skills.rest
chancoute
chancouteCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

Extract structured content, title, HTML, and metadata from web page URLs.

Updated Jan 8, 2026
Search Tags:#backend#HTML#metadata#URL#content-extraction#web-reading
One-click install
npx skills add https://github.com/chancoute/sgin --skill web-reader-chancoute
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/chancoute/sgin/tree/main/skills/web-reader
Command: npx skills add https://github.com/chancoute/sgin --skill web-reader-chancoute

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) components.

What problem does it solve?

This Skill enables backend systems to fetch web pages and extract structured content, including the title, HTML, plain text, and essential metadata, reducing manual scraping work.

Core Features & Use Cases

  • Page Reading: Retrieve the main article content, title, URL, and publication time from any accessible web page.
  • Metadata Extraction: Pull metadata such as descriptions, keywords, and author information when available.
  • Use Case: Build content dashboards, knowledge bases, or research tools that ingest web content for indexing and analysis.

Quick Start

Use the web-reader skill to read a page by URL with the backend SDK:

  • via SDK: await zai.functions.invoke('page_reader', { url: 'https://example.com' });
  • via CLI: z-ai function -n page_reader -a '{"url":"https://example.com"}'

Frequently Asked Questions about web-reader

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

FAQPage Schema
How do I extract web content and metadata from a URL for backend content aggregation?▼

To extract web content from a URL, use the page_reader function via the z-ai-web-dev-sdk backend invocation. It returns structured data including the page title, HTML, plain text, URL, and publication time for content aggregation workflows.

What is the best way to fetch article title and publishedTime from web pages?▼

The best way to fetch article titles and publication times is invoking the page_reader function through the backend SDK. It reads accessible web pages and returns structured fields like data.title and data.publishedTime directly.

Can I use the z-ai-web-dev-sdk to read HTML and metadata from any accessible web page?▼

Yes, you can use the z-ai-web-dev-sdk to read HTML and metadata from any accessible web page. By invoking the page_reader function with a URL, the backend SDK returns the extracted title, HTML content, and metadata.

Does the page_reader function return plain text or HTML when extracting web page content?▼

The page_reader function returns HTML content from web pages. Alongside the HTML, it provides the data.title, data.url, data.publishedTime, and tokens used, supplying the structured output needed for backend workflows.

Related Skills

Explore More Software Engineering Skills→
EnztunEnztun

web-search

Perform real-time web searches with structured results using the z-ai-web-dev-sdk.

Community
Advanced
liumeixinliumeixin
4

design-shi-wiki

Manage knowledge base content, indexing, and migration workflows.

Community
Intermediate
zeustritonzeustriton

web-reader

Extract page titles, HTML, and metadata from single or batch URLs.

Community
Intermediate
greencmgreencm
1

scrape

Extract data from web pages by parsing HTML content.

Community
Intermediate