Jina.ai Reader for Openclaw

A powerful utility to fetch clean, AI-optimized Markdown content from any website, including paywalled and JavaScript-heavy pages.

jiangtianjiao
v1.0.1
Mar 4, 2026
2
2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install jina-ai-reader

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install jina-ai-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.ai Reader?

Jina.ai Reader is a versatile utility designed to simplify web content extraction for AI agents. By utilizing Jina.ai's reading engine, it converts complex web pages into streamlined Markdown format, making it easier for large language models to process information. This Openclaw Skills addition is particularly effective at bypassing paywalls on sites like Medium or Every.to and handling the nuances of social media platforms like Twitter/X, providing a seamless data bridge for your automation workflows.

Jina.ai Reader Use Cases

  • Extracting high-quality text from search engine results for RAG (Retrieval-Augmented Generation) pipelines.
  • Reading content from paywalled news sites and technical blogs without manual intervention.
  • Capturing full Twitter/X threads and posts for sentiment analysis or data gathering.
  • Scraping Single Page Applications (SPAs) that require JavaScript execution to render content.

How Jina.ai Reader Works

  1. The user provides a target URL and optional flags to the script via the CLI.
  2. The script sends a request to the Jina.ai Reader API, which handles the rendering and parsing.
  3. If specified, the tool waits for JavaScript to execute to ensure dynamic content is captured.
  4. The service cleans the HTML, removes clutter, and converts the core content into Markdown.
  5. The resulting Markdown, including optional metadata and images, is returned to the local environment.

Jina.ai Reader Setup

To use this skill, ensure you have Node.js installed. No API key is required for basic usage. This is one of the most accessible Openclaw Skills for web data extraction.

# Run the reader script against a target URL
node scripts/jina-reader.mjs "https://example.com"

# Fetch with a 5-second wait for JavaScript rendering
node scripts/jina-reader.mjs "https://spa-site.com" --wait-ms 5000

Jina.ai Reader Data Schema & Taxonomy

The tool returns a structured Markdown response. When options are enabled, the schema includes the following elements:

Data Point Format Description
Main Content Markdown The primary text of the article or post.
Title String The page title extracted from metadata.
Links Markdown Links Included only if --with-links is passed.
Images Alt Text + URL Included only if --with-images is passed.

Jina.ai Reader Advanced Features

  • Custom rendering delays via --wait-ms to handle slow-loading dynamic content and SPAs.
  • Selective extraction of links and image captions to control context window usage in LLM prompts.
  • Native support for Twitter/X thread extraction, a feature often missing in standard scrapers.
  • Integration-ready for multi-agent workflows using Openclaw Skills for automated research and content aggregation.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*