sdtm

Answer SDTM structure questions and generate dummy SDTM domain data as R tibbles.

13|6|Updated Aug 9, 2026
One-click install
npx skills add https://github.com/kaipingyang/CDISC_training --skill sdtm-kaipingyang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sdtm
Source: https://github.com/kaipingyang/CDISC_training/tree/main/.claude/skills/sdtm
Command: npx skills add https://github.com/kaipingyang/CDISC_training --skill sdtm-kaipingyang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Clinical data professionals often need quick, accurate answers about CDISC SDTM domain structures, variable roles, codelists, and SUPPQUAL relationships, plus realistic example data for learning or prototyping, without digging through the full SDTMIG specification. ## Core Features & Use Cases - SDTM Structure Q&A: Explains domain meaning, class, structure, variable Role/Type/Core/Origin, and codelist values for domains such as DM, AE, EX, LB, VS, EG, CM, MH, DS, PC, PP, TU, TR, and RS. - SUPPQUAL Guidance: Documents the fixed 10-variable SUPPQUAL structure, IDVAR/IDVARVAL linking logic, and R code to pivot SUPP datasets back to wide format. - Dummy Data Generation: Produces runnable R tibble code with realistic CDISCPILOT01-based example records following ISO 8601 dates and correct variable types. - Use Case: A clinical data trainee asks "generate dummy AE data" and receives a ready-to-run R tibble with AEDECOD, AESEV, AESER, and AESTDTC populated from real pilot study patterns. ## Quick Start Ask the assistant to explain the structure of the AE domain or to generate dummy SDTM data for the DM domain in R.

Frequently Asked Questions about sdtm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate dummy SDTM data in R?

Request a specific domain such as DM or AE and the skill returns runnable R code using tibble() with realistic CDISCPILOT01 sample values. Generated data includes Req and Exp variables, ISO 8601 dates, and correct integer or float types.

What is SUPPQUAL in SDTM and how does it link to parent domains?

SUPPQUAL is a supplemental qualifier dataset with exactly 10 fixed variables including RDOMAIN, IDVAR, IDVARVAL, QNAM, and QVAL. It links to the parent domain through USUBJID plus the parent record's --SEQ value stored in IDVARVAL.

Which SDTM domains does this skill cover?

Detailed reference files cover DM, AE, EX, LB, VS, EG, CM, MH, DS, PC, PP, TU, TR, and RS, plus SUPPQUAL and general SDTM concepts. The index also summarizes Trial Design and Relationship domains like TA, TE, TS, and RELREC.

How are TU, TR, and RS domains related in oncology studies?

TU identifies each lesion at baseline with a TULNKID, TR records per-visit measurements referencing that TULNKID, and RS stores the overall RECIST response assessment. TRLNKGRP and RSLNKGRP connect measurements to their evaluation.

Does the generated dummy SDTM data use real study values?

Yes, examples are drawn from the pharmaversesdtm CDISCPILOT01 pilot data, so terms, codelist values, and date patterns reflect actual CDISC pilot records. STUDYID is CDISCPILOT01 and USUBJID follows the 01-701-XXXX format.