GhostFetch - OpenClaw Skill — OpenClaw Tutorials

Install Command

npx clawhub@latest install ghostfetch

Installation Guide

Check Environment

Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.

Run Installation

Run the install command above in your terminal. ClawHub will automatically download and install GhostFetch to the ~/.openclaw/skills/ directory.

Verify Installation

Run openclaw skills list to check your installed skills and confirm GhostFetch appears in the list.

Configure (Optional)

Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.

Manual Installation: Copy the Skill folder to ~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.

Lightweight Scraping Markdown Output Batch Processing

Detailed Description

GhostFetch is a lightweight web content extraction skill that is faster and more resource-efficient than full browser automation, ideal for scenarios requiring bulk webpage body text extraction.

Core Features

Body Text Extraction: Automatically identifies the main content area of a webpage, removing ads, navigation, and other distractions
Markdown Output: Converts webpage content into clean Markdown format
Batch Scraping: Pass in multiple URLs at once for parallel scraping
Metadata Extraction: Extracts title, description, author, publication date, and other metadata
Lightweight and Efficient: Based on HTTP requests rather than a browser, offering fast speed and low resource usage

Configuration

{
  skills: {
    ghostfetch: {
      timeout: 10000,
      maxConcurrent: 5,
      userAgent: "OpenClaw/1.0",
      extractImages: false
    }
  }
}

Use Cases

Quickly read webpage article content (for pages that don't require JS rendering)
Batch collect information from multiple webpages for summary analysis
Provide webpage content input for RAG systems
Build an article knowledge base

Difference from Agent Browser

GhostFetch is based on HTTP requests — it's fast but cannot handle pages that require JavaScript rendering. If the target page is a single-page application (SPA) or requires login, use Agent Browser instead.

← Back to Skills List