A powerful content extraction tool that converts complex web pages into clean, AI-ready markdown using the Jina Reader API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install haibo-jina-reader
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 haibo-jina-reader 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 Jina Reader Content Extractor?
The jina-reader skill is a specialized tool designed to bridge the gap between complex web architecture and AI processing. By utilizing the Jina Reader API, this Openclaw Skills component strips away HTML boilerplate, JavaScript noise, and even certain paywalls to deliver structured markdown content. It is an essential asset for developers building research-heavy workflows or AI agents that need to consume web content reliably without the overhead of manual scraping.
This skill ensures that your AI agents receive high-quality, readable text along with critical metadata like titles and publication dates. It integrates seamlessly with existing Openclaw Skills to provide a robust foundation for automated content analysis and information retrieval. Whether you are dealing with single articles or batch processing multiple sources, this skill provides the clean data required for high-accuracy LLM performance.
Jina Reader Content Extractor Use Cases
- Summarizing long-form articles or blog posts without HTML clutter.
- Processing search engine results from other Openclaw Skills into structured data.
- Conducting automated research and data gathering for technical documentation.
- Building content analysis pipelines that require clean text input from various web sources.
- Bypassing rendering issues on modern JavaScript-heavy websites for faster data extraction.
How Jina Reader Content Extractor Works
- The user or agent provides a target URL to the script provided by the Openclaw Skills suite.
- The skill sends a request to the Jina Reader API, which handles page rendering and content extraction.
- The API processes the page to remove ads, navigation menus, and non-essential HTML elements.
- The skill receives the processed markdown content and associated metadata such as title and timestamp.
- Depending on the requested format, the data is returned as raw markdown or a structured JSON object for further processing within the ecosystem of Openclaw Skills.
Jina Reader Content Extractor Setup
To get started with this skill within your environment, ensure you have the necessary scripts in your directory.
# Make the scripts executable
chmod +x scripts/jina-reader.py scripts/jina-reader.sh
# Basic usage to verify installation
scripts/jina-reader.sh https://example.com
Ensure your environment is configured to allow outbound requests to the Jina Reader API. No complex API keys are required for basic usage as this skill leverages standard Openclaw Skills patterns.
Jina Reader Content Extractor Data Schema & Taxonomy
The skill organizes data into structured formats to ensure compatibility with other Openclaw Skills.
| Field | Type | Description |
|---|---|---|
| status | String | Indicates success or failure of the extraction. |
| metadata.title | String | The extracted title of the webpage. |
| metadata.url | String | The original source URL. |
| metadata.published | String | The publication date if available in GMT. |
| content | String | The primary body text converted to clean markdown. |
Jina Reader Content Extractor Advanced Features
- Multi-format support allowing output in either raw Markdown or structured JSON for programmatic consumption.
- Configurable request timeouts using the -t or --timeout flag to handle slow-loading sites.
- Seamless integration with search-based Openclaw Skills like tavily-search or searxng for automated end-to-end research.
- Lightweight shell script version for fast execution and easy piping to other CLI tools.
- Built-in metadata extraction for tracking source provenance and publication dates.
SKILL.md
Loading
Related Openclaw Skills
Upbit Trading Bot
An AI-driven cryptocurrency trading bot for Upbit featuring real-time monitoring, GLM-4.7 analysis, and automated execution.
Token Optimizer
A powerful cost-reduction tool for Openclaw Skills that optimizes token usage through intelligent model routing and local heartbeat providers.
Token Optimizer
The Token Optimizer reduces OpenClaw AI costs by up to 97% through intelligent model routing, local provider heartbeats, and efficient prompt caching.
Bilibili Danmaku Analysis
A comprehensive tool for fetching Bilibili video bullet comments and performing automated sentiment analysis and keyword visualization.
Xiaohongshu Video Downloader & Summarizer
A comprehensive automation tool for downloading Xiaohongshu videos and generating full resource packs including transcripts and AI summaries.
Secure Skill Installer
A security-focused gateway that scans and validates Openclaw Skills using the ClawDex API before allowing installation.
Featured*
