How does this skill help with research papers?

It provides a structured framework to analyze study design, identify internal/external validity issues, and flag potential biases in published findings.

Does it support standard medical research frameworks?

Absolutely, it integrates guidance for GRADE and Cochrane Risk of Bias (ROB) assessments for rigorous evidence-based analysis.

Can this skill detect statistical p-hacking?

Yes, it includes checks for common statistical pitfalls like p-hacking, outcome switching, and multiple comparison errors.

Is this skill only for medical research?

While it utilizes common medical frameworks, the core principles for methodology critique, statistical evaluation, and fallacy detection apply to all scientific and data-driven disciplines.

Scientific Critical Thinking

Name: Scientific Critical Thinking
Author: ricable

byricable

•

Data Science & ML

Evaluates scientific research rigor and methodology through systematic analysis of experimental design, statistical validity, and potential biases.

About

The Scientific Critical Thinking skill empowers Claude to perform high-level analysis of research papers, clinical trials, and scientific claims. By applying industry-standard frameworks like GRADE and Cochrane Risk of Bias (ROB), it helps researchers and developers identify methodological flaws, detect cognitive or statistical biases, and assess the strength of evidence. Whether you are conducting a literature review or validating data-driven conclusions, this skill provides a structured approach to ensuring scientific integrity and logical soundness across various domains.

Key Features

Systematic bias and confounding detection
Methodology and experimental design critique
1 GitHub stars
Identification of logical and scientific fallacies
Statistical analysis and p-value interpretation
Evidence quality assessment using GRADE and Cochrane ROB

Use Cases

Conducting systematic reviews or meta-analyses
Reviewing academic research papers for methodological validity
Validating the statistical foundations of data science claims

About

Key Features

Systematic bias and confounding detection
Methodology and experimental design critique
1 GitHub stars
Identification of logical and scientific fallacies
Statistical analysis and p-value interpretation
Evidence quality assessment using GRADE and Cochrane ROB

Use Cases

Conducting systematic reviews or meta-analyses
Reviewing academic research papers for methodological validity
Validating the statistical foundations of data science claims