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.

Install to Claude Code

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