Skip to main content
skill CX Codex GP ChatGPT official · OpenAI

chebi-skill — Codex skill: ChEBI lookup and installation

Query ChEBI 2.0 for chemical searches, compound records, ontology links, and structure metadata. Use it when an agent needs a concise ChEBI summary.

Install into Codex · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openai/plugins --skill chebi-skill -a codex
Open on GitHub

What chebi-skill does

The skill searches ChEBI by text, fetches a compound record by its identifier, and follows parent or child links in the ontology. It uses es_search/ for text lookup and compound/<CHEBI:id>/ for a targeted record. Structure metadata is also within scope. By default, the script’s JSON response is turned into a short Markdown summary.

Every ChEBI request goes through scripts/rest_request.py. The script reads a JSON object from stdin; base_url and path are required, and the service address is https://www.ebi.ac.uk. Ask for raw JSON when you need machine-readable output. The input format also supports saving a raw response with save_raw and raw_output_path.

The skill supports Codex and ChatGPT; the installation command below targets Codex. Requests run through the included script, so the skill relies on scripts/rest_request.py to contact ChEBI.

What it helps with

  • find a chemical by a text query
  • fetch a compound record by ChEBI identifier
  • inspect child terms in the ontology
  • trace parent terms for a compound
  • retrieve chemical structure metadata

Example prompts for the agent

  • Look up caffeine in ChEBI and summarize the result.
  • Fetch the ChEBI record for CHEBI:27732 and give me its key details.
  • Show the ontology children of CHEBI:27732.

How to install chebi-skill

1Skills CLI (Vercel)

npx skills add openai/plugins --skill chebi-skill -a codex

2Manually: put the files in place

.agents/skills/chebi-skill/SKILL.md

For all projects use ~/.agents/skills/

Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them

Questions about chebi-skill

How do I install chebi-skill in Codex?

Run npx skills add openai/plugins --skill chebi-skill -a codex.

What does chebi-skill do?

It queries ChEBI 2.0 for chemical searches, compound records, ontology relationships, and structure metadata. The default output is a concise Markdown summary.

How does chebi-skill send ChEBI requests?

It uses scripts/rest_request.py, which reads a JSON object from stdin. The object needs base_url and path, and requests use https://www.ebi.ac.uk.

Similar skills

All skills for Science and research →

From the same set422

The whole set →
clinvar-variation-skill Queries ClinVar Clinical Tables and NCBI Variation to look up genetic variants, identifiers, and summary records. CX Codex GP ChatGPT 13installs clinicaltrials-skill This skill sends compact requests to the ClinicalTrials.gov API v2 and returns concise study summaries. Use it for study search and field inspection. CX Codex GP ChatGPT 13installs civic-skill Runs targeted GraphQL queries against CIViC to inspect schemas and extract cancer variant evidence. Fits life science research workflows in Codex. CX Codex GP ChatGPT 13installs chembl-skill This skill queries the ChEMBL API for activity, molecule, target, mechanism, and text-search data. Use it when you need concise summaries of ChEMBL records. CX Codex GP ChatGPT 13installs cellxgene-skill This skill sends compact CELLxGENE Discover API requests and summarizes public collection and dataset metadata. Use it for focused single-cell lookups. CX Codex GP ChatGPT 13installs cbioportal-skill Sends compact queries to the cBioPortal REST API for cancer studies and mutations. It outputs concise markdown summaries directly into the agent session. CX Codex GP ChatGPT 13installs biostudies-arrayexpress-skill This skill searches BioStudies and ArrayExpress by text or accession, then returns a concise summary. Use it to find a study or retrieve its record. CX Codex GP ChatGPT 13installs biobankjapan-phewas-skill Retrieves single-variant BioBank Japan PheWAS summaries from rsID, GRCh37, or GRCh38 inputs. Useful for rapid genetic association checks inside your coding agent. CX Codex GP ChatGPT 13installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor