What problem does it solve? Researchers, reviewers, and analysts often struggle to systematically assess whether scientific claims are supported by rigorous methodology, sound statistics, and unbiased evidence, leading to acceptance of flawed conclusions. ## Core Features & Use Cases - Methodology and Design Critique: Evaluate study design, internal/external/construct validity, randomization, blinding, and measurement quality against established standards. - Bias and Fallacy Detection: Identify cognitive, selection, measurement, and analysis biases plus logical fallacies such as p-hacking, HARKing, and correlation-causation confusion. - Evidence Quality Assessment: Apply GRADE criteria, Cochrane risk-of-bias tools, and evidence hierarchies to weigh confidence in findings. - Use Case: When reviewing a clinical trial paper claiming a treatment effect, use this Skill to check randomization quality, power analysis, multiple comparison corrections, and whether causal language is justified by the design. ## Quick Start Ask the AI to critically evaluate the methodology, statistical validity, and potential biases of an attached research paper using GRADE and Cochrane risk-of-bias frameworks.