mims-harvard avatar

Tooluniverse Drug Drug Interaction

This analyzes drug interactions with a report-first workflow that checks local pharmacology references before hitting external databases. It covers both CYP450 and UGT enzyme interactions (the valproate-lamotrigine SJS risk gets explicit treatment), bidirectional perpetrator-victim analysis, and evidence grading for clinical claims. The local script handles common high-risk pairs like statins with azoles, warfarin with inducers, and prodrug activation failures. Use it when reviewing polypharmacy cases or when a patient develops new symptoms after starting a medication. The framework pushes you to reason mechanistically about inhibition versus induction before consulting references, which makes the output more clinically useful than a simple interaction flag.

skills.sh installs
457
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-drug-drug-interaction --agent claude-code

Installs into .claude/skills of the current project.

Files

Drug-Drug Interaction Prediction & Risk Assessment

Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations.

KEY PRINCIPLES:

  1. Report-first approach - Create DDI_risk_report.md FIRST, then populate progressively
  2. Bidirectional analysis - Always analyze A→B and B→A interactions (effects may differ)
  3. Evidence grading - Grade all DDI claims by evidence quality (★★★ FDA label, ★★☆ clinical study, ★☆☆ theoretical)
  4. Risk scoring - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence
  5. Patient safety focus - Provide actionable clinical guidance, not just theoretical interactions
  6. Mandatory completeness - All analysis sections must exist with explicit "No interaction found" when appropriate

LOCAL PHARMACOLOGY REFERENCE (USE FIRST)

Before querying any external database, consult the local reference script for instant answers on CYP/UGT roles and known critical interactions:

scripts/pharmacology_ref.py   (no external dependencies, runs offline)

Sponsors

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
Git & Pull Requests, Code Review & Quality, Productivity & Planning, Design & UI/UX
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68
1dpearson2699 avatarphotos-camera-mediadpearson2699/swift-ios-skillsImplement, review, or improve photo picking, camera capture, and media handling in iOS apps. Use when working with PhotosPicker, PHPickerViewController, camera 456skills.sh installs
2aaronontheweb avatarplaywright-ci-cachingaaronontheweb/dotnet-skillsCache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute download overhead on every build.455skills.sh installs
3ythx-101 avatarx-tweet-fetcherythx-101/x-tweet-fetcherFetch tweets, replies, timelines, search results, X Lists, and X Articles from X/Twitter without login or API keys. Single tweets: zero dependencies (FxTwitter)455skills.sh installs
4evoscientist avatarpaper-rebuttalevoscientist/evoskillsGuides writing effective rebuttals after receiving peer review feedback. Covers review diagnosis (score-driven color-coding), response strategy (champion identi453skills.sh installs
5openclaudia avatarcopy-editingopenclaudia/openclaudia-skillsLine-by-line copy editing and improvement for marketing content. Polish existing copy for clarity, conciseness, impact, and conversion. Trigger phrases: "edit m453skills.sh installs
6openclaudia avatarschema-markupopenclaudia/openclaudia-skillsGenerate Schema.org structured data (JSON-LD) for any page type. Use when the user says "schema markup", "structured data", "JSON-LD", "rich snippets", "rich re453skills.sh installs