biorxiv-database

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

Updated Apr 1, 2026

Search Tags:#python #search #metadata #preprints #pdf-download #biorxiv #literature-review

Ready to run

npx skills add https://github.com/xiaoyu-ops/the_work_of_dedup --skill biorxiv-database-xiaoyu-ops

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: biorxiv-database
Source: https://github.com/xiaoyu-ops/the_work_of_dedup/tree/main/.claude/skills/biorxiv-database
Command: npx skills add https://github.com/xiaoyu-ops/the_work_of_dedup --skill biorxiv-database-xiaoyu-ops

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Researchers need to quickly locate, summarize, and obtain metadata for bioRxiv preprints to support literature reviews and knowledge discovery.

Core Features & Use Cases

Keyword-based search across dates and categories to surface relevant preprints.
Metadata retrieval including titles, authors, DOIs, abstracts, and category for integration with analysis pipelines.
PDF access: download full-text PDFs for offline reading and reproducible reviews.

Quick Start

Query bioRxiv for CRISPR papers from the last year and export the results to a JSON file.

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 ranges in Python?▼

Search bioRxiv preprints by supplying keywords, authors, and date ranges to filter results. The Skill queries the bioRxiv API and returns metadata including title, authors, DOI, abstract, and category for downstream analysis.

What metadata fields are included when retrieving bioRxiv paper details?▼

Retrieving bioRxiv metadata returns title, authors, date, DOI, abstract, and category. Results are structured in a consistent JSON-like format suitable for direct ingestion into data pipelines.

Can I download full-text PDFs from bioRxiv for offline literature reviews?▼

Yes, you can download full-text PDFs from bioRxiv for offline reading and reproducible reviews. The Skill provides PDF access alongside metadata retrieval to support complete literature exploration.

How does the Skill handle bioRxiv API rate limits and response errors?▼

The Skill ensures robust handling of bioRxiv API responses, rate limits, and errors. It processes API interactions automatically and returns consistent structures even when encountering rate constraints.

Do I need the requests library to run bioRxiv metadata searches?▼

Yes, the requests library is required as a dependency to run bioRxiv metadata searches. The Python environment must have requests installed to handle the API interactions and PDF downloads.

What's the best way to export bioRxiv search results to a JSON file?▼

Export bioRxiv search results to a JSON file by querying the API with your desired filters. The Skill returns a consistent JSON-like structure that can be directly saved for data pipeline ingestion and analysis.