biorxiv-database

Query bioRxiv preprint metadata by keywords, authors, and date ranges.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/BKZhao/MIMIC-Papers-Repro-Agent --skill biorxiv-database-bkzhao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: biorxiv-database
Source: https://github.com/BKZhao/MIMIC-Papers-Repro-Agent/tree/main/.codex/skills/biorxiv-database
Command: npx skills add https://github.com/BKZhao/MIMIC-Papers-Repro-Agent --skill biorxiv-database-bkzhao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

bioRxiv hosts a large volume of life sciences preprints; this skill enables researchers to efficiently discover, filter, and retrieve paper metadata and PDFs for literature reviews and follow-up analysis.

Core Features & Use Cases

  • Keyword, author, and date-range search with optional category filtering.
  • Metadata extraction: doi, title, authors, date, category, license, abstract.
  • PDF downloads and export to JSON for downstream analytics.

Quick Start

Ask it to search bioRxiv for a topic and export the results to JSON.

Frequently Asked Questions about biorxiv-database

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

FAQPage Schema
How do I search bioRxiv preprints and export structured metadata?

You can search bioRxiv preprints by keywords, authors, and date ranges to extract structured metadata like doi, title, and abstract, then export the results to JSON for downstream analysis.

Can I filter bioRxiv literature searches by specific category?

Yes, bioRxiv literature searches support optional category filtering, allowing you to narrow down preprint results to defined life sciences categories before extracting metadata.

What is the best way to download bioRxiv preprint PDFs in bulk?

The best way to download bioRxiv preprint PDFs is to query the bioRxiv API using specific search parameters, which returns structured metadata and enables direct PDF downloads for the matched papers.

Does the bioRxiv API search return DOI and abstract fields for preprints?

Yes, querying the bioRxiv API returns consistent JSON formatted metadata that includes fields like doi, title, authors, date, category, license, and abstract for each preprint.

Do I need the requests library to query bioRxiv preprint data?

Yes, you need the requests library installed in your Python environment, as the skill relies on it to communicate with the bioRxiv API and retrieve preprint metadata.

What are the limitations of using bioRxiv API for literature reviews?

A limitation of using the bioRxiv API is that it only covers preprints hosted on bioRxiv, meaning it will not return peer-reviewed or published articles from other life sciences databases.