
Clinical Trial Protocol Skill
Generates clinical trial protocols for medical devices or drugs through a structured five-step workflow that starts with intervention details, researches similar trials and FDA guidance, then builds out protocol sections covering study design, population criteria, intervention specifics, and operational procedures. Built around a waypoint system that saves progress as JSON and markdown files, so you can stop and resume without losing work. Includes a research-only mode if you just need competitive analysis and regulatory pathway intel without the full protocol. Requires the clinical trials MCP server to search ClinicalTrials.gov and pull trial details. The architecture is thoughtfully modular, each step isolated in its own subskill file, and it even includes a Python script for statistical sample size calculations. This is serious regulatory documentation work, not a quick template filler.
- skills.sh installs
- 457
- GitHub stars
- 443
- last updated
- Aug 21, 2026
Install
$ npx -y skills add anthropics/healthcare --skill clinical-trial-protocol-skill --agent claude-codeInstalls into .claude/skills of the current project.
Files
Clinical Trial Protocol Skill
⚠️ EXECUTION CONTROL - READ THIS FIRST
CRITICAL: This orchestrator follows a SIMPLE START approach:
- Display the welcome message FIRST (shown in "Startup: Welcome and Confirmation" section below)
- Ask user to confirm they're ready to proceed - Wait for confirmation (yes/no)
- Jump directly into Full Workflow Logic - Automatically run subskills sequentially
- Do NOT pre-read subskill files - Subskills are loaded on-demand only when their step executes
Why this matters:
- Pre-reading all subskills wastes context and memory
- Subskills should only load when actually needed during execution
- Workflow automatically handles resuming from existing waypoints
Overview
This skill generates clinical trial protocols for medical devices or drugs using a modular, waypoint-based architecture
What This Skill Does
Starting with an intervention idea (device or drug), this orchestrated workflow offers two modes:
Sponsors
Details
- Repository
- github.com/anthropics/healthcare
- Categories
- Documentation, Data Science & ML, Design & UI/UX
- First seen
- Jun 3, 2026