cdisc-workflows

Build a USDM v3.0 study representation from a ClinicalTrials.gov record (Stage 1 output) and, when present, the protocol PDF Schedule of Activities. Use this skill for Stage 2 of the protocol-to-synthetic-SDTM pipeline: when 00_raw/<NCT>.json exists and you need 01_usdm/usdm.json + soa.json. Deterministically maps the structured, enumerated CT.gov fields (arms, interventions, eligibility flags, phase, design) and uses the LLM ONLY for the free-text fragments that have no clean schema field — parsing eligibility criteria into discrete criterion objects, normalising objectives/endpoints, and reading the protocol Schedule of Activities into a visit grid + activity list. Triggers: 'extract USDM', 'build USDM', 'Stage 2', 'USDM from study record', 'SoA extraction'.

Match each USDM activity/assessment to a CDISC Biomedical Concept (BC). Use this skill for Stage 3 of the protocol-to-synthetic-SDTM pipeline: when 01_usdm/usdm.json exists and you need 02_bc_matches.json. Deterministically retrieve candidate BCs from the CDISC Library (keyword / NCIt search via the cdisclib MCP server), then use the LLM ONLY to select the best-matching BC from the retrieved candidate set and assign a confidence score. The LLM never invents a BC id — it only chooses from candidates. Unmatched activities are flagged, not dropped. Triggers: 'match biomedical concepts', 'BC matching', 'Stage 3', 'map activities to BCs', 'find biomedical concept for activity'.