Query bioRxiv/medRxiv preprints via REST API. Search by DOI, category, or date range; retrieve metadata (title, abstract, authors, category, DOI, version history) and PDFs. No auth. For peer-reviewed biomedical use pubmed-database; broader scholarly search use openalex-database.
SkillScore100Maintained
Automatic
◆Research pack
Last verified 8/27/2026
What it changes
Passed 22 of 22 test cases with the skill, and 21 of 22 without it.
Without skill95%
With skill100%
Checks it passed that the model alone missed
uses the publisher path segment in the URL endpoint
1 fixed21 passed either way0 still failing0 broke
Pass-rate lift
+5 pp
Tokens
+369%
Agent turns
0%
Response time
-38%
Model gemini-3.6-flashMeasured 8/27/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
I want to verify if bioRxiv manuscript '10.1101/2024.05.28.596311' has a corresponding peer-reviewed journal article using the API. What REST endpoint path structure on api.biorxiv.org provides this check?
What was checked, without and with the skill
Checked
Without skill
With skill
uses the publisher path segment in the URL endpoint
Missed
Passed
case-07 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md516 linessingle file
bioRxiv / medRxiv Preprint Database
Overview
bioRxiv (biology) and medRxiv (health sciences) are free preprint servers hosting 200,000+ and 50,000+ manuscripts, respectively, before or alongside peer review. The unified REST API provides programmatic access to preprint metadata (title, abstract, authors, category, DOI, version history) without authentication. Preprints are available as PDF and can be retrieved by DOI, date range, or category.
When to Use
Finding the most current research in fast-moving fields before peer review (e.g., infectious disease during outbreaks)
Monitoring weekly preprint submissions in a specific discipline category (e.g., bioinformatics, genomics, neuroscience)
Retrieving metadata and abstracts for a set of bioRxiv DOIs for literature screening
Building a corpus of preprints to track the preprint-to-publication pipeline
Checking whether a specific preprint has been updated or published in a peer-reviewed journal
For peer-reviewed biomedical literature use pubmed-database; for all disciplines use openalex-database
Prerequisites
Python packages: requests, pandas
Data requirements: bioRxiv/medRxiv DOIs, date ranges, or category names
Environment: internet connection; no API key or authentication required
Rate limits: no stated hard limit; use reasonable delays for bulk queries
pip install requests pandas
Quick Start
import requests
BASE = "https://api.biorxiv.org"
# Retrieve recent bioinformatics preprints
r = requests.get(f"{BASE}/details/biorxiv/2024-01-01/2024-01-07/0",
params={"category": "bioinformatics"})
r.raise_for_status()
data = r.json()
print(f"Total preprints: {int(data['messages'][0]['total'])}") # API returns total as a string
for article in data["collection"][:3]: