getbib

Retrieve BibTeX entries for papers via Playwright browser workflows.

15|1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/shilong20/getbib --skill getbib
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: getbib
Source: https://github.com/shilong20/getbib/tree/main
Command: npx skills add https://github.com/shilong20/getbib --skill getbib

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, and includes scripts (resource) components.

What problem does it solve?

This Skill helps researchers convert paper titles into accurate BibTeX entries by consulting authoritative sources and extracting BibTeX via an automated browser workflow, reducing manual effort and hallucinations.

Core Features & Use Cases

  • Authority-first BibTeX retrieval: searches trusted sources (DBLP, OpenReview, arXiv, NeurIPS, PMLR, IEEE) for verifiable BibTeX entries.
  • End-to-end extraction: uses Playwright-driven browsing to fetch BibTeX from the recommended page or metadata path, not memory.
  • Batch processing and auditability: outputs a browsable link document (bib_link_candidates.md) and final BibTeX file with per-item provenance for review.

Quick Start

Enter a paper title (and optional author) to fetch a trusted BibTeX via browser extraction.

Frequently Asked Questions about getbib

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

FAQPage Schema
How do I get BibTeX entries for multiple papers automatically?

You can retrieve BibTeX entries for multiple papers by batch processing files in CSV, TSV, JSON, JSONL, or TXT formats. The tool searches authoritative sources like DBLP, arXiv, and OpenReview, then extracts verifiable BibTeX via browser automation.

Can I use Playwright to scrape BibTeX from academic sources like PMLR or NeurIPS?

Yes, this skill uses Playwright to fetch BibTeX directly from trusted academic sources including PMLR, NeurIPS, IEEE, and OpenReview. It browses the recommended page or metadata path to extract accurate entries rather than generating them from memory.

What is the best way to avoid hallucinated citations when generating a bibliography?

The best way to avoid hallucinated citations is extracting BibTeX directly from authoritative sources. This tool queries trusted databases and uses a browser workflow to fetch verifiable entries, outputting a browsable link document and final BibTeX file for review.

Does batch BibTeX retrieval support adding optional author fields to improve search accuracy?

Yes, batch BibTeX retrieval supports optional author fields alongside paper titles. Providing author names helps refine the search query when consulting trusted sources, ensuring more accurate extraction results.

What files are outputted when converting paper titles to BibTeX?

Converting paper titles to BibTeX outputs a final BibTeX file, a browsable link document named bib_link_candidates.md for auditing sources, and a summary.json file containing intermediate results and provenance data.