biorxiv-database

Queries bioRxiv and medXxiv preprint servers REST API for metadata and PDFs.

298|27|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill biorxiv-database-jaechang-hits
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: biorxiv-database
Source: https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/biorxiv-database
Command: npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill biorxiv-database-jaechang-hits

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides programmatic access to the latest research preprints from bioRxiv and medRxiv, enabling users to stay ahead of peer-reviewed publications.

Core Features & Use Cases

  • Search Preprints: Query by date range, category, or DOI.
  • Retrieve Metadata: Get titles, abstracts, authors, categories, and version history.
  • Check Publication Status: Determine if a preprint has been published in a journal.
  • Use Case: A researcher needs to find the most recent studies on a specific gene therapy before it appears in a journal. They can use this Skill to search bioRxiv for relevant preprints published in the last week.

Quick Start

Find the latest preprints in the 'genomics' category from the past 3 days.

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 and medRxiv preprints by date or category?

You can retrieve bioRxiv and medRxiv preprint metadata by querying the REST API with a date range, category, or DOI. This Skill returns titles, abstracts, authors, and version history for matching biology and health science preprints.

Can I check if a bioRxiv preprint has been published in a peer-reviewed journal?

Yes, this Skill checks the publication status of bioRxiv and medRxiv preprints against peer-reviewed journals. It queries the REST API to determine if a preprint has been formally published in a journal.

What Python libraries do I need to retrieve bioRxiv full-text PDFs and metadata?

You need the Python `requests` and `pandas` libraries to retrieve bioRxiv and medRxiv preprint metadata and PDFs. `requests` handles API interactions while `pandas` structures the data for handling.

How do I find the most recent research preprints in a specific biology category?

To find recent biology preprints, query the bioRxiv API by date range and specific category like genomics. This retrieves the latest preprint metadata, helping you discover research before formal peer-reviewed publication.

Does the bioRxiv API allow searching for preprints using a DOI?

Yes, searching bioRxiv and medRxiv preprints by DOI is fully supported. This Skill queries the REST API with a specific DOI to retrieve the corresponding preprint metadata, full-text PDFs, and publication status.

What limitations exist when using a REST API for scientific preprint discovery?

Using this REST API approach for preprint discovery requires Python programming knowledge and the `requests` and `pandas` libraries. It focuses on retrieving bioRxiv and medRxiv metadata programmatically rather than providing a visual search interface.