domains / research / biorxiv-preprint-search / biorxiv-database

biorxiv-database

Skill card

combined

Both copies describe the same bioRxiv search/download skill, but they disagree on the CLI surface and add different material capabilities. The aipoch copy documents a minimal BioRxivSearcher API and a simple CLI (keyword + days_back), while the FreedomIntelligence copy documents a richer CLI with --keywords, --author, --start-date, --end-date, --category, --doi, --download-pdf, --search-fields, and --output, plus a full JSON output schema and a list of valid categories. Crowning one copy would hide the other's real workflow options, so the catalog should combine them and flag the CLI conflict.

Repositories

Other copies

Combined skill

---
name: biorxiv-database
description: Search, retrieve metadata, and download PDFs for bioRxiv preprints; use when you need to discover biology preprints by keywords, authors, date ranges, or categories and programmatically fetch their details.
license: MIT
---

## When to Use

- Find recent bioRxiv preprints for a topic within a time window.
- Track publications by specific authors.
- Conduct systematic literature reviews or trend analysis.
- Retrieve structured metadata (title, abstract, DOI, authors, category, dates) for downstream analysis.
- Download full-text PDFs for preprints identified by DOI.
- Filter by bioRxiv subject categories.

## Dependencies

- Python 3.8+
- `requests>=2.25.0`

## Core Capabilities

- Keyword search with configurable lookback window or explicit date range.
- Author search within a date range.
- Date-range search with optional category filter.
- Paper details retrieval by DOI.
- PDF download by DOI to a local file path.
- Category filtering using valid bioRxiv subject categories.
- Structured JSON output with query metadata and result list.

## CLI Usage

### Keyword Search

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

### Keyword Search with Lookback and Category

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

### Author Search

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

### Date Range Search

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

### Paper Details by DOI

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

### PDF Download

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

## Python API

```python
from scripts.biorxiv_search import BioRxivSearcher

searcher = BioRxivSearcher()

# Search by keywords with lookback window
papers = searcher.search_by_keywords(["CRISPR"], days_back=30)

# Download PDF by DOI
if papers:
    searcher.download_pdf(papers[0]["doi"], "paper.pdf")
```

## Valid Categories

- animal-behavior-and-cognition
- biochemistry
- bioengineering
- bioinformatics
- biophysics
- cancer-biology
- cell-biology
- clinical-trials
- developmental-biology
- ecology
- epidemiology
- evolutionary-biology
- genetics
- genomics
- immunology
- microbiology
- molecular-biology
- neuroscience
- paleontology
- pathology
- pharmacology-and-toxicology
- physiology
- plant-biology
- scientific-communication-and-education
- synthetic-biology
- systems-biology
- zoology

## Output Format

All searches return structured JSON:

```json
{
  "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": ""
    }
  ]
}
```

## Recommended Workflow

1. Validate the request and confirm all required inputs (keywords, author, DOI, dates, category) are present.
2. Select the appropriate search mode (keyword, author, date range, DOI).
3. Execute the search and save results to a JSON file.
4. Review results and extract DOIs for PDF downloads if needed.
5. Download PDFs using the DOI and output path.
6. Run a final validation pass for completeness and consistency.

## Validation and Safety Rules

- Validate required inputs before execution and stop early when mandatory fields are missing.
- Do not fabricate results, references, or conclusions not supported by the API response.
- Emit a clear warning when credentials, privacy constraints, or unsupported requests affect the result.
- Keep output safe, reproducible, and within the documented scope.

## Failure Handling

- If validation fails, explain the exact missing field or parameter and show the minimum fix.
- If an external dependency or script fails, surface the command path, likely cause, and next recovery step.
- If partial output is returned, label it clearly and identify which checks could not be completed.

## Quick Validation

```bash
python scripts/biorxiv_search.py --help
```

## Conflicts

- aipoch/medical-research-skills documents a positional CLI (`python scripts/biorxiv_search.py "CRISPR" 30`), while FreedomIntelligence/OpenClaw-Medical-Skills documents a flag-based CLI (`--keywords`, `--days-back`, `--start-date`, `--end-date`, `--category`, `--doi`, `--download-pdf`, `--search-fields`, `--output`). Use the flag-based CLI as the primary interface; the positional form may be a legacy or simplified wrapper.
- aipoch/medical-research-skills does not document author search, category filtering, date-range flags, or a JSON output schema, while FreedomIntelligence/OpenClaw-Medical-Skills documents all of these. The combined skill includes all documented capabilities.