Summary
If you're setting up clinical trials and need to generate CDISC-compliant schemas (SDTM/ADaM) from protocol documents, this automates a lot of the tedious mapping work between study design and regulatory data structures. It's aimed at the study setup phase when you're designing EDC systems or prepping for FDA submissions. The big caveat is that it only generates the design, you still need to implement it in a GxP-validated environment with proper controls. It works on protocols, not actual patient data, and can struggle with vague protocols or non-standard Phase 1 studies where variables don't fit cleanly into existing CDISC domains. Saves time on the grunt work but doesn't replace validation requirements.
Install to Claude Code
npx -y skills add jorgealves/agent_skills --skill clinical-trial-schema-designer --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub
Clinical Trial Schema Designer
Purpose and Intent
The clinical-trial-schema-designer bridges the gap between clinical research and data engineering. It helps automate the creation of standardized data structures (CDISC) based on clinical protocols, reducing the manual effort required for data ingestion and submission preparation.
When to Use
- Study Setup: Use during the "Start-up" phase of a clinical trial to design the Electronic Data Capture (EDC) schemas.
- Data Integration: When merging data from multiple sources into a single study standard.
- Submission Prep: To ensure the data structure matches FDA/PMDA requirements for SDTM/ADaM.
When NOT to Use
- Unvalidated Systems: Clinical data must be handled in GxP-validated environments. This tool generates the design, but the implementation must follow strict validation protocols.
- Medical Decision Making: This is a data structuring tool, not a clinical diagnostic or treatment tool.
Error Conditions and Edge Cases
- Ambiguous Protocols: If the input text is vague about how a variable is measured, the generated schema may be incomplete.
- Non-Standard Studies: Phase 1 or highly experimental studies may use variables that don't fit existing CDISC domains perfectly.
Security and Data-Handling Considerations
- IP Protection: Clinical protocols are intellectual property. Ensure the environment running this skill is secure.
- No Patient Data: This tool works on protocols (the plan), not the actual results (the data).
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
