A lightweight web collection utility for extracting structured data and monitoring site changes without a headless browser.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install data-scraper
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install data-scraper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Data Scraper is a powerful utility designed for efficient web data collection and structured text extraction. By utilizing curl-based parsing instead of heavy browser environments, it provides a fast and resource-efficient way to transform raw HTML into usable formats. As part of the Openclaw Skills ecosystem, this tool simplifies complex scraping tasks into straightforward CLI commands, making it ideal for developers and data analysts who need speed and reliability.
The tool excels at stripping away unnecessary boilerplate like scripts and styles, leaving behind clean, readable content. Whether you are performing market research or building a local knowledge base, Data Scraper provides the surgical precision needed to isolate specific data points from any public URL.
To begin using this skill within your environment, ensure you have the necessary permissions for network access. You can test the installation with the following commands:
# Fetch and clean text from a URL
data-scraper fetch "https://example.com"
# Extract specific data using CSS selectors
data-scraper extract "https://example.com" --selector ".price"
The skill manages data through a structured hierarchy to ensure portability and clarity:
| Component | Type | Description |
|---|---|---|
| Snapshots | File | Timestamped versions of pages stored in data-scraper/snapshots/ |
| Table Output | JSON | An array of objects where keys are derived from table headers |
| Batch Config | TXT | A simple list of URLs for sequential processing |
| Metadata | Object | Includes User-Agent strings, cookie data, and custom headers |
Loading
An automated sales aggregation and reporting skill for e-commerce platforms with multi-channel delivery.

An automated workflow for creating and preparing 5-slide Instagram-ready card news image sets from a single topic.

A professional AI agent skill for generating government funding plans, investor pitch decks, and technical infrastructure architecture.

A specialized tool for defining, managing, and applying consistent brand tones and writing styles across multiple AI-driven communication channels.

A professional decision-tracking skill that records rationales and automatically evaluates results after 30 days.

A comprehensive Git automation skill that streamlines status checks, smart commits, and safe pushes with intelligent defaults.








































