generate-research-questions

Generate ranked PICO/PECO research questions from profiled dataset JSON files.

Updated Mar 8, 2026

Search Tags:#feasibility #epidemiology #study-design #research-questions #pico #biostatistics #data-profile

Ready to run

npx skills add https://github.com/DamarisDeng/paper-writing-system --skill generate-research-questions

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: generate-research-questions
Source: https://github.com/DamarisDeng/paper-writing-system/tree/main/workflow/skills/generate-research-questions
Command: npx skills add https://github.com/DamarisDeng/paper-writing-system --skill generate-research-questions

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill converts profiled dataset outputs into a structured set of research questions, enabling rapid transition from data profiling to study design and planning.

Core Features & Use Cases

Generates a ranked set of primary and secondary research questions from profile.json and variable_types.json.
Performs rigorous feasibility checks, assigns variable roles (outcomes, exposures, covariates, stratifications), and documents assumptions to support robust study design.
Produces a validated research_questions.json artifact that guides downstream analysis and literature review in a reproducible workflow.

Quick Start

Run the generate-research-questions command with your output folder to produce candidate questions from profiled datasets.

Frequently Asked Questions about generate-research-questions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate research questions from profiled dataset outputs?▼

Generate research questions by processing profile.json and variable_types.json files into a ranked candidate set. The output is a research_questions.json artifact containing primary PICO/PECO questions, secondary questions, and variable role mappings for study design.

What is the PICO framework for formulating epidemiology research questions?▼

The PICO framework structures research questions by defining Population, Intervention, Comparison, and Outcome variables. This skill automatically assigns dataset variables to these roles to generate primary PICO/PECO questions suitable for epidemiology study design.

Can I assess study feasibility using my existing dataset profile?▼

Yes, you can assess study feasibility by running profiled dataset outputs through rigorous feasibility checks. The process evaluates variable types and data profiles to determine if sufficient data exists to support proposed research questions and study design.

How do I assign variable roles like exposure and outcome for biostatistics analysis?▼

Assign variable roles by mapping dataset variables into outcomes, exposures, covariates, and stratifications based on profile.json and variable_types.json. The skill automatically documents assumptions and outputs these mappings to support robust biostatistics analysis.

What's the best way to transition from data profiling to study design?▼

Transition from data profiling to study design by converting profile.json and variable_types.json into ranked research questions. This produces a validated research_questions.json artifact that guides downstream literature review and analysis in a reproducible workflow.