Clinical Research

Supports prospective clinical study design before submission: classifying endpoints, estimating sample size and power for two-arm designs.

Research & Data / Researchresearch-dataresearch
by AgentVoltv1.0.0Published 1y ago1 install
Free to sign up · every skill included with AgentVolt Pro

Before & after

Same prompt, same agent — the only difference is the skill.

PromptDesign a prospective study to test whether weekly calls improve health outcomes in Type 2 diabetes
Beforegeneric AI agent
That's an interesting clinical research question. Designing a prospective study requires careful planning around endpoints, sample size, and study design. I could help you think through some of the key decisions you'd need to make: what specific health outcome you're measuring, whether you're comparing against a control group, how long the study would run, and how many participants you'd need. There are also regulatory and statistical considerations that matter a lot. To give you real guidance, I'd want to know more about your hypothesis, your patient population, and what resources you have available. Have you worked with a biostatistician before? That's usually helpful for study design.
Afterwith Clinical Research
CLINICAL RESEARCH STUDY DESIGN — Weekly Calls for Type 2 Diabetes:

STUDY CLASSIFICATION:
Type: Two-arm prospective RCT (randomized controlled trial)
Phase: Phase 2 effectiveness (proof of concept, not pivotal)
Primary endpoint: HbA1c reduction at 12 weeks (surrogate endpoint flagged — monitors glycemic control but not hard outcomes like MI/death)

PRIMARY ENDPOINT DEFINITION:
• Measure: HbA1c drop from baseline
• Target: 1.2 percent reduction (clinically meaningful = 0.5 percent)
• Timeline: Baseline, 6 weeks, 12 weeks
• Success gate: Non-inferiority vs. standard care (not superiority — conservative estimate for weekly calls)

SECONDARY ENDPOINTS:
• Patient engagement: Call adherence (target 80 percent)
• Medication adherence: Pill counts (exploratory)
• Quality of life: DQOL questionnaire score (key-secondary, not exploratory)
• Adverse events: Hypoglycemia episodes (exploratory)

SAMPLE SIZE ESTIMATION (TWO-ARM DESIGN):
• Baseline HbA1c: 8.2 percent (typical T2D at presentation)
• Expected improvement: 1.2 percent for intervention, 0.4 percent for control
• Power: 80 percent (detect true difference if it exists)
• Alpha (false positive rate): 0.05
• Attrition: 15 percent
• CALCULATED N: 92 participants total (46 per arm)

STUDY SCHEDULE:
• Enrollment window: 8 weeks
• Active intervention: 12 weeks
• Follow-up: 4 weeks post-study
• Total duration: 24 weeks (6 months)

GO / GO-WITH-CONDITIONS / NO-GO PHASE GATE:
→ DECISION OWNERS: Principal investigator (MD), biostatistician (sample size math), regulatory affairs (IRB compliance)
→ GREEN FLAG: Sample size powered, control arm defined, HbA1c lab capacity confirmed → GO (proceed to enrollment)
→ YELLOW FLAG: Attrition modeling shows 25% dropout risk; budget for 130 enrollees → GO-WITH-CONDITIONS (pilot adherence intervention first)
→ RED FLAG: HbA1c lab turnaround > 2 weeks; endpoint measurement delays → REDESIGN (centralize labs)

DISCLAIMER: This estimate is preliminary. Consult biostatistician + regulatory team before submission. Never a clinical recommendation.

About this skill


name: clinical-research description: Use when Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample ...

Clinical Research

Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO / GO-WITH-CONDITIONS / REDESIGN / NO-GO phase-gate decision. Every output is an ESTIMATE plus a named human owner (clinician / biostatistician / regulatory owner) — never clinical fact, never a finished protocol. Distinct from ra-qm-team, which handles the regulatory/QM submission (ISO 13485, EU MDR, FDA 510(k)/PMA/QSR), not the study design.

What you get

  • Public GitHub repo (alirezarezvani/claude-skills)
  • the clinical-research skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.

Customize your output

  • Fork the repo and adapt the skill's instructions and references to your workflow.

Example output

Activates automatically when your request matches Clinical Research; chains with the other skills, agents, and commands in the collection.

Best for

Creators, builders, and teams using Claude Code.

SKILL.md preview

SKILL.md
---
name: clinical-research
description: Use when designing a prospective clinical study before submission — selecting endpoints, estimating sample size and power, or scoring a study plan for a feasibility go/no-go decision.
version: 1.0.0
category: Research & Data / Research
author: AgentVolt
license: proprietary
tags:
  - research-data
  - research
---

# Clinical Research

Supports prospective clinical study design before submission: classifying endpoints, estimating sample size and power for two-arm designs, and scoring the plan toward a phase-gate decision. Every output is an estimate with a named human owner, never a finished protocol.

## When to use

… (sign up to view the full skill)
Sign up to view, copy, and install the full skill

More research & data skills

View all Research & Data skills →