/claim #16

Summary

• Adds a self-contained study power and effect-size feasibility assistant for issue #16.
• Screens manuscript/statistical claims against sample size, outcome type, effect size, variance, alpha, target power, multiple-testing load, and preregistration evidence.
• Emits pass/revise/hold decisions, reviewer actions, deterministic audit digests, and JSON/Markdown/SVG/MP4 review artifacts.

Scope boundaries

• Uses synthetic study metadata only.
• Does not call external AI, statistics, publication, payment, or identity services.
• Avoids overlap with existing prompt-safety, supplement readiness, rebuttal pack, uncertainty calibration, limitations disclosure, grant-fit, citation-context, benchmark leakage, figure-claim, analysis-variable, and literature freshness/current-evidence temporal-drift slices.
• This module is specifically about whether the declared design has enough statistical power for the claimed effect; it does not judge whether the cited literature is current.

Validation

• npm run check
• npm test
• npm run demo
• ffprobe -v error -show_entries format=duration,size -show_entries stream=codec_name,width,height -of default=noprint_wrappers=1 reports/demo.mp4
• git diff --check