This is a computational go/no-go framework for drug targets before you commit resources to medichem. It runs a gated validation across genetic evidence, druggability, safety, and competitive landscape, then outputs a 0-100 score with a tier classification. The pipeline enforces an evidence hierarchy: genetic links first (OpenTargets, GWAS), then structural tractability (PDB, AlphaFold), tissue safety (GTEx), and existing compounds (ChEMBL, ClinicalTrials.gov). It's opinionated about running ML models even when you have database evidence, and it makes you compute rather than describe. Use this when you need a defensible rationale for target prioritization or deselection, not for general target biology exploration.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-drug-target-validation