Primekg

This is a query interface for PrimeKG, Harvard's precision medicine knowledge graph with 100,000+ biomedical entities and 4 million relationships across genes, drugs, diseases, and phenotypes. You get three main functions: search for entities by name, pull direct neighbors with relationship types, and get disease context summaries. It's useful for drug repurposing research or when you need to connect molecular targets to clinical outcomes without stitching together multiple databases yourself. The data lives in a local CSV, so queries are fast but you're working with a static snapshot. Pairs well with OpenTargets for genetics or Semantic Scholar when you need current literature on top of the structured relationships.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill primekg --agent claude-code

Installs into .claude/skills of the current project.

Files

PrimeKG Knowledge Graph

When to use

Use for reproducing PrimeKG analyses, resolving entities in a specific graph artifact, or exploring recorded gene, drug, disease, phenotype, anatomy, and pathway associations. A path supports a research hypothesis; it does not establish causality, treatment efficacy, a prescribing recommendation, or a diagnostic conclusion.

PrimeKG upstream now recommends OptimusKG for new work. This skill remains scoped to PrimeKG CSVs; the helper is not an OptimusKG client. Published PrimeKG integrates 20 resources, with approximately 129,000 nodes and 4.05 million undirected relationships. CSVs contain reverse rows, so row counts differ from distinct undirected relationship counts. Count the actual pinned artifact.