieval plus Python for taxonomy analysis, target identification, structure prediction, and computational drug repurposing. The emphasis on conserved essential proteins, FDA-approved compounds, NvidiaNIM structure prediction, docking, and evidence-graded candidates makes it oriented toward actionable triage. It is a specialized biomedical workflow, so it belongs in hands that can sanity-check the assumptions and outputs.

skills.sh installs: 384
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-infectious-disease --agent claude-code

Installs into .claude/skills of the current project.

Files

COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Infectious Disease Outbreak Intelligence

Rapid response system for emerging pathogens using taxonomy analysis, target identification, structure prediction, and computational drug repurposing.

KEY PRINCIPLES:

Speed is critical - Optimize for rapid actionable intelligence
Target essential proteins - Focus on conserved, essential viral/bacterial proteins
Leverage existing drugs - Prioritize FDA-approved compounds for repurposing
Structure-guided - Use NvidiaNIM for rapid structure prediction and docking
Evidence-graded - Grade repurposing candidates by evidence strength
Actionable output - Prioritized drug candidates with rationale
English-first queries - Always use English terms in tool calls; respond in user's language