Does it support the creation of visual diagrams?

Absolutely. It integrates with the scientific-schematics skill to automatically generate publication-quality decision trees, flowcharts, and framework diagrams.

What frameworks does this skill use to evaluate evidence?

The skill utilizes globally recognized standards including the GRADE framework (Grading of Recommendations, Assessment, Development, and Evaluations) and the Cochrane Risk of Bias (ROB) tool.

Can this skill help identify p-hacking in research papers?

Yes, it includes a robust statistical review checklist that identifies common pitfalls such as p-hacking, outcome switching, and improper p-value interpretation.

Is this skill meant for formal peer review writing?

While it provides the critical analysis required for a review, the documentation recommends using the dedicated 'peer-review' skill for the formal writing and formatting of review documents.

Scientific Critical Thinking

Name: Scientific Critical Thinking
Author: Weiwei-Mao

byWeiwei-Mao

Data Science & ML

Evaluates the rigor of scientific claims by assessing methodology, identifying biases, and grading evidence quality using standardized frameworks.

About

Scientific Critical Thinking is a specialized skill designed to help researchers and developers systematically evaluate the validity of scientific evidence. It provides a structured approach to critiquing experimental designs, detecting cognitive and analytical biases, and assessing statistical robustness. By applying industry-standard frameworks like GRADE and Cochrane Risk of Bias, the skill enables users to distinguish high-quality evidence from flawed research. Additionally, it features built-in integration for generating publication-quality scientific schematics to visualize complex frameworks and workflows.

Key Features

0 GitHub stars
Evidence quality grading using GRADE and Cochrane ROB
Statistical analysis evaluation and pitfall identification
Automated generation of scientific diagrams and flowcharts
Methodology and experimental design validation
Systematic bias and confounding factor detection

Use Cases

Conducting deep-dive critical analysis of research papers and protocols
Synthesizing high-confidence evidence for meta-analyses and systematic reviews
Developing rigorous experimental designs that minimize systematic bias

About

Key Features

0 GitHub stars
Evidence quality grading using GRADE and Cochrane ROB
Statistical analysis evaluation and pitfall identification
Automated generation of scientific diagrams and flowcharts
Methodology and experimental design validation
Systematic bias and confounding factor detection

Use Cases

Conducting deep-dive critical analysis of research papers and protocols
Synthesizing high-confidence evidence for meta-analyses and systematic reviews
Developing rigorous experimental designs that minimize systematic bias