Back to resources

SKILL

ontology-term-resolution

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

SUMMARY

What it does

This Agent Skill resolves free-text scientific labels to ontology term IDs and validates existing CURIEs against the EBI Ontology Lookup Service (OLS4). It is intended for use whenever an ontology identifier must be produced or checked, including annotating tissue, cell type, disease, phenotype, assay, chemical, organism, sex, or developmental stage fields; preparing metadata for GEO, ENA, BioSamples, CELLxGENE, HCA, or ISA-Tab submission; auditing a metadata table of term IDs; checking whether a term is obsolete and what replaced it; or mapping between ontologies. The skill provides two scripts: resolve_terms.py (text to ID) and validate_terms.py (ID to verdict). It requires Python 3.11+ and network access to https://www.ebi.ac.uk/ols4 (public, no API key). The skill is part of Scientific Agent Skills by K-Dense and is licensed under MIT.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.ontology-resolutionweight 90 · confidence 90data.ontology-validationweight 90 · confidence 90data.metadata-auditweight 70 · confidence 80

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.