← Back to Skills
Society & SafetyTechnologyPlatinum

Helps you spot hallucinations, red flags, and dangerous reassurance in AI-generated health information before you act on it.

AI Health Literacy Guard

Evaluate AI health responses critically

intermediatev5.0

Best for

  • Evaluate AI-generated health responses for red flags and hallucinations
  • Learn safe query patterns for health-related AI questions
  • Understand when AI health advice is dangerous vs. informational
  • Identify fabricated citations and invented medical guidelines

What you'll get

  • Risk assessment report for a ChatGPT diabetes response with 3 red flags identified
  • Safe query template for medication interaction questions with cross-reference checklist
  • Analysis of AI-generated mental health advice highlighting dangerous reassurance patterns
  • Emergency escalation alert when AI under-triaged chest pain symptoms
Expects

An AI-generated health response or a health-related question the user wants to ask AI

Returns

Risk assessment with red flags, accuracy analysis, recommended action, and safer query strategy

What's inside

You are a Health Literacy Guard. You help people evaluate AI-generated health information for risks and decide when to seek professional care, never providing medical advice yourself. - Flag the benchmark-bedside gap: LLMs score 90%+ on medical exams but under-triage 51.6% of emergencies, explaining...

Covers

What You Do DifferentlyMethodologyWatch For
Not designed for ↓
  • ×Providing medical diagnoses or treatment recommendations
  • ×Replacing professional medical consultation
  • ×Evaluating non-AI health information sources
  • ×Serving as a medical reference database

SupaScore

89.6
Research Quality (15%)
9.2
Prompt Engineering (25%)
8.8
Practical Utility (15%)
9
Completeness (10%)
8.5
User Satisfaction (20%)
9
Decision Usefulness (15%)
9.2

Evidence Policy

Standard: no explicit evidence policy.

ai health safetymedical ai literacyhealth misinformationai hallucination detectionpatient safety

Research Foundation: 8 sources (6 paper, 1 official docs, 1 industry frameworks)

This skill was developed through independent research and synthesis. SupaSkills is not affiliated with or endorsed by any cited author or organisation.

Version History

v5.03/25/2026

v5.5 final distill

v1.0.13/15/2026

Works well with

© 2026 Kill The Dragon GmbH. This skill and its system prompt are protected by copyright. Unauthorised redistribution is prohibited. Terms of Service · Legal Notice