biorxiv-database

Search bioRxiv preprints by keywords, authors, dates, and categories, returning structured JSON metadata.

1.0k|117|Updated Feb 26, 2026

Search Tags:#search #metadata #download #literature #preprints #biorxiv

Ready to run

npx skills add https://github.com/OpenLAIR/dr-claw --skill biorxiv-database-openlair

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: biorxiv-database
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/biorxiv-database
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill biorxiv-database-openlair

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Researchers often struggle to efficiently locate, filter, and retrieve metadata from bioRxiv preprints. This skill centralizes the workflow by enabling keyword, author, date-range, and category searches and returns structured JSON with titles, abstracts, DOIs, and citation-ready information. It also supports PDF downloads for full-text analysis when needed.

Core Features & Use Cases

Keyword and author searches across title and abstract to identify relevant papers.
Date-range and category filtering to narrow results and support literature reviews.
Retrieve detailed paper metadata by DOI and download PDFs for downstream analysis.

Quick Start

Invoke the bioRxiv database tool to search by keywords, authors, or dates and obtain a structured result set.

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 by keyword, author, or date range in Python?▼

You can search bioRxiv preprints by keyword, author, and date range using Python workflows that query the bioRxiv database and return structured JSON metadata including titles, abstracts, and DOIs. Category filtering is also supported to narrow results.

Can I download bioRxiv preprint PDFs for full-text analysis?▼

Yes, you can download bioRxiv preprint PDFs for full-text analysis. The skill provides a robust interface to fetch paper details by DOI and retrieve PDF files directly within your Python scripts for downstream processing.

What metadata fields are returned when retrieving bioRxiv preprint details by DOI?▼

Retrieving bioRxiv preprint details by DOI returns structured JSON with citation-ready information. This includes paper titles, abstracts, DOIs, and other consistent metadata fields formatted for immediate use in literature reviews.

Does searching bioRxiv preprints require managing API rate limits manually?▼

No, manual rate limit management is not required. The skill handles rate-limited requests automatically, providing a robust interface that ensures consistent result formatting and prevents API throttling during bioRxiv metadata retrieval.

What is the best way to filter bioRxiv literature search results by category?▼

The best way to filter bioRxiv literature search results is by using the built-in category filtering feature. This allows you to narrow keyword and author searches to specific bioRxiv categories, returning structured metadata for targeted literature reviews.

Do I need the requests library to run bioRxiv metadata searches in my Python workflow?▼

Yes, the requests library is required. It serves as the dependency for making rate-limited requests to the bioRxiv database, enabling you to execute searches and retrieve structured metadata within your Python scripts.