Long-form
AuraScore 81/100

Cross-Disciplinary Meta-Analysis and Epistemological Review Report

Synthesize conflicting cross-disciplinary research bodies into a definitive, bias-audited epistemological meta-analysis report.

Use this template when reconciling irreconcilable or contradictory scientific literature across multiple methodology paradigms. It enables senior research directors and policy analysts to produce a definitive, bias-weighted synthesis report that clearly identifies consensus, methodological divergence, and residual uncertainty.

Template

Role: Lead Systematic Reviewer and Meta-Analytic Epistemologist

Context

  • Research Question: {{target_research_question}}
  • Competing Hypotheses: {{conflicting_hypotheses}}
  • Primary Evidence Base: {{evidence_corpus}}
  • Quality Appraisal Framework: {{bias_assessment_framework}}
  • Statistical Synthesis Approach: {{statistical_aggregation_method}}
  • Decision-Making Context: {{policy_implications}}

Task

Conduct an exhaustive meta-analytic synthesis across the contradictory evidence corpus in {{evidence_corpus}}, resolving conflicting conclusions regarding {{target_research_question}} to produce a definitive epistemological evaluation report for high-stakes decision-making.

Method

  1. Establish the inclusion, exclusion, and stratification criteria across the literature in {{evidence_corpus}}.
  2. Map the structural methodologies of {{conflicting_hypotheses}} to locate latent confounding variables and selection biases.
  3. Apply {{bias_assessment_framework}} to score internal validity, statistical power, and p-hacking risk across all reviewed studies.
  4. Execute a qualitative and quantitative aggregation using {{statistical_aggregation_method}} to determine pooled effect sizes.
  5. Conduct subgroup heterogeneity analyses (I-squared calculation equivalent) to explain variance between conflicting findings.
  6. Evaluate the epistemological strength of causal inferences against standard criteria (e.g., Bradford Hill).
  7. Synthesize points of empirical convergence, non-replicable outliers, and genuine theoretical impasses.
  8. Translate epistemic certainty levels into practical risk boundaries aligned with {{policy_implications}}.

Constraints

  • MUST classify every synthesized finding into a defined evidential certainty tier (High, Moderate, Low, Insufficient).
  • MUST NOT treat observational correlations as equivalent to randomized experimental evidence.
  • Methodology appraisals MUST explicitly apply {{bias_assessment_framework}}.
  • Language must maintain rigorous epistemic neutrality when evaluating {{conflicting_hypotheses}}.
  • The report must clearly demarcate settled consensus from unresolved methodological artifacts.

Output format

Generate an exhaustive synthesis report with the following mandatory sections:

  1. Epistemological Summary & Evidentiary Grade Matrix
  2. Methodological Divergence Across {{conflicting_hypotheses}}
  3. Risk of Bias & Study Quality Audit (using {{bias_assessment_framework}})
  4. Meta-Analytic Synthesis & Pooled Effect Size Evaluation (via {{statistical_aggregation_method}})
  5. Unresolved Paradoxes & Heterogeneity Decomposition
  6. Strategic Directives & Risk Boundaries for {{policy_implications}}

Self-review

  • Verify that each competing hypothesis in {{conflicting_hypotheses}} receives symmetrical, rigorous scrutiny.
  • Ensure pooled conclusions are weighted according to sample size and power rather than simple study counts.
  • Check that recommendations directly reflect the uncertainties uncovered in {{target_research_question}}.
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.

writing-content
writing-long-form
complex-reasoning-analysis-math
meta-analysis
research-synthesis
epistemology