Programmatic PubMed access via NCBI E-utilities REST API. Covers Boolean/MeSH queries, field-tagged search, endpoints (ESearch, EFetch, ESummary, EPost, ELink), history server for batches, citation matching, systematic review strategies.
SkillScore96Maintained
Automatic
◆Research pack
Last verified 8/23/2026
What it changes
Passed 22 of 23 test cases with the skill, and 20 of 23 without it.
Without skill87%
With skill96%
Checks it passed that the model alone missed
The API request sets rettype to xml.
The query uses the format diabetes mellitus, type 2[mh]/drug therapy.
Multiple citation records in bdata are separated with carriage return characters.
2 fixed20 passed either way1 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+354%
Agent turns
0%
Response time
-32%
Model gemini-3.6-flashMeasured 8/23/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
How do I format a single search term combining the MeSH concept 'diabetes mellitus, type 2' with the specific 'drug therapy' subheading?
What was checked, without and with the skill
Checked
Without skill
With skill
The query uses the format diabetes mellitus, type 2[mh]/drug therapy.
Missed
Passed
case-15 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md499 lines3 files
PubMed Database
Overview
PubMed is the U.S. National Library of Medicine's database providing free access to 36M+ biomedical citations from MEDLINE and life sciences journals. This skill covers programmatic access via the E-utilities REST API and advanced search query construction using Boolean operators, MeSH terms, and field tags.
When to Use
Searching biomedical literature with structured Boolean/MeSH queries
Building automated literature monitoring or extraction pipelines
Conducting systematic literature reviews or meta-analyses
Retrieving article metadata, abstracts, or citation information by PMID/DOI
Finding related articles or exploring citation networks programmatically
Batch processing large sets of PubMed records
For Python-native PubMed access, prefer BioPython (Bio.Entrez) — this skill covers direct REST API usage
For broader academic search (non-biomedical), use OpenAlex or Semantic Scholar APIs
Prerequisites
pip install requests # HTTP client for E-utilities API
# Optional: pip install biopython — Bio.Entrez wrapper (higher-level API)