/cs-clinical-research¶
Run the clinical-research skill on this input:
$ARGUMENTS
Three-tool workflow¶
-
endpoint_selector.py— Score candidate endpoints across clinical relevance, measurability, regulatory acceptance, sensitivity-to-change, and burden. Classify PRIMARY / KEY-SECONDARY / EXPLORATORY. Flags unvalidated surrogates (cannot be primary). Industry tuning via--profile. -
sample_size_estimator.py— Closed-form power / sample size for two-arm means (Cohen's d), proportions (normal approx), or survival (Schoenfeld events). Inflates for dropout. The effect/difference/HR must trace to a published or anchor-based source. -
phase_gate_scorer.py— Score the study plan 0-100 across recruitment feasibility, endpoint readiness, statistical power, operational complexity, and budget fit. Verdict + named owners (PI, Medical Monitor, Biostatistician, Regulatory Owner).
Output¶
- Endpoint classification + surrogate flags
- Sample-size estimate with assumptions block
- Phase-gate verdict with named owner chain
- Top 3 next actions
Hard rule¶
Every output is an ESTIMATE, not a protocol. A biostatistician, medical monitor, and regulatory owner sign the final design.
First run + optimization¶
- Onboard first:
python3 scripts/onboard.py(area, alpha, power, dropout, named owners) — saved config pre-configures every tool.--showlists the questions. - Optimize (opt-in): only if the user asks to optimize/run a loop, hand off to autoresearch via
scripts/ar_evaluator.py(feasibility_composite, higher is better).
Distinct from¶
ra-qm-team— that's the regulatory submission. This designs the study.research/grants— that finds funding. This designs the trial.product-team/experiment-designer— that's a product A/B. This is a clinical trial.