mcpField
C
clinical-trial-schema-designer

clinical-trial-schema-designer

github.com/jorgealvesData & databases2186 installsUpdated 4d ago
Repository

About clinical-trial-schema-designer

clinical-trial-schema-designer is a skill for clinical research and data engineering teams designing trial data structures. It generates CDISC-based designs from protocols for study setup, data integration, and submission preparation; it does not handle patient data or medical decisions.

Key features

  1. 01Design data structures from protocols
  2. 02Generate standardized CDISC structures
  3. 03Plan integration of data sources
  4. 04Prepare SDTM/ADaM submission structures
  5. 05Work from protocols, not patient data

Use cases

  1. 01Design EDC schemas for a clinical trial
  2. 02Unify data from multiple sources
  3. 03Prepare structures for FDA/PMDA requirements

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jorgealves/agent_skills --skill clinical-trial-schema-designer

After installing, type/clinical-trial-schema-designerin Claude Code to confirm it loaded.

Bundled filesskill.yaml

Details

From the project README

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).

Comments

Markdown supported