literature-search-biorxiv

Search and fetch bioRxiv and medRxiv preprint metadata by DOI or date range.

1|Updated Mar 7, 2025
One-click install
npx skills add https://github.com/carmonalab/ECODA_paper --skill literature-search-biorxiv-carmonalab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: literature-search-biorxiv
Source: https://github.com/carmonalab/ECODA_paper/tree/main/.agents/skills/literature_search_biorxiv
Command: npx skills add https://github.com/carmonalab/ECODA_paper --skill literature-search-biorxiv-carmonalab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires polite-http, and includes scripts (resource) components.

What problem does it solve? Finding and retrieving life sciences preprints from bioRxiv and medRxiv requires navigating a date-based API that lacks server-side keyword search, making manual discovery slow and error-prone. ## Core Features & Use Cases - DOI Metadata Lookup: Fetch complete JSON metadata for a specific paper directly via its DOI using search_by_doi.py. - Date-Range Browsing with Filters: Browse preprints within a 1-4 week window, filtered locally by category, keywords, or author using search_by_dates.py. - Rate-Limited API Access: Scripts enforce polite cross-process rate limiting and automatic pagination across all result pages. - Use Case: A researcher knows a preprint's DOI from a citation and needs its full metadata and abstract; they fetch it instantly with the DOI script instead of browsing the archive. ## Quick Start Use the bioRxiv literature search skill to fetch the metadata and abstract for the preprint with DOI 10.1101/2023.08.15.551388.

Frequently Asked Questions about literature-search-biorxiv

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

FAQPage Schema
How do I search bioRxiv for papers by keyword?▼

Use search_by_dates.py with a narrow date range of 1-4 weeks, a --category filter, and --keywords. The bioRxiv API has no server-side keyword search, so the script downloads all metadata in the range and filters locally.

How do I fetch bioRxiv paper metadata by DOI?▼

Run search_by_doi.py with the --doi argument and optionally --include_abstracts. This is the most reliable entry point and returns the paper's full JSON metadata directly from the bioRxiv API.

Can I download bioRxiv full-text PDFs with this skill?▼

No, this skill only retrieves metadata. To download full-text PDFs, use the EuropePMC skill: look up the paper's PMCID via its DOI, then retrieve the PDF through EuropePMC.

Why does a broad bioRxiv date range search fail or time out?▼

The bioRxiv API does not support server-side keyword filtering, so scripts must download all metadata for the entire range and filter locally. Broad ranges cause thousands of API calls, timeouts, and potential rate-limit blocking.

Does the bioRxiv search include abstracts in results?▼

Abstracts are stripped from JSON output by default to save context space. Pass the --include_abstracts flag to search_by_dates.py or search_by_doi.py to include full abstracts in the results.