Tooluniverse Adverse Event Detection

This is a serious pharmacovigilance tool that runs FDA FAERS disproportionality analysis to detect adverse drug event signals. It calculates PRR, ROR, and information component statistics with confidence intervals, then produces a quantitative safety signal score from 0 to 100. The workflow pulls FAERS reports, mines FDA labels for boxed warnings, cross-references OpenTargets and DrugBank for mechanism-based context, and applies the Naranjo causality algorithm. It's built for post-market surveillance and regulatory work where you need statistical rigor, not just anecdotal safety info. The skill emphasizes computation over description and uses multi-source triangulation to separate drug-specific signals from class-wide effects or confounders.

skills.sh installs: 371
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-adverse-event-detection --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.

Adverse Drug Event Signal Detection & Analysis

Automated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly