Preregistration Writer AI Prompt

Help me write a complete preregistration for my study.

Study overview: {{study_overview}}
Platform: {{platform}} (OSF, AsPredicted, ClinicalTrials.gov, PROSPERO)

Preregistration locks in your hypotheses, design, and analysis plan before data collection, preventing HARKing and p-hacking.

1. Hypotheses:
   - State each hypothesis precisely and in a way that is clearly falsifiable
   - Specify directionality: 'X will be higher than Y' not 'X and Y will differ'
   - Distinguish confirmatory hypotheses (tested with pre-specified alpha) from exploratory questions
   - Number each hypothesis: H1, H2, H3

2. Design:
   - Study type and design (RCT, observational, within-subjects, etc.)
   - Manipulations and their operationalization
   - Measures: name and description of each instrument
   - Primary outcome: specify exactly one primary outcome
   - Secondary outcomes: list all, in priority order

3. Participants:
   - Target population and eligibility criteria (inclusion and exclusion)
   - Recruitment source and procedure
   - Sample size and power analysis justification
   - Stopping rule: will data collection stop at a fixed N or at a fixed date?

4. Analysis plan:
   - Primary analysis: exact test, model specification, covariates, alpha level
   - Secondary analyses: same level of specificity
   - Handling of assumption violations: specify in advance what you will do
   - Missing data approach
   - Exclusion criteria for the analytic sample (different from eligibility)
   - Multiple comparison correction

5. What happens if:
   - Recruitment falls short of target?
   - Primary outcome has excessive missing data?
   - A key assumption is violated?
   Pre-specify contingency plans for foreseeable problems.

6. Transparency commitments:
   - Will data be shared? Where and under what conditions?
   - Will analysis code be shared?
   - Will materials be shared?

Return: complete preregistration text formatted for the chosen platform, with each section written at the level of specificity required to make it a meaningful constraint.