Does this skill perform statistical power calculations?

The skill provides the necessary framework and justification for power analysis, guiding you through the methodological requirements for justified sample sizes.

Is it compliant with NIH grant requirements?

Yes, it includes specific checklists for NIH rigor and transparency, including considerations for Sex as a Biological Variable (SABV) and resource authentication.

Can I use this for non-biological research?

Absolutely. While it meets NIH standards, the principles of randomization, control groups, and internal validity are applicable to social sciences, engineering, and software testing.

How does this improve AI-generated research?

It provides domain-specific guardrails that ensure AI-driven research workflows maintain scientific integrity and follow established methodological patterns rather than just generating text.

Experiment Design & Research Rigor

Name: Experiment Design & Research Rigor
Author: astoreyai

byastoreyai

•

数据科学与机器学习

Facilitates the creation of methodologically sound research studies following NIH rigor standards and experimental best practices.

关于

The Experiment Design skill empowers researchers to architect high-quality scientific studies by providing structured frameworks for randomization, control groups, and statistical power analysis. It helps users navigate complex design choices—such as between-subjects vs. within-subjects or factorial designs—while ensuring compliance with NIH rigor and reproducibility standards. Ideal for drafting grant proposals, pre-registrations, and rigorous research protocols, this skill ensures that your AI-assisted research is grounded in scientific validity and transparent reporting.

主要功能

Structured protocols for randomization and double-blind execution
Automated NIH rigor checklists for scientific premise and biological variables
2 GitHub stars
Comprehensive study design templates including RCT, Factorial, and Crossover designs
Validation of internal validity and control group appropriateness
Guidance for power analysis and sample size justification

使用场景

Optimizing clinical or behavioral study designs to minimize bias
Developing rigorous methodology sections for NIH and NSF grant proposals
Creating transparent pre-registration documents for open science platforms

关于

主要功能

Structured protocols for randomization and double-blind execution
Automated NIH rigor checklists for scientific premise and biological variables
2 GitHub stars
Comprehensive study design templates including RCT, Factorial, and Crossover designs
Validation of internal validity and control group appropriateness
Guidance for power analysis and sample size justification

使用场景

Optimizing clinical or behavioral study designs to minimize bias
Developing rigorous methodology sections for NIH and NSF grant proposals
Creating transparent pre-registration documents for open science platforms