Biorxiv Openclaw Skill

What This Skill Does

The Biorxiv Openclaw skill, developed by aquaskyline, serves as a specialized gateway for researchers, students, and professionals to interface directly with the bioRxiv preprint repository. It abstracts the complexity of the official bioRxiv API into a streamlined command-line tool, enabling users to programmatically fetch, filter, and organize the latest preprints in the life sciences. Whether you are looking for groundbreaking discoveries in genomics or the latest computational methods in bioinformatics, this skill provides a structured way to access paper metadata, including titles, authors, DOIs, publication dates, and specific research categories. It eliminates the need for manual browser-based searching by allowing users to pull data directly into their workflows as structured JSON or plain text output.

Installation

To integrate this skill into your environment, use the OpenClaw command-line interface. Run the following command in your terminal:

clawhub install openclaw/skills/skills/aquaskyline/biorxiv-openclaw-skill

Ensure your OpenClaw environment is properly configured before running the installation command. Once installed, verify the installation by calling the help documentation to confirm the script path.

Use Cases

• Automated Literature Reviews: Use the tool in a script to pull the latest papers in your field every morning.
• Trend Analysis: Aggregate data across multiple categories like systems biology or synthetic biology to identify emerging research themes over a specific date range.
• Data Pipeline Integration: Pipe the --json output directly into secondary analysis tools or internal databases for citation management.
• Rapid Filtering: Quickly filter thousands of preprints to find relevant work based on specific categories like immunology or microbiology without navigating web interfaces.

Example Prompts

1. "OpenClaw, use the biorxiv skill to find the 10 most recent bioinformatics preprints from the last week and summarize the common themes."
2. "Search the genomics category for papers published between March 1st and March 5th, 2026, and export the metadata as a JSON file."
3. "Can you list all the available subject collections supported by the biorxiv skill and fetch three recent papers from the neuroscience category?"

Tips & Limitations

• Rate Limiting: While the API is public, ensure your scripts are well-behaved if automating repetitive pulls. The API returns up to 100 papers per request, so use the pagination/cursor logic for large datasets.
• Data Freshness: This tool accesses preprints; remember that these have not yet undergone peer review and should be cited as such.
• Collection Accuracy: Only use the officially supported categories listed in the documentation to ensure the API returns valid data.
• Network Dependency: As an API-based tool, you must have an active internet connection to fetch the latest data.