Skill UI

A comprehensive workflow for systematically reviewing medical evidence. It allows users to search databases for clinical studies, build curated citation collections, grade evidence using established frameworks like GRADE, and generate professionally formatted, structured reports in academic citation styles (e.g., AMA). Ideal for conducting literature reviews and supporting clinical research. This tool helps transform raw medical data into actionable, structured knowledge.

This module provides minimal working examples for the OpenEvidence API, designed for clinical intelligence applications. Users can perform complex clinical queries to get treatment recommendations, check potential drug interactions based on patient context, and search for authoritative medical guidelines from major health organizations (e.g., ACC/AHA). Ideal for developing evidence-based healthcare decision support systems.

Generates publication-ready clinical decision support documents for pharma and clinical research, covering biomarker-stratified cohort analysis, evidence-graded treatment recommendations, statistical comparisons, and regulatory-ready LaTeX/PDF outputs.

Provide REST API access to ClinPGx, the successor to PharmGKB, for querying gene-drug interactions, CPIC/DPWG/FDA guidelines, allele functions, and evidence that supports precision dosing and pharmacogenomics-driven clinical decisions.

Query NCBI ClinVar for variant clinical significance, mixing gene/condition searches, API/FTP downloads, and VCF annotations to support genomic medicine interpretation workflows.

A specialized toolkit designed for generating and validating research-only artifacts for Clinical Decision Support (CDS) systems. It supports evidence-profile generation, cohort analysis, survival modeling, biomarker evaluation, and governance documentation. IMPORTANT: This skill is strictly for aggregate research and documentation; it must never be used for patient care, diagnosis, or live clinical operations.

A comprehensive toolkit for building, evaluating, and auditing survival models, specifically handling right-censored and competing-risk outcomes. It supports various models including Cox PH, survival forests, and SVMs, while providing best practices for leakage-safe preprocessing and robust performance evaluation in clinical or scientific ML workflows.