pubmed-eutils
Skill1 starsChanged 31 days agoBSD-3-ClauseView on GitHub
Search PubMed and fetch article metadata directly through NCBI E-utilities (esearch, efetch, esummary) with curl, reporting PMIDs. Use whenever a curator needs literature for a gene, process, or claim, wants a PMID for a citation, or asks to look something up in PubMed. Do not use a PubMed MCP for this.
- Reads credentials
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- amigoSkill
- annotate-functionSkill
- gene-reviewSkill
- gocam-best-practiceSkill
- gocam-reviewSkill
- noctuaSkill
- reportSkill
- save-to-drop-boxSkill
- summarySkill
- uniprot-databaseSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Use NCBI E-utilities directly via curl.
- Very specific: line 14
Always include email=help@geneontology.org&tool=go-ai-hub in requests, and &api_key=$NCBI_API_KEY when that variable is set (it is on the …
- Distinctive: line 15
Always report PMIDs instead of or in addition to DOIs.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PubMed searches via NCBI E-utilities
Use NCBI E-utilities directly via curl. Do NOT use a PubMed MCP.
Always include email=help@geneontology.org&tool=go-ai-hub in requests, and &api_key=$NCBI_API_KEY when that variable is set (it is on the GO AI hub; without it NCBI allows 3 requests/second).
Always report PMIDs instead of or in addition to DOIs.
Two-step workflow:
- Search for PMIDs (esearch):
Returns JSON with a list of PMIDs incurl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&retmax=50&term=QUERY&retmode=json&email=help@geneontology.org&tool=go-jupyter&api_key=$NCBI_API_KEY"esearchresult.idlist. Fetch details (esummary for metadata, efetch for full abstracts):
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id=PMID1,PMID2,...&retmode=json&email=help@geneontology.org&tool=go-jupyter&api_key=$NCBI_API_KEY"Returns title, authors, journal, date, DOI per article.
For full abstracts use efetch with XML:
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=PMID1,PMID2,...&retmode=xml&email=help@geneontology.org&tool=go-jupyter&api_key=$NCBI_API_KEY"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

