Framing Research Questions

This is the mandatory first step before any data analysis, designed to prevent p-hacking and HARKing by forcing you to write down your research question, hypotheses, and what counts as an answer before you touch outcome data. It walks through context exploration, clarifying questions, proposes 2-3 framings with tradeoffs, then documents everything in a markdown file you commit to git. The hard gate is real: no loading datasets, no statistics, no plots until your research framing is approved. It's strict about this because once you've seen the data, you can't unsee it, and every subsequent choice becomes contaminated. Even "simple" questions go through this. If you do any kind of confirmatory analysis or care about scientific rigor, this enforces the discipline that keeps results honest.

Install to Claude Code

npx -y skills add k-dense-ai/science-superpowers --skill framing-research-questions --agent claude-code