A specialized research tool for fetching, filtering, and analyzing biology preprints from the official bioRxiv repository.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install biorxiv-openclaw-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install biorxiv-openclaw-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is bioRxiv Skill?
The bioRxiv skill is a powerful research integration designed to interface directly with the official bioRxiv API. It enables AI agents and developers to programmatically access a vast repository of biology preprints across numerous domains, including bioinformatics, genomics, and neuroscience. As part of the growing library of Openclaw Skills, this tool simplifies the process of staying updated with the latest scientific discoveries without requiring any authentication.
By leveraging this skill, users can automate the retrieval of high-quality metadata, such as paper titles, authors, DOIs, and publication dates. Whether you are building a discovery engine or a specialized research assistant, these Openclaw Skills provide the necessary connectivity to bridge the gap between AI-driven analysis and the cutting edge of biological research.
bioRxiv Skill Use Cases
- Monitoring recent preprints in specific biological categories like bioinformatics or microbiology.
- Automating literature reviews by fetching papers within specific date ranges.
- Extracting paper metadata including DOIs and author lists for citation management.
- Searching for specific topics across multiple subject collections simultaneously.
How bioRxiv Skill Works
- The user or AI agent triggers a request specifying a collection, limit, or date range.
- The skill constructs a request to the official bioRxiv API details endpoint.
- The API returns a structured payload containing metadata for up to 100 papers per call.
- The skill processes the response, applying filters for categories or specific keywords if requested.
- The final data is returned as a summarized list or raw JSON for further programmatic use.
bioRxiv Skill Setup
This skill is ready to use without API keys as bioRxiv provides a public API. To get started with these Openclaw Skills, run the following commands:
# List all available subject collections
python scripts/biorxiv.py --list
# Fetch the 10 most recent bioinformatics papers
python scripts/biorxiv.py --collection bioinformatics --limit 10
bioRxiv Skill Data Schema & Taxonomy
The skill returns structured metadata for each preprint. When using the JSON output mode, the data follows this taxonomy:
| Field | Description |
|---|---|
| title | The full title of the preprint |
| authors | A list of contributing researchers |
| doi | The Digital Object Identifier for the paper |
| date | The date the preprint was posted or updated |
| category | The specific subject collection (e.g., genomics) |
| server | The host server (always biorxiv for this skill) |
bioRxiv Skill Advanced Features
- Temporal filtering: Retrieve preprints published between specific start and end dates.
- JSON Export: Output results in machine-readable JSON format for integration into external data pipelines.
- Cursor-based navigation: Support for navigating large sets of results through the bioRxiv API cursor system.
- Multi-collection support: Ability to target any of the 19+ available subject collections from plant biology to biophysics.
SKILL.md
Loading
Related Openclaw Skills
Release Preflight
A pre-release safety and scope checker designed to prevent private data leakage and ensure repository readiness before sharing or publishing.
Jupiter
Jupiter is a high-precision decision routing engine designed to compute the optimal path when multiple competing choices create analysis paralysis.
MJZJ Supply and Demand Manager
A specialized AI agent skill for managing cross-border e-commerce supply and demand listings on the MJZJ platform via Openclaw Skills.
Tavily Best Practices
A comprehensive developer guide for building production-ready AI search, content extraction, and autonomous research agents using Tavily.
Map
A strategic logic mapping tool that transforms abstract business ambitions into structured, navigable paths.
Tool Call Retry
An automated retry and error correction engine designed to stabilize LLM tool calls and external API interactions.
Featured*
