web-reader

Extract title, HTML, and publish_time from web page URLs.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/Kraits/cxc-ace --skill web-reader-kraits
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/Kraits/cxc-ace/tree/main/skills-backup/web-reader
Command: npx skills add https://github.com/Kraits/cxc-ace --skill web-reader-kraits

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web content is often scattered and difficult to extract reliably for automation. The Web Reader skill provides a backend-first capability to fetch a page's title, main HTML, and optional publication time so you can index, summarize, or analyze articles.

Core Features & Use Cases

  • Automated Page Reading: extract title, HTML, and publish_time from a URL
  • Metadata Extraction: retrieve author, description, keywords when available
  • Use Case: build a content feed or knowledge base by aggregating multiple web articles for QA or research

Quick Start

Invoke the web-reader on a URL to fetch the title, HTML, and metadata using the page_reader backend function.

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 page content and metadata from a URL in backend automation?

To extract web page content from a URL in backend automation, you can use a web scraping skill to fetch the page's title, main HTML, and publish_time. It also retrieves available metadata like author, description, and keywords for indexing articles.

Can I use z-ai-web-dev-sdk to scrape articles and build a knowledge base?

Yes, you can use z-ai-web-dev-sdk to scrape articles and build a knowledge base. This backend-first capability fetches title, HTML, and publication time to aggregate multiple web articles for research, QA, or content indexing.

What is the best way to automate web content extraction for a content feed?

The best way to automate web content extraction for a content feed is using a backend script that normalizes data and applies error handling. This approach reliably retrieves the title, HTML, and publish_time needed to populate your feed.

Does this web scraping approach retrieve publication time and author metadata?

Yes, this web scraping approach retrieves publication time and author metadata when available. Alongside the main HTML and title, it extracts description and keywords to provide comprehensive metadata for your content-aware applications.

Why does web content extraction fail and what limitations exist with backend scripts?

Web content extraction can fail due to missing metadata or inaccessible page structures, which is why error handling is essential. Limitations include its exclusive backend operation and dependency on z-ai-web-dev-sdk, meaning it cannot run in frontend environments.