Tooluniverse Clinical Trial Matching

This matches cancer patients to clinical trials by their molecular profile, not just diagnosis. It queries ClinicalTrials.gov then cross-references against CIViC, OpenTargets, ChEMBL, and FDA databases to score trials on a 0-100 scale with evidence tiers. The workflow is thorough: it parses eligibility criteria for biomarker requirements, maps patient mutations to trial interventions, checks drug mechanisms against the patient's specific alterations, and handles geographic proximity. Best for precision oncology cases where you need ranked trial options for patients with known mutations like EGFR L858R or KRAS G12C, especially after standard therapies have failed. The molecular-first matching is the key bit here, it prioritizes genotype over everything else.

skills.sh installs: 406
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-clinical-trial-matching --agent claude-code

Installs into .claude/skills of the current project.

Files

Clinical Trial Matching for Precision Medicine

Transform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.

KEY PRINCIPLES:

Report-first approach - Create report file FIRST, then populate progressively
Patient-centric - Every recommendation considers the individual patient's profile
Molecular-first matching - Prioritize trials targeting patient's specific biomarkers