A high-performance extraction tool that converts web articles into clean, readable Markdown using the Diffbot Article API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install diffbot-fetch
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 diffbot-fetch 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 Diffbot Fetch?
Diffbot Fetch is a specialized utility within the Openclaw Skills ecosystem designed to bypass web clutter and extract the signal from the noise. By leveraging the Diffbot Article API, this skill identifies the primary content of any webpage—be it a blog post, news report, or long-form essay—and strips away intrusive ads, navigation menus, and sidebars. The result is a structured, clean Markdown output that is perfectly formatted for AI consumption or archival purposes.
Diffbot Fetch Use Cases
- Extracting clean text from news articles for automated summarization.
- Scraping blog posts to build local knowledge bases or RAG systems.
- Converting cluttered web pages into readable Markdown for offline consumption.
- Gathering research data without the overhead of HTML boilerplate.
How Diffbot Fetch Works
- The user provides a target URL to the Diffbot Fetch skill via the CLI or agent interface.
- The skill sends a request to the Diffbot Article API using the configured API token.
- Diffbot's computer vision and NLP models analyze the page to identify the core article body.
- The raw extraction is processed and converted into a clean Markdown format.
- The finalized content is returned to the user or the calling Openclaw Skills agent for further processing.
Diffbot Fetch Setup
To get started with this entry in the Openclaw Skills library, ensure you have a valid Diffbot API token. Configure your environment as follows:
# Set your Diffbot API Key
export DIFFBOT_API_KEY="your_token_here"
# Run the fetch command
uv run fetch.py "https://example.com/article"
Diffbot Fetch Data Schema & Taxonomy
The skill focuses on a streamlined output schema to ensure compatibility with other Openclaw Skills.
| Field | Type | Description |
|---|---|---|
| Source URL | String | The original link provided for extraction. |
| Content | Markdown | The primary article body stripped of HTML tags. |
| Metadata | Object | Includes available author info, date, and title where applicable. |
Diffbot Fetch Advanced Features
- Intelligent identification of multi-page articles for comprehensive extraction.
- Automatic conversion of HTML tables and lists into standard Markdown syntax.
- Seamless integration with other Openclaw Skills for automated content pipelines.
- High-accuracy extraction powered by Diffbot's proprietary machine learning models.
SKILL.md
Loading
Related Openclaw Skills
Whisky Encyclopedia Guide
A comprehensive AI-driven encyclopedia for exploring whisky regions, distilleries, tasting notes, and market trends.
Agent Commerce
Agent Commerce is a foundational protocol layer that enables AI agents to communicate with merchant systems for product search, price negotiation, and order fulfillment.
Aliyun Image Generator
A powerful AI skill that leverages Alibaba Cloud's Tongyi Wanxiang to generate high-quality images directly through an AI agent workflow.
Ride Insights
A privacy-first mobility intelligence tool for extracting, analyzing, and anonymizing ride-sharing data from major providers.
Spring Fountain Revival
A robust memory survival and triple-layer backup system designed to ensure AI agent interaction data never disappears.
Memory System
A comprehensive memory architecture for AI agents featuring tiered storage, semantic vector search, and automated memory consolidation.
Featured*
