Start
Run it after a literature turn in the same session, so it has evidence to work from:
text
/hypothesis Based on the HRV biofeedback literature collected in this session, map the research space, list gaps and contradictions, and generate testable hypotheses ranked by novelty, plausibility and testability.
You can also run it on its own — it will search first.
What you get
hypotheses_report.md with:
- Research space map — the constructs, populations and designs the literature covers.
- Gaps and contradictions — where results disagree or evidence is missing, with the sources.
- Candidate hypotheses — each with rationale, the sources it builds on, the design that would test it, and scores for novelty, plausibility and testability.
- Ranked shortlist — the ones worth designing next.
Next step
Pick one and ask for the design: "Design an experiment to test hypothesis 2" — the experiment-design skill reads the hypothesis and its sources.
Walkthrough: From literature to hypotheses.