Skill UI

A comprehensive guide for assembling a fully transparent and reproducible research package required for academic submissions (e.g., JRU/Springer). It structures the necessary components—including full experimental instructions, source code (z-Tree/Qualtrics), estimation scripts, and de-identified data—to allow any external party to replicate the study's findings end-to-end. Focuses on both procedural reproducibility and structural econometrics re-runnability.

A comprehensive guide for designing and reporting rigorous computational studies in Operations Research (OR) manuscripts. It covers best practices for selecting benchmark instances and strong baselines, applying statistical methods to stochastic output (e.g., confidence intervals), and adhering to mandatory code and data deposit standards (ORJournal workflow) to ensure full reproducibility.

Mandatory package structure for submitting accepted empirical papers to the Quarterly Journal of Economics (QJE). It ensures complete research reproducibility by organizing raw data, derived files, and analysis code. This package guides authors in creating a comprehensive, self-contained deposit that allows any investigator to regenerate every figure, table, and result published in the manuscript, adhering to strict academic data-availability policies.

This skill guides the creation of computable phenotypes and patient cohorts using the OHDSI/OMOP CDM standards. It allows users to define precise, executable criteria by combining standard concept sets (like PheKB) with advanced Natural Language Processing (NLP) features extracted from free clinical text. Use this when structured codes alone are insufficient to capture critical health information (e.g., symptoms, social context).

This skill decodes complex pipe-delimited HL7 v2.x messages (including ADT, ORU, MDM) into structured segments and fields. It is essential for ingesting HL7 feeds from interface engines, allowing users to surface embedded clinical narratives (OBX-5 and NTE-3) for subsequent Natural Language Processing (NLP) analysis. It also provides segment-aware de-identification capabilities to redact PHI while preserving the native HL7 message structure.