biorxiv-database

Search bioRxiv preprints, extract metadata, and download PDFs via API.

Updated May 10, 2026

Search Tags:#metadata #systematic review #literature search #preprints #biorxiv #pdf download #scientific research

Ready to run

npx skills add https://github.com/Imad-Oute/ResearchForge --skill biorxiv-database-imad-oute

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: biorxiv-database
Source: https://github.com/Imad-Oute/ResearchForge/tree/main/OpenSource-Projects/claude-scientific-skills/scientific-skills/biorxiv-database
Command: npx skills add https://github.com/Imad-Oute/ResearchForge --skill biorxiv-database-imad-oute

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables efficient access to bioRxiv preprint metadata, facilitating rapid literature searches and data collection.

Core Features & Use Cases

Preprint Searching: Find recent papers by keywords, authors, categories, or date ranges.
Metadata Retrieval: Obtain detailed information such as titles, abstracts, DOIs, publication dates, and license types.
PDF Downloading: Retrieve full-text PDFs of preprints for in-depth analysis.
Use Case: A researcher wants to gather all recent neurobiology preprints mentioning CRISPR within a specified period and download selected PDFs for review.

Quick Start

Use the bioRxiv database skill to search for papers about COVID-19 in the last month and download the first PDF.

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 keywords and date range for a systematic review?▼

Search bioRxiv preprints by using scripted access to query keywords, authors, categories, or date ranges. This retrieves matching preprint metadata, including titles, abstracts, and DOIs, to support rapid literature searches for systematic reviews.

Can I download bioRxiv preprint PDFs automatically along with their metadata?▼

Yes, you can download bioRxiv preprint PDFs automatically. The skill retrieves full-text PDFs alongside detailed metadata like publication dates and license types, enabling in-depth analysis and local data collection for research workflows.

What is needed to retrieve bioRxiv preprint metadata using API endpoints?▼

Retrieving bioRxiv preprint metadata requires the Python requests library for HTTP operations. The skill utilizes bioRxiv API endpoints and local scripting to perform automated metadata extraction and search workflows.

How do I extract bioRxiv metadata like DOIs and abstracts for trend analysis?▼

Extract bioRxiv metadata by running local scripts that interact with bioRxiv API endpoints. This process obtains detailed information such as titles, abstracts, DOIs, and publication dates, directly supporting trend analysis and data collection.

Are there limitations when using scripted bioRxiv API access for literature searches?▼

Scripted bioRxiv API access depends on the requests library for HTTP operations and is constrained by API rate limits. It is designed for retrieving preprint metadata and PDFs, not for accessing peer-reviewed published journal articles.

Does this bioRxiv database skill support filtering preprints by specific categories?▼

Yes, the bioRxiv database skill supports filtering preprints by specific categories. You can find recent papers by keywords, authors, categories, or date ranges to gather targeted datasets for research.