A specialized utility for searching and harvesting full-text scientific articles and metadata from PubMed Central using official NCBI APIs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pmc-harvest
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 pmc-harvest 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 PMC Harvest?
PMC Harvest is a technical utility designed to bridge the gap between scientific literature and AI workflows. It enables developers to programmatically access the vast repository of PubMed Central (PMC) using official NCBI E-utilities and OAI-PMH interfaces. This skill is essential for anyone looking to expand their Openclaw Skills library with robust capabilities for medical research and automated data collection.
The tool excels at handling the nuances of biomedical data, providing built-in support for JATS XML parsing and batch processing. Whether you need to search for specific journals, retrieve abstracts for lightweight review, or harvest full-text open-access articles for complex analysis, PMC Harvest provides a streamlined interface for both CLI and programmatic use.
PMC Harvest Use Cases
- Building high-quality, domain-specific datasets for medical RAG pipelines.
- Automating systematic literature reviews by programmatically fetching abstracts and metadata.
- Monitoring specific biomedical journals for new publications based on search criteria.
- Batch harvesting open-access full-text articles for large-scale data analytics and NLP tasks.
How PMC Harvest Works
- The user provides a search query, a specific journal name, or a list of PMCIDs via the command line or API.
- The skill connects to NCBI E-utilities to resolve search queries and identify target article IDs.
- Metadata is retrieved through the esummary service to provide quick overviews of the found literature.
- For full-text requests, the skill utilizes the OAI-PMH endpoint to fetch complete XML records for open-access articles.
- The JATS XML is parsed into structured formats, extracting the title, abstract, and body text for use within other Openclaw Skills workflows.
PMC Harvest Setup
To integrate this tool into your Openclaw Skills environment, ensure you have Node.js installed and follow these steps:
# Clone and enter the skill directory
cd pmc-harvest
# Install required dependencies
npm install
# Run a test to verify connectivity with NCBI APIs
node scripts/pmc-harvest.js --test
PMC Harvest Data Schema & Taxonomy
The skill organizes retrieved biomedical data into a structured taxonomy for easy integration:
| Data Type | Description | Structure |
|---|---|---|
| Search Results | List of PMCIDs matching the query | Array of Strings |
| Article Metadata | Basic info like title, authors, and year | JSON Object |
| Full Text Content | The complete article body and section headers | Parsed JATS XML |
| Journal Config | List of journals for batch harvesting | JSON File |
PMC Harvest Advanced Features
- Programmatic API support allowing for custom integration into broader Node.js applications and Openclaw Skills.
- Batch harvesting mode for processing multiple journals simultaneously via JSON configuration.
- Built-in JATS XML parser that simplifies complex scientific document structures into clean, usable text.
- Rate-limit management to ensure compliance with NCBI public API guidelines without requiring an API key.
SKILL.md
Loading
Related Openclaw Skills
Mealie
A powerful API client for Mealie that lets you manage recipes, meal plans, and shopping lists through AI-driven workflows.
Crawl4AI Web Scraper
A powerful web scraping skill for AI agents that leverages local Crawl4AI instances to extract full-page content with JavaScript rendering.
Cozi Family Organizer
A powerful integration that allows AI agents to interact directly with the Cozi Family Organizer for managing shared schedules and lists.
Agent Earth
Agent Earth allows AI agents to perform virtual city walks by researching landmarks, generating rich waypoint data, and publishing results to a global platform.
Ragflow API Client
A universal API client for managing knowledge bases and performing Retrieval-Augmented Generation (RAG) within self-hosted Ragflow instances.
Stirling-PDF
A comprehensive self-hosted PDF manipulation suite providing over 60 tools for document processing via a robust REST API.