Mining Pubmed Literature

What it does

When your agent uses it

• The user wants citations for a condition
• Abstracts to summarize
• MeSH-based searches
• A corpus of literature to run NER over

Example prompts

• “Use the mining-pubmed-literature skill to search and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical…”
• “/mining-pubmed-literature”

Requirements

• Python 3
• A credential in API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Build the query. Combine OpenMed-extracted terms with MeSH tags and field
2. 2ESearch with usehistory=y to capture WebEnv + query_key and the count.
3. 3Batch-fetch with EFetch/ESummary in pages of ≤ ~200 IDs (or by history),
4. 4Parse abstracts/metadata; store PMID, title, journal, date, abstract text.
5. 5NER the abstracts with openmed.analyze_text to extract diseases, drugs,

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • eutils.ncbi.nlm.nih.gov

  Also links to:

  • ncbi.nlm.nih.gov
  • support.nlm.nih.gov
  • pubmed.ncbi.nlm.nih.gov
  • meshb.nlm.nih.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mining Pubmed Literature loads about 1.7k tokens when it runs. Until then it costs about 175 tokens; SKILL.md has 525 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~175

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 525 words, ~1,747 tokens.

name

mining-pubmed-literature

description

Searches and fetches PubMed and PMC via NCBI E-utilities (ESearch then EFetch/ESummary) to gather biomedical evidence and build text corpora. Use when the user wants citations for a condition or drug, abstracts to summarize, MeSH-based searches, or a corpus of literature to run NER over. Trigger keywords: PubMed, PMC, NCBI, E-utilities, ESearch, EFetch, ESummary, MeSH, PMID, literature search, abstracts, evidence. Pairs adjacent to OpenMed: fetched abstracts feed openmed.analyze_text for biomedical NER, and OpenMed-extracted diagnoses/drugs/genes become the search terms. E-utilities are public; an optional free API key raises rate limits from 3 to 10 requests/second.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

research-genomics

metadata.pairs

adjacent

metadata.version

1.0

import requests, time

BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
API_KEY = None   # set to your free NCBI key to get 10 req/s instead of 3

def _params(**kw):
    if API_KEY:
        kw["api_key"] = API_KEY
    return kw

def esearch(term: str, retmax: int = 50) -> dict:
    """Find PMIDs; usehistory=y stores them on the Entrez History server."""
    r = requests.get(f"{BASE}/esearch.fcgi", params=_params(
        db="pubmed", term=term, retmax=retmax,
        usehistory="y", retmode="json"), timeout=30)
    r.raise_for_status()
    res = r.json()["esearchresult"]
    return {"count": int(res["count"]), "ids": res["idlist"],
            "webenv": res["webenv"], "query_key": res["querykey"]}

def efetch_abstracts(webenv: str, query_key: str, retmax: int = 50) -> str:
    """Pull abstracts by reference to the stored result set (no ID list needed)."""
    r = requests.get(f"{BASE}/efetch.fcgi", params=_params(
        db="pubmed", WebEnv=webenv, query_key=query_key,
        retmax=retmax, rettype="abstract", retmode="text"), timeout=60)
    r.raise_for_status()
    return r.text

hits = esearch('("type 2 diabetes"[MeSH]) AND metformin AND 2023:2025[pdat]')
print(hits["count"], "papers")
abstracts = efetch_abstracts(hits["webenv"], hits["query_key"])

curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=metformin&retmode=json"
curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=38000000&rettype=abstract&retmode=text"

def esummary(ids: list[str]) -> dict:
    r = requests.get(f"{BASE}/esummary.fcgi", params=_params(
        db="pubmed", id=",".join(ids), retmode="json"), timeout=30)
    r.raise_for_status()
    return r.json()["result"]   # keyed by PMID: title, pubdate, source, authors…

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/mining-pubmed-literature of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c