web-fetch

Fetch URL content and extract readable text via Jina Reader API.

2|Updated Mar 22, 2024
One-click install
npx skills add https://github.com/wh131462/x-cli --skill web-fetch-wh131462
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-fetch
Source: https://github.com/wh131462/x-cli/tree/main/.claude/skills/web-fetch
Command: npx skills add https://github.com/wh131462/x-cli --skill web-fetch-wh131462

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click, httpx, and includes scripts (resource) components.

What problem does it solve?

Fetch and extract readable content from any URL, enabling quick reading, summarization, and downstream analysis without manual copy-pasting.

Core Features & Use Cases

  • Web content extraction: Retrieve clean, readable article text and metadata from diverse pages.
  • JSON output for AI workflows: Returns structured data (title, content, URL, metadata) suitable for LLM processing.
  • Use Case: Read long documentation or blog posts and feed the extracted text into a summarization or QA model.

Quick Start

Fetch a page by URL and return the cleaned content for processing.

Frequently Asked Questions about web-fetch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract readable text from a web URL for AI processing?

Extracting readable text from a web URL involves fetching page content via the Jina Reader API, which handles diverse page structures and returns structured JSON with title, content, and metadata for downstream AI processing.

Can I get JSON output from web content extraction?

You can get JSON output from web content extraction as the script returns structured data including the page title, cleaned text content, URL, and metadata, making it ready for direct LLM processing.

Does the web content fetcher require a timeout parameter?

The web content fetcher requires both a valid URL and a timeout parameter to operate, using the uv runner to invoke the extraction script and fetch page content via the Jina Reader API.

What is the best way to read long documentation from a URL without manual copy-pasting?

Reading long documentation without manual copy-pasting is best done by fetching the URL and applying the Jina Reader API to extract readable text, which ensures clean output across various page structures for quick reading.

What are the limitations when extracting web content from diverse page structures?

Limitations when extracting web content include dependency on the Jina Reader API to handle diverse page structures and the configured timeout parameter, which may restrict fetching from slow or heavily scripted dynamic pages.