A high-performance CLI skill for searching and retrieving biomedical literature and data from NCBI's PubMed database.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pubmed-edirect
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 pubmed-edirect 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 PubMed EDirect?
The PubMed EDirect skill integrates NCBI's powerful Entrez Direct utilities into your local environment, allowing your AI agent to perform complex queries across biomedical databases. It provides a suite of command-line tools that offer direct access to publications, gene sequences, and structures without needing a web browser. By using this tool within the ecosystem of Openclaw Skills, developers can automate literature reviews, data extraction, and cross-database linking efficiently.
This skill is designed for advanced users who require high-throughput access to the National Center for Biotechnology Information (NCBI) resources. It bypasses traditional web interfaces, enabling a pipeline-oriented approach to bioinformatics and medical research directly through a terminal-based agent.
PubMed EDirect Use Cases
- Searching for specific biomedical literature using advanced field qualifiers like [TIAB] or [AUTH].
- Fetching large batches of abstracts for systematic reviews or meta-analyses.
- Extracting structured data from NCBI XML responses for data science and machine learning workflows.
- Analyzing publication trends over specific time periods for research planning and competitive intelligence.
- Finding related records across different NCBI databases such as Gene, Protein, or PMC.
How PubMed EDirect Works
- The user or agent initiates a search query using the esearch utility to identify relevant records in a specific database like PubMed.
- Results are passed through Unix pipes to efilter to narrow down the selection based on specific criteria, such as publication dates or article types.
- The efetch tool retrieves the full record or specific subsets (like abstracts or metadata) in various formats including XML, text, or FASTA.
- The xtract utility parses the XML output to convert raw data into structured formats like tab-delimited text or CSV for easy analysis.
- Openclaw Skills leverage these CLI tools to automate complex research workflows and integrate publication data into larger AI-driven projects.
PubMed EDirect Setup
This skill requires manual installation of the EDirect suite from NCBI. Follow these steps to prepare your environment for Openclaw Skills integration:
# Step 1: Download the official installer script
wget -q https://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/install-edirect.sh
# Step 2: Review the script content for security purposes
less install-edirect.sh
# Step 3: Execute the installation
./install-edirect.sh
# Step 4: Verify the installation by running a test search
esearch -db pubmed -query "Openclaw Skills" -retmax 1
Optional: Set NCBI_API_KEY in your environment to increase rate limits to 10 requests per second.
PubMed EDirect Data Schema & Taxonomy
The skill processes and organizes data using a pipeline architecture. Below is how the data is structured during retrieval:
| Component | Description |
|---|---|
| Database | Target NCBI database (e.g., pubmed, pmc, gene, nuccore) |
| Query Syntax | Standard Entrez query format including field tags like [TIAB] and [DP] |
| Output Formats | XML (default), ASN.1, FASTA, or custom tabular via xtract parsing |
| Metadata | Includes PMIDs, publication dates, journal titles, and author lists |
| Scripts | Includes pre-built bash scripts for CSV export and trend analysis |
PubMed EDirect Advanced Features
- Support for NCBI API keys to increase rate limits from 3 to 10 requests per second for high-volume tasks.
- Pipeline-based architecture allowing for complex, multi-stage data processing via standard Unix pipes.
- Cross-database linking (elink) to find protein sequences or gene data related to specific research papers.
- Custom bash scripts included for batch fetching abstracts and generating publication trend visualizations.
- Deep integration with Openclaw Skills for creating automated research agents capable of autonomous literature discovery.
SKILL.md
Loading
Related Openclaw Skills
marp-cli
A versatile command-line utility that transforms Markdown documents into professional presentation decks across multiple formats.
arxiv-cli-tools
A streamlined command-line interface for rapid discovery and bulk downloading of scientific papers from arXiv.
aria2-rpc
A specialized interface for controlling aria2 download services remotely using the JSON-RPC 2.0 protocol.
apktool
A professional command-line utility for reverse engineering Android APK files, enabling developers to decode, modify, and rebuild applications.
Pyzotero CLI for Zotero Management
A powerful Python-based command-line interface for full lifecycle management of Zotero libraries using both local and cloud APIs.
Zotero CLI
A powerful command-line interface for Zotero that allows researchers to manage bibliographic references, read attachments, and sync notes directly from the terminal.
METADATA
Featured*
