skills/literature/search/database-comparison-guide/SKILL.md
Compare major academic databases and when to use each for research
npx skillsauth add wentorai/research-plugins database-comparison-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A comprehensive reference for choosing and querying the right academic database for your research domain, including coverage details, advanced operators, and cross-database strategies.
| Database | Coverage | Disciplines | Access Model | Unique Strength | |----------|----------|-------------|--------------|-----------------| | Web of Science | 1900-present, 21,000+ journals | Multidisciplinary | Subscription | Citation indexing, Journal Impact Factor | | Scopus | 1970-present, 27,000+ journals | Multidisciplinary | Subscription | Largest abstract/citation DB, CiteScore | | PubMed | 1946-present, 35M+ records | Biomedical, life sciences | Free | MeSH controlled vocabulary, clinical filters | | IEEE Xplore | 1872-present, 6M+ docs | Engineering, CS | Subscription | Conference proceedings, standards | | Google Scholar | Broad, undisclosed | All fields | Free | Widest coverage, full-text indexing | | JSTOR | Historical archives | Humanities, social sciences | Subscription | Historical journal runs, primary sources | | arXiv | 1991-present, 2.4M+ papers | Physics, CS, Math, Bio | Free | Preprints, no peer-review delay | | SSRN | 1994-present | Social sciences, law | Free | Working papers, early-stage research |
For physics, computer science, and mathematics, combine arXiv preprints with Web of Science indexed journals:
# arXiv API query for recent ML papers
curl "http://export.arxiv.org/api/query?search_query=cat:cs.LG+AND+ti:transformer&start=0&max_results=25&sortBy=submittedDate&sortOrder=descending"
For biomedical research, PubMed with MeSH terms provides the most precise retrieval:
# PubMed E-utilities search with MeSH
curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=%22machine+learning%22[MeSH]+AND+%22drug+discovery%22[MeSH]&retmax=50&sort=date"
TS=("deep learning" AND "drug discovery") AND PY=(2020-2025)
# TS = Topic (title + abstract + keywords)
# PY = Publication Year
# Use NEAR/x for proximity: TS=("climate" NEAR/3 "adaptation")
TITLE-ABS-KEY("deep learning" AND "drug discovery") AND PUBYEAR > 2019
# Additional operators:
# AUTHLASTNAME(smith) AND AUTHFIRST(j*)
# AFFIL("MIT" OR "Massachusetts Institute of Technology")
# REF("seminal paper title")
"deep learning"[Title/Abstract] AND "drug discovery"[Title/Abstract]
AND ("2020/01/01"[Date - Publication] : "2025/12/31"[Date - Publication])
# Use filters: Clinical Trial[pt], Review[pt], Free Full Text[Filter]
A robust literature search should query multiple databases to maximize recall:
tools
10 document processing skills. Trigger: extracting text from PDFs, parsing references, document Q&A. Design: parsing pipelines (GROBID, marker) and structured extraction tools.
documentation
Guide to tldraw for infinite canvas whiteboarding and diagram creation
testing
Create graphical abstracts, schematic diagrams, and scientific illustrations
documentation
Create UML diagrams and architecture visualizations with PlantUML