Drug Interaction Checker#

Check for interactions between multiple medications, including severity classification and mechanism explanations.

Features#

• Multi-drug analysis: Check interactions between 2+ medications simultaneously
• Severity classification: Critical / Major / Moderate / Minor / Unknown
• Mechanism explanation: Pharmacological basis for each interaction
• Clinical guidance: Recommendations for management

Severity Levels#

LevelDescriptionAction RequiredCriticalLife-threatening interactionAbsolute contraindicationMajorSignificant risk, may need medical interventionAvoid combination or monitor closelyModerateModerate risk, may require dose adjustmentMonitor for adverse effectsMinorMild interaction, unlikely to cause issuesBe aware, usually acceptableUnknownInsufficient dataProceed with caution

Usage#

Python Script#

bash

python scripts/main.py --drugs "Warfarin" "Aspirin" "Ibuprofen"

As a Module#

python

from scripts.main import check_interactions

result = check_interactions(["Metformin", "Simvastatin", "Amlodipine"])

Parameters#

ParameterTypeDefaultRequiredDescription--drugslist-YesList of drug names (generic or brand names accepted)--formatstringtextNoOutput format (text, json, markdown)--include-mechanismflagtrueNoInclude pharmacological mechanism--include-managementflagtrueNoInclude clinical recommendations--output, -ostring-NoOutput file path

Output Format#

json

{
  "drugs_checked": ["Drug A", "Drug B"],
  "interactions": [
    {
      "drug_pair": ["Drug A", "Drug B"],
      "severity": "Major",
      "mechanism": "Pharmacodynamic synergism...",
      "effect": "Increased bleeding risk",
      "recommendation": "Avoid combination or monitor INR closely"
    }
  ],
  "summary": {
    "critical": 0,
    "major": 1,
    "moderate": 0,
    "minor": 0
  }
}

Data Sources#

This skill uses a curated drug interaction database stored in references/interactions_db.json. The database includes:

• FDA-approved drug interaction data
• Known metabolic pathways (CYP450 enzymes)
• Pharmacodynamic interactions
• Common supplement interactions

Limitations#

• Database may not include all possible drug combinations
• Always consult healthcare professionals for medical decisions
• Does not account for patient-specific factors (age, renal function, etc.)
• Not a substitute for professional medical advice

Technical Difficulty#

High - Requires extensive pharmacological knowledge database, accurate severity classification, and clear mechanism explanations.

References#

See references/ directory for:

• interactions_db.json - Drug interaction database
• severity_criteria.md - Classification criteria
• cyp450_substrates.json - Metabolic pathway data

Risk Assessment#

Risk IndicatorAssessmentLevelCode ExecutionPython/R scripts executed locallyMediumNetwork AccessNo external API callsLowFile System AccessRead input files, write output filesMediumInstruction TamperingStandard prompt guidelinesLowData ExposureOutput files saved to workspaceLow

Security Checklist#

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Output does not expose sensitive information
• Prompt injection protections in place
• Input file paths validated (no ../ traversal)
• Output directory restricted to workspace
• Script execution in sandboxed environment
• Error messages sanitized (no stack traces exposed)
• Dependencies audited

Prerequisites#

bash

# Python dependencies
pip install -r requirements.txt

Evaluation Criteria#

Success Metrics#

• Successfully executes main functionality
• Output meets quality standards
• Handles edge cases gracefully
• Performance is acceptable

Test Cases#

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status#

• Current Stage: Draft

• Next Review Date: 2026-03-06

• Known Issues: None

• Planned Improvements:

  • Performance optimization
  • Additional feature support