citation-management

Convert DOIs to BibTeX entries and validate citations for bibliographies.

5|2|Updated Jan 22, 2026

Search Tags:#bibliography #PubMed #metadata-extraction #BibTeX #citation-management #Google Scholar #CrossRef

Ready to run

npx skills add https://github.com/hyperbolic-c/auto-writing --skill citation-management-hyperbolic-c

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: citation-management
Source: https://github.com/hyperbolic-c/auto-writing/tree/main/claude-scientific-writer/skills/citation-management
Command: npx skills add https://github.com/hyperbolic-c/auto-writing --skill citation-management-hyperbolic-c

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, scholarly, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Manual citation management is time-consuming and error-prone, leading to inconsistent bibliographies and missing DOIs. This Skill automates metadata extraction, DOI-to-BibTeX conversion, and BibTeX formatting to produce accurate, submission-ready references.

Core Features & Use Cases

Search Google Scholar and PubMed to locate relevant papers and extract complete metadata (title, authors, year, journal, DOI).
Convert DOIs to BibTeX entries and automatically format keys, protecting capitalization and standardizing fields.
Validate citations, detect duplicates, and produce clean bibliography files for manuscripts.
Use Case: A researcher compiling a literature review can rapidly assemble a validated BibTeX library from multiple databases.

Quick Start

To begin, run: python scripts/search_pubmed.py "CRISPR gene editing" --limit 20 --output papers.json Then run: python scripts/extract_metadata.py --input papers.json --output citations.bib Finally run: python scripts/validate_citations.py citations.bib --check-dois

Frequently Asked Questions about citation-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automatically convert a DOI to a formatted BibTeX entry?▼

You can extract metadata and convert DOIs to BibTeX automatically by querying CrossRef, PubMed, or DataCite APIs. This process captures publication metadata and formats it into structured BibTeX with proper keys, protecting capitalization and standardizing fields for clean bibliographies.

What's the best way to extract publication metadata from PubMed and Google Scholar?▼

Extracting publication metadata from PubMed and Google Scholar is done via a Python workflow using the scholarly and requests libraries. This approach searches databases for relevant papers and pulls complete metadata including titles, authors, years, journals, and DOIs into structured JSON files.

Can I programmatically validate citations and detect duplicate entries in a bibliography?▼

You can validate citations and detect duplicates programmatically by running a validation script against your bibliography file. This workflow checks DOIs against external databases, identifies duplicate entries, and produces a clean, submission-ready bibliography for your manuscripts.

Does the scholarly Python library work well for building a literature review bibliography?▼

Yes, the scholarly Python library works for building a literature review bibliography by programmatically searching Google Scholar. Combined with requests for PubMed and CrossRef, it enables researchers to rapidly assemble a validated BibTeX library from multiple databases.

How do I search PubMed for papers and export the results to a BibTeX file?▼

To search PubMed and export BibTeX, you run a Python script to query the database and save the results as a JSON file. Then, a metadata extraction script reads that JSON, retrieves publication details, and generates a properly formatted BibTeX file for your manuscript.