Preprint Search on bioRxiv

What it does

When your agent uses it

• Finding recent preprints on a research topic
• Tracking new preprints from a particular author
• Collecting bioRxiv metadata for a literature review or citation list
• Downloading preprint PDFs for full-text analysis
• Filtering preprints by bioRxiv subject category

Example prompts

• “Search bioRxiv for CRISPR and gene editing preprints posted since January and list titles and DOIs.”
• “Find preprints on neural networks and deep learning from this year and save the metadata as JSON.”
• “Which preprints did this author post recently? Give me titles and abstracts.”

Requirements

• Python 3
• Network access to the bioRxiv API

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Keyword Search
2. 2Author Search
3. 3Date Range Search
4. 4Paper Details by DOI
5. 5PDF Downloads

What it can do on your machine

Read from SKILL.md and the folder at commit 6baece9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • biorxiv.org
  • doi.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Preprint Search on bioRxiv loads about 3.7k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 19 tokens; SKILL.md has 808 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~19

When it runs · the whole SKILL.md, loaded when a task matches

~3.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LigphiDonk/Oh-my--paper at commit 6baece9, republished under its MIT licence (© LigphiDonk). 808 words, ~3,668 tokens.

name

biorxiv-database

description

Efficient database search tool for bioRxiv preprint server.

id

biorxiv-database

version

1.0.0

stages

survey, ideation, experiment

tools

read_file, search_project, write_file, run_terminal

summary

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or…

primaryIntent

research

intents

research, data

capabilities

search-retrieval, data-processing

domains

bioinformatics

keywords

biorxiv-database, resource prep, search-retrieval, data-processing, bioinformatics, biorxiv, database, efficient, search, tool, preprint, server

python scripts/biorxiv_search.py \
  --keywords "CRISPR" "gene editing" \
  --start-date 2024-01-01 \
  --end-date 2024-12-31 \
  --output results.json

python scripts/biorxiv_search.py \
  --keywords "neural networks" "deep learning" \
  --days-back 180 \
  --category neuroscience \
  --output recent_neuroscience.json

python scripts/biorxiv_search.py \
  --keywords "AlphaFold" \
  --search-fields title \
  --days-back 365

python scripts/biorxiv_search.py \
  --author "Smith" \
  --start-date 2023-01-01 \
  --end-date 2024-12-31 \
  --output smith_papers.json

# Last year by default if no dates specified
python scripts/biorxiv_search.py \
  --author "Johnson" \
  --output johnson_recent.json

python scripts/biorxiv_search.py \
  --start-date 2024-01-01 \
  --end-date 2024-01-31 \
  --output january_2024.json

python scripts/biorxiv_search.py \
  --start-date 2024-06-01 \
  --end-date 2024-06-30 \
  --category genomics \
  --output genomics_june.json

# Last 30 days
python scripts/biorxiv_search.py \
  --days-back 30 \
  --output last_month.json

python scripts/biorxiv_search.py \
  --doi "10.1101/2024.01.15.123456" \
  --output paper_details.json

python scripts/biorxiv_search.py \
  --doi "https://doi.org/10.1101/2024.01.15.123456"

python scripts/biorxiv_search.py \
  --doi "10.1101/2024.01.15.123456" \
  --download-pdf paper.pdf

import json
from biorxiv_search import BioRxivSearcher

# Load search results
with open('results.json') as f:
    data = json.load(f)

searcher = BioRxivSearcher(verbose=True)

# Download each paper
for i, paper in enumerate(data['results'][:10]):  # First 10 papers
    doi = paper['doi']
    searcher.download_pdf(doi, f"papers/paper_{i+1}.pdf")

{
  "query": {
    "keywords": ["CRISPR"],
    "start_date": "2024-01-01",
    "end_date": "2024-12-31",
    "category": "genomics"
  },
  "result_count": 42,
  "results": [
    {
      "doi": "10.1101/2024.01.15.123456",
      "title": "Paper Title Here",
      "authors": "Smith J, Doe J, Johnson A",
      "author_corresponding": "Smith J",
      "author_corresponding_institution": "University Example",
      "date": "2024-01-15",
      "version": "1",
      "type": "new results",
      "license": "cc_by",
      "category": "genomics",
      "abstract": "Full abstract text...",
      "pdf_url": "https://www.biorxiv.org/content/10.1101/2024.01.15.123456v1.full.pdf",
      "html_url": "https://www.biorxiv.org/content/10.1101/2024.01.15.123456v1",
      "jatsxml": "https://www.biorxiv.org/content/...",
      "published": ""
    }
  ]
}

python scripts/biorxiv_search.py \
  --keywords "organoids" "tissue engineering" \
  --start-date 2023-01-01 \
  --end-date 2024-12-31 \
  --category bioengineering \
  --output organoid_papers.json

import json

with open('organoid_papers.json') as f:
    data = json.load(f)

print(f"Found {data['result_count']} papers")

for paper in data['results'][:5]:
    print(f"\nTitle: {paper['title']}")
    print(f"Authors: {paper['authors']}")
    print(f"Date: {paper['date']}")
    print(f"DOI: {paper['doi']}")

from biorxiv_search import BioRxivSearcher

searcher = BioRxivSearcher()
selected_dois = ["10.1101/2024.01.15.123456", "10.1101/2024.02.20.789012"]

for doi in selected_dois:
    filename = doi.replace("/", "_").replace(".", "_") + ".pdf"
    searcher.download_pdf(doi, f"papers/{filename}")

python scripts/biorxiv_search.py \
  --keywords "machine learning" \
  --start-date 2020-01-01 \
  --end-date 2024-12-31 \
  --category bioinformatics \
  --output ml_trends.json

# Track multiple authors
authors = ["Smith", "Johnson", "Williams"]

for author in authors:
    python scripts/biorxiv_search.py \
      --author "{author}" \
      --days-back 365 \
      --output "{author}_papers.json"

from scripts.biorxiv_search import BioRxivSearcher

# Initialize
searcher = BioRxivSearcher(verbose=True)

# Multiple search operations
keywords_papers = searcher.search_by_keywords(
    keywords=["CRISPR", "gene editing"],
    start_date="2024-01-01",
    end_date="2024-12-31",
    category="genomics"
)

author_papers = searcher.search_by_author(
    author_name="Smith",
    start_date="2023-01-01",
    end_date="2024-12-31"
)

# Get specific paper details
paper = searcher.get_paper_details("10.1101/2024.01.15.123456")

# Download PDF
success = searcher.download_pdf(
    doi="10.1101/2024.01.15.123456",
    output_path="paper.pdf"
)

# Format results consistently
formatted = searcher.format_result(paper, include_abstract=True)

from datetime import datetime, timedelta

# Last quarter
end_date = datetime.now()
start_date = end_date - timedelta(days=90)

python scripts/biorxiv_search.py \
  --start-date {start_date.strftime('%Y-%m-%d')} \
  --end-date {end_date.strftime('%Y-%m-%d')}

python scripts/biorxiv_search.py \
  --keywords "COVID-19" \
  --days-back 30 \
  --limit 50 \
  --output covid_top50.json

# Note: Abstract inclusion is controlled in Python API
from scripts.biorxiv_search import BioRxivSearcher

searcher = BioRxivSearcher()
papers = searcher.search_by_keywords(keywords=["AI"], days_back=30)
formatted = [searcher.format_result(p, include_abstract=False) for p in papers]

import json
import pandas as pd

# Load results
with open('results.json') as f:
    data = json.load(f)

# Convert to DataFrame for analysis
df = pd.DataFrame(data['results'])

# Analyze
print(f"Total papers: {len(df)}")
print(f"Date range: {df['date'].min()} to {df['date'].max()}")
print(f"\nTop authors by paper count:")
print(df['authors'].str.split(',').explode().str.strip().value_counts().head(10))

# Filter and export
recent = df[df['date'] >= '2024-06-01']
recent.to_csv('recent_papers.csv', index=False)

uv pip install requests

python tests/test_biorxiv_search.py

🧬 bioRxiv Database Search Skill Test Suite
======================================================================

🧪 Test 1: Initialization
✅ BioRxivSearcher initialized successfully

🧪 Test 2: Date Range Search
✅ Found 150 papers between 2024-01-01 and 2024-01-07
   First paper: Novel CRISPR-based approach for genome editing...

[... additional tests ...]

======================================================================
📊 Test Summary
======================================================================
✅ PASS: Initialization
✅ PASS: Date Range Search
✅ PASS: Category Filtering
✅ PASS: Keyword Search
✅ PASS: DOI Lookup
✅ PASS: Result Formatting
✅ PASS: Interval Search
======================================================================
Results: 7/7 tests passed (100%)
======================================================================

🎉 All tests passed! The bioRxiv database skill is working correctly.

© LigphiDonk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in skills/biorxiv-database of LigphiDonk/Oh-my--paper.

• SKILL.md
• references/api_reference.md
• scripts/biorxiv_search.py

Open the folder on GitHubat commit 6baece9

Used in 12 other repositories

We found 20 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 12 other GitHub owners. This page covers the copy in LigphiDonk/Oh-my--paper, which our catalogue first saw on October 7, 2026.

• davila7/claude-code-templatescli-tool/components/skills/scientific/biorxiv-database
• jimmc414/Kosmoskosmos-claude-scientific-skills/scientific-skills/biorxiv-database
• Microck/ordinary-claude-skillsskills_all/biorxiv-databaseskills_categorized/academic/biorxiv-database+5 more
• aiskillstore/marketplaceskills/davila7/biorxiv-databaseskills/k-dense-ai/biorxiv-database
• lamm-mit/scienceclawskills/biorxiv-database
• agent-skills-hub/agent-skills-hubskills/biorxiv-database
• OpenLAIR/dr-clawskills/biorxiv-database
• LeonChaoX/qinyan-academic-skillsskills/01-论文检索与文献管理/biorxiv-database
• wu-yc/LabClawskills/literature/biorxiv-database
• FreedomIntelligence/OpenClaw-Medical-Skillsskills/biorxiv-database
• BioTender-max/awesome-bio-agent-skillsskills/labclaw/biorxiv-database
• infometa/workbuddyskillsplugins/codebuddy-plugins-official/external_plugins/scientific-skills/biorxiv-database