This is a comprehensive oncology decision support tool that takes a patient's molecular profile (mutations, cancer type, biomarkers) and returns prioritized treatment recommendations with evidence levels. It queries CIViC, ClinVar, OpenTargets, and ClinicalTrials.gov to deliver FDA-approved therapies first, then investigational options, with built-in reasoning about resistance mechanisms when first-line treatments fail. The workflow is structured around real tumor board use cases: you get actionable treatment lists, not data dumps. It knows the difference between EGFR exon 19 deletion in NSCLC (osimertinib) versus T790M-mediated resistance (different TKI), and it won't recommend off-label options when approved ones exist. If you're building clinical decision support or need to automate evidence gathering for precision oncology cases, this handles the lookup hierarchy correctly.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-precision-oncology