Skip to content
Get packs

Ontology Term Resolution

Look up and verify ontology term IDs (UBERON, CL, EFO, HPO) against EBI OLS before using them

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
12 files

What it does

When an agent needs an ontology ID for a label such as a tissue, cell type, or disease, this skill makes it search the EBI Ontology Lookup Service instead of writing an ID from memory, then check that the chosen ID exists, is current, and carries the expected label. It also helps check prefixes and identifier formats, and maps lab shorthand like PBMC through ZOOMA, always with an OLS check before the ID is accepted.

Great for

  • Researchers preparing metadata for GEO, ENA, BioSamples, CELLxGENE, HCA or ISA-Tab submissions
  • Curators auditing a spreadsheet of ontology IDs for obsolete or mislabelled terms
  • Data engineers building CI checks that reject malformed or wrong-ontology CURIEs

Skip it if

  • Final scientific judgement about whether a term fits a sample: the skill flags lexical matches, but a curator must confirm context, since a valid ID can still be the wrong term.
  • Environments without network access, because OLS, Bioregistry, Identifiers.org and ZOOMA lookups all require live internet calls.

Try asking

  • “Find the UBERON term for 'left ventricle' and tell me whether it is an exact label match”
  • “Check this metadata.tsv for obsolete EFO IDs and labels that do not match their IDs”
  • “Is HPO a valid ontology prefix, or should I use HP?”
  • “Map the lab shorthand PBMC to a cell ontology term and validate the result”
Step-by-step guide: how to use Ontology Term ResolutionInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 12 original files, the MIT licence and an attribution note.

    ontology-term-resolution.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ontology-term-resolution.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ontology-term-resolution.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Always review match_type and validate the selected ID before writing it into a file; search results are candidates, not answers.
  • Constrain searches with --ontology (for example uberon or cl), because unfiltered ZOOMA results mix in unrelated ontologies.
  • Use --exact-only with --format tsv for batch columns so that anything not an exact hit is reported for manual review instead of guessed.

What's inside

  • references/companion-apis.md
  • references/curation-rules.md
  • references/ols4-api.md
  • references/ontology-registry.md
  • scripts/id_client.py
  • scripts/lookup_prefix.py
  • scripts/map_terms.py
  • scripts/ols_client.py
  • scripts/resolve_terms.py
  • scripts/validate_terms.py
  • scripts/zooma_client.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.