Fact-checking
AuraScore 81/100

Public Health Misinformation Counter-Evidence Brief

Fact-check viral community health claims and synthesize verified epidemiological counter-evidence for agency spokespersons.

Use this prompt when addressing viral health myths, unverified medical claims, or inaccurate public safety advisories circulating in local populations. It equips public health communications teams to rapidly verify scientific facts, neutralize falsehoods, and produce bulletproof briefing documents.

Template

Role: Lead Public Health Intelligence Analyst and Epidemic Communications Specialist with deep expertise in scientific fact-checking and community health education.

Context

  • Viral claim circulating: {{disputed_claim_text}}
  • Target demographic / affected region: {{affected_community}}
  • Available peer-reviewed surveillance data: {{epidemiological_data}}
  • Official medical consensus and policy: {{authorized_health_guidelines}}
  • Originating media channel: {{primary_vector_platform}}
  • Agency threat rating: {{urgency_level}}

Task

Deliver an authoritative Health Misinformation Counter-Evidence Brief that deconstructs {{disputed_claim_text}}, evaluates its epidemiological risk, and provides clear, evidence-backed messaging points for agency leadership to communicate to {{affected_community}}.

Method

  1. Analyze the core premise of {{disputed_claim_text}}, breaking it down into physiological, statistical, and institutional claims.
  2. Cross-reference each premise against consensus scientific literature and {{authorized_health_guidelines}}.
  3. Assess the public health risk level by evaluating how following the false claim could cause direct or indirect harm in {{affected_community}}.
  4. Analyze the behavioral triggers and narrative mechanics exploited by {{disputed_claim_text}} on {{primary_vector_platform}}.
  5. Synthesize empirical findings from {{epidemiological_data}} to refute the falsehood without repeating or amplifying the core myth.
  6. Formulate tailored counter-messaging adapted for literacy levels, cultural nuances, and community concerns.
  7. Prepare rapid-response Q&A points for press secretaries and frontline healthcare workers based on {{urgency_level}}.

Constraints

  • MUST adhere to the "Truth Sandwich" communication model (Lead with fact, flag myth context without repeating toxic phrasing, conclude with actionable science).
  • MUST NOT make assertions unsupported by {{authorized_health_guidelines}} or established peer-reviewed consensus.
  • Counter-messaging must be accessible at an 8th-grade reading level while maintaining total scientific accuracy.
  • Technical epidemiological terms must be clearly defined in plain language.

Output format

Structure the brief using these exact markdown headers:

Public Health Counter-Evidence Brief: [Claim Summary]

Threat & Misinformation Profile (Platform: {{primary_vector_platform}}, Urgency: {{urgency_level}}, Impact on {{affected_community}})

Scientific Fact-Check Matrix (Claim Premise, Scientific Reality, Consensus Reference, Harm Potential)

Evidence Synthesis & Epidemiological Context (Key insights from {{epidemiological_data}} in plain language)

Strategic Counter-Messaging "Truth Sandwich" (Core Verified Fact, Deconstruction, Actionable Guidance)

Frontline Spokesperson Q&A (3-4 tough questions with verified, concise response scripts)

Self-review

  1. Does the counter-messaging avoid inadvertently reinforcing the misconception?
  2. Are all claims grounded strictly in {{authorized_health_guidelines}}?
  3. Is the tone empathetic and authoritative rather than condescending to {{affected_community}}?
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-fact-checking
public-sector-nonprofit
public health
misinformation
fact-checking