Back to resources

SKILL

primekg

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/primekg
Use with an agent

SUMMARY

What it does

This skill provides programmatic access to the Precision Medicine Knowledge Graph (PrimeKG), enabling search for entities (genes, drugs, diseases, phenotypes), retrieval of direct neighbors and associations, analysis of disease context, and identification of drug-disease paths. It is designed for knowledge-based drug discovery, drug repurposing, phenotype analysis, and network pharmacology. The skill includes a Python script (query_primekg.py) that queries a local CSV data file (kg.csv) downloaded from the PrimeKG Harvard Dataverse. The source documentation describes functions such as search_nodes, get_neighbors, and get_disease_context, and lists relationship types including protein_protein, drug_protein, disease_gene, drug_disease, disease_phenotype, and gwas. The skill is part of the Scientific Agent Skills library by K-Dense and is licensed under MIT.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

knowledge-graph.queryweight 90 · confidence 80data.retrieveweight 70 · confidence 70analysis.disease-contextweight 60 · confidence 60

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.