Tooluniverse Precision Oncology

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.

skills.sh installs: 426
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-precision-oncology --agent claude-code

Installs into .claude/skills of the current project.

Files

Precision Oncology Treatment Advisor

Provide actionable treatment recommendations for cancer patients based on their molecular profile using CIViC, ClinVar, OpenTargets, ClinicalTrials.gov, and structure-based analysis.

Domain Reasoning

Treatment selection follows a strict evidence hierarchy: FDA-approved for this specific mutation in this cancer type ranks highest, followed by approval for this mutation in any cancer (tumor-agnostic), then active clinical trials, and finally off-label use. Skipping this hierarchy to recommend off-label therapies when an approved option exists is a clinical error. Always check current NCCN guidelines and recent literature, as approvals change rapidly — a drug that was investigational last year may now be first-line.

When looking up treatment for a specific mutation, search CIViC and OncoKB FIRST, not PubMed. These databases have curated evidence levels. PubMed is for when curated databases don't have the answer.

Treatment Selection Reasoning

SKILL.md on GitHub

Details

Repository: github.com/mims-harvard/tooluniverse
First seen: Jun 3, 2026