agentleFS
YunghoYungho/family-doctor/pubmed-search/SKILL.md

pubmed-search

Skill2 starsChanged 8 months agoMITView on GitHub

Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies. Triggers on \"pubmed\", \"papers\", \"literature\", \"search PubMed\", \"find research on\".

7 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    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
  1. Distinctive:

    Search NCBI PubMed for scientific literature using NCBI E-utilities API.

    line 9
  2. Distinctive:

    Use the esearch endpoint to find article IDs:

    line 23
  3. Distinctive:

    Use efetch to get abstracts and metadata:

    line 33
  4. Very specific:

    Use quotes for exact phrases: "thyroid nodule"TI-RADS

    line 67
  5. Very specific:

    Use MeSH terms: "Hypertension"[Mesh]

    line 71
  6. Distinctive:

    After showing results, suggest:

    line 75
  7. Distinctive:

    No PII sent — only search terms transmitted to NCBI

    line 82

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PubMed Search

Search NCBI PubMed for scientific literature using NCBI E-utilities API.

When to Use

  • User asks to find papers on a topic
  • User wants recent publications in a field
  • User asks for references or citations
  • User wants to know the state of research on a topic
  • Trigger phrases: "pubmed", "papers", "literature", "research", "studies"

How to Execute

Step 1: Search for PMIDs

Use the esearch endpoint to find article IDs:

curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=YOUR_QUERY&retmax=10&retmode=json&sort=relevance"

Replace YOUR_QUERY with the search topic. Use sort=date for most recent.

Step 2: Fetch Article Details

Use efetch to get abstracts and metadata:

curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=PMID1,PMID2&retmode=xml"

Step 3: Parse and Display Results

Extract from XML/JSON:

  • PMID
  • Title
  • Authors (first author + et al.)
  • Journal name + Year
  • Abstract (first 300 chars)
  • PubMed URL: https://pubmed.ncbi.nlm.nih.gov/{PMID}/

Output Format

Return results in this structured format:

*PubMed Search: "[query]"*
_Found X results. Top N:_

*1.* [Article Title]
   _First Author et al. — Journal (Year)_
   PMID: [PMID]
   pubmed.ncbi.nlm.nih.gov/[PMID]

*2.* ...

Advanced Search Tips

  • Use quotes for exact phrases: "thyroid nodule"TI-RADS
  • Combine with AND/OR: diabetes AND hypertension
  • Filter by date: diabetes[dp] 2024:2026[pdat]
  • Filter by type: review[pt] AND hypertension[ti]
  • Use MeSH terms: "Hypertension"[Mesh]

Follow-up Suggestions

After showing results, suggest:

  • "Want me to summarize any of these papers?"
  • "Should I search with different keywords?"
  • "Want me to find related papers?"

Privacy Note

  • No PII sent — only search terms transmitted to NCBI
  • NCBI E-utilities is a free public API
  • Rate limit: ~3 requests/second recommended

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.