skills.rest
catalinakarstulovic2-ai
catalinakarstulovic2-aiCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

Extract web page titles, HTML, publish time, and metadata via the z-ai-web-dev-sdk.

Updated Jun 9, 2026
Search Tags:#typescript#backend#sdk#metadata#web#web-scraping#content-extraction
One-click install
npx skills add https://github.com/catalinakarstulovic2-ai/hotel --skill web-reader-catalinakarstulovic2-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/catalinakarstulovic2-ai/hotel/tree/main/.claude/skills/web-reader
Command: npx skills add https://github.com/catalinakarstulovic2-ai/hotel --skill web-reader-catalinakarstulovic2-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web pages contain valuable information that is often difficult to extract for automated workflows. This skill provides a robust mechanism to fetch a page's title, HTML content, publication time, and basic metadata for use in apps and dashboards.

Core Features & Use Cases

  • Automated content extraction: Retrieve title, HTML, and publish time from any URL.
  • Metadata extraction: Pull meta description, keywords, and author information from HTML.
  • Backend integration: Use the z-ai-web-dev-sdk in server-side code to power data pipelines, dashboards, and automation tools.
  • Use Case: Build content-monitoring tools that track changes to articles and summarize pages for reporting.

Quick Start

To get started, provide a URL and let the web reader fetch the page title, HTML content, and publish time.

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 multiple URLs in a backend TypeScript application?▼

To extract web content and metadata in a backend TypeScript application, provide the target URLs to the web reader skill. It returns structured results containing the title, HTML, publish time, and usage tokens for each page.

Can I use the z-ai-web-dev-sdk to fetch article publish time and HTML content for content monitoring?▼

Yes, the z-ai-web-dev-sdk can fetch article publish time and HTML content for content monitoring. The skill implements backend-only usage of the SDK to retrieve structured page data suitable for tracking changes and summarizing articles.

What is the best way to scrape web page metadata like description and author information?▼

The best way to scrape web page metadata is to use a skill that supports optional extraction. This skill pulls meta descriptions, keywords, and author information directly from the HTML alongside the title and publication time.

Does the web reader skill handle errors when scraping content from multiple URLs?▼

Yes, the web reader skill handles errors when scraping content from multiple URLs. It processes the URLs and returns structured results while managing extraction failures, ensuring your content pipelines continue running smoothly.

How do I get structured SEO data like title and metadata for downstream dashboards?▼

To get structured SEO data for downstream dashboards, pass your target URLs to the web reader. It extracts the title, URL, HTML, publish time, and metadata, providing a structured output ready for SEO analysis and reporting.

Related Skills

Explore More Software Engineering Skills→
ncsound919ncsound919

LLM

Implement LLM chat completions with the z-ai-web-dev-sdk on backend runtimes.

Community
Intermediate
kevinnftkevinnft
13

blogwatcher

Track blog and RSS/Atom feed updates using the blogwatcher-cli tool.

Community
Intermediate
zakarooozakarooo

web-search

Search the web in real time via the z-ai-web-dev-sdk web_search function.

Community
Intermediate
lvhuanidlvhuanid

web-reader

Extract text, HTML, and metadata from web pages using z-ai-web-dev-sdk.

Community
Intermediate