Tooluniverse Disease Research

This generates comprehensive disease research reports by querying 10 different databases and assembling everything into a structured markdown file. It hits OpenTargets for genetics and drugs, pulls phenotypes from HPO, checks ClinVar for variants, queries clinical trials, and maps pathways through Reactome. The workflow is report-first: it creates the file upfront and progressively fills sections as it researches, with mandatory source citations for every data point. What stands out is the evidence grading system and the explicit instruction to look up facts rather than rely on training data, which matters for medical information that changes. Produces tables with genes, variants, drugs, trials, and pathways. Best for rare diseases or when you need a full intelligence brief on a condition.

skills.sh installs: 439
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

ToolUniverse Disease Research

Generate a comprehensive disease research report with full source citations. The report is created as a markdown file and progressively updated during research.

IMPORTANT: Always use English disease names and search terms in tool calls. Respond in the user's language.

LOOK UP, DON'T GUESS

When asked about a disease, query Orphanet/OMIM/DisGeNET FIRST. Don't rely on memory for prevalence, genetics, or treatment — these change over time. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.