tooluniverse-drug-drug-interaction

Analyze drug-drug interactions and generate evidence-graded clinical risk reports.

1.7k|254|Updated Mar 3, 2025
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-drug-drug-interaction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tooluniverse-drug-drug-interaction
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/plugins/tooluniverse/skills/tooluniverse-drug-drug-interaction
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-drug-drug-interaction

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tooluniverse, and includes scripts (resource) components.

What problem does it solve?

Assessing whether two or more medications can be safely combined requires checking CYP450 and UGT metabolism, transporter effects, pharmacodynamic overlap, FDA labels, and literature evidence across many databases, which is slow and error-prone when done manually.

Core Features & Use Cases

  • Mechanism-based DDI analysis: Identifies perpetrator-victim relationships across CYP450, UGT glucuronidation, transporter (P-gp, OATP), and pharmacodynamic pathways, with bidirectional A→B and B→A evaluation.
  • Evidence-graded risk scoring: Produces a 0-100 risk score and severity classification (Contraindicated/Major/Moderate/Minor) backed by FDA labels, PubMed literature, and FAERS adverse event data.
  • Offline pharmacology reference: Ships a dependency-free script covering CYP/UGT roles, narrow therapeutic index drugs, and a curated database of critical interactions such as valproate + lamotrigine.
  • Use Case: A clinician asks whether simvastatin can be taken with ketoconazole; the Skill flags the combination as contraindicated via CYP3A4 inhibition, cites the FDA label, and recommends pravastatin or rosuvastatin as safer alternatives.

Quick Start

Ask the agent to analyze the drug interaction between warfarin and amoxicillin and generate a DDI risk report with management recommendations.

Frequently Asked Questions about tooluniverse-drug-drug-interaction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check drug interactions between two medications?

Provide the two drug names and the Skill resolves identifiers via RxNorm and DrugBank, analyzes CYP, UGT, and transporter mechanisms in both directions, then generates a markdown risk report with severity classification and management recommendations.

What databases are used for drug interaction analysis?

The analysis queries DrugBank for documented interactions, DailyMed for FDA label warnings, PubMed for clinical literature, FAERS for post-market adverse events, and RxNorm for drug identification. A local offline reference script covers CYP and UGT roles without network access.

Can this analyze polypharmacy with five or more drugs?

Yes, the Skill supports polypharmacy risk assessment by evaluating all pairwise combinations in a regimen, producing a DDI matrix, flagging moderate and major interactions, and generating a combined monitoring schedule for labs like INR, potassium, and blood pressure.

Does the drug interaction checker work offline?

The bundled pharmacology_ref.py script runs offline with no external dependencies, covering CYP substrates, inhibitors, inducers, UGT enzymes, narrow therapeutic index drugs, and a curated database of critical interactions. Full evidence gathering requires ToolUniverse database access.

Why are UGT glucuronidation interactions often missed?

Most DDI reasoning focuses on CYP450 Phase I metabolism, but Phase II glucuronidation via UGT enzymes causes dangerous interactions like valproate doubling lamotrigine levels through UGT1A4 inhibition. The Skill explicitly checks UGT substrates, inhibitors, and inducers to catch these cases.