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.

GitHub stars: 202
last updated: Jun 1, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Framing Research Questions Into Investigations

Help turn a fuzzy research interest into a precise, falsifiable question with explicit hypotheses, the data required, and what would count as an answer — through natural collaborative dialogue.

Start by understanding the context (the data on hand, the domain, what your human partner already knows), then ask questions one at a time to sharpen the interest. Once you understand what is being investigated, present the framing and get approval.

Do NOT load the dataset, compute any statistic, fit any model, plot any outcome, or invoke any execution skill until you have presented a research framing and your human partner has approved it. This applies to EVERY investigation regardless of perceived simplicity.

Why this gate is strict for science specifically: Looking at outcomes before the question and predictions are fixed contaminates a confirmatory analysis. Once you have seen the data, you cannot un-see it, and every later choice (which test, which subgroup, which cutoff) becomes suspect. Framing first is what keeps a result confirmatory rather than a story told after the fact.

SKILL.md on GitHub