Agent skill

clinical-study-designer

Clinical study design skill for medical device trials including IDE studies and post-market studies

Stars 514
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/domains/science/biomedical-engineering/skills/clinical-study-designer

Metadata

Additional technical details for this skill

domain
science
category
Clinical Evidence
skill id
BME-SK-024
specialization
biomedical-engineering

SKILL.md

Clinical Study Designer Skill

Purpose

The Clinical Study Designer Skill supports design of clinical studies for medical devices, including IDE studies, post-market studies, and registries, ensuring scientific rigor and regulatory acceptance.

Capabilities

  • Study design selection (RCT, single-arm, registry)
  • Endpoint definition guidance
  • Sample size calculation (superiority, non-inferiority, equivalence)
  • Protocol template generation
  • Informed consent template generation
  • CRF design assistance
  • Statistical analysis plan development
  • Randomization strategy
  • Blinding methodology
  • Interim analysis planning
  • Adaptive design support

Usage Guidelines

When to Use

  • Designing clinical trials
  • Calculating sample sizes
  • Developing protocols
  • Planning statistical analyses

Prerequisites

  • Clinical objectives defined
  • Target population identified
  • Comparator strategy determined
  • Regulatory pathway established

Best Practices

  • Select design appropriate for objectives
  • Ensure adequate statistical power
  • Plan for missing data
  • Include clinically meaningful endpoints

Process Integration

This skill integrates with the following processes:

  • Clinical Study Design and Execution
  • Clinical Evaluation Report Development
  • AI/ML Medical Device Development
  • Post-Market Surveillance System Implementation

Dependencies

  • PASS software
  • nQuery
  • FDA IDE guidance
  • ISO 14155 standard
  • Statistical analysis tools

Configuration

yaml
clinical-study-designer:
  study-designs:
    - randomized-controlled
    - single-arm
    - crossover
    - registry
    - real-world-evidence
  hypothesis-types:
    - superiority
    - non-inferiority
    - equivalence
  endpoint-types:
    - primary
    - secondary
    - exploratory

Output Artifacts

  • Protocol documents
  • Statistical analysis plans
  • Sample size calculations
  • Informed consent templates
  • CRF designs
  • Randomization schemes
  • Study synopses
  • IDE submission components

Quality Criteria

  • Design appropriate for clinical question
  • Sample size adequately powered
  • Endpoints clinically meaningful
  • Protocol comprehensive
  • SAP statistically rigorous
  • Documentation supports regulatory acceptance

Expand your agent's capabilities with these related and highly-rated skills.

a5c-ai/babysitter

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).

514 31
Explore
a5c-ai/babysitter

model-profile-resolution

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

514 31
Explore
a5c-ai/babysitter

verification-suite

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

514 31
Explore
a5c-ai/babysitter

state-management

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

514 31
Explore
a5c-ai/babysitter

git-integration

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

514 31
Explore
a5c-ai/babysitter

frontmatter-parsing

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

514 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results