skills.rest
marktantongco
marktantongcoCOMMUNITY
Explore all skills by this author →
GitHub

web-reader

Extract title, HTML, text, and publish time from web pages.

2|Updated Mar 31, 2026
Search Tags:#html#web scraping#metadata#content extraction#rss#z-ai-web-dev-sdk
One-click install
npx skills add https://github.com/marktantongco/promptc-os --skill web-reader-marktantongco
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-reader
Source: https://github.com/marktantongco/promptc-os/tree/main/skills/web-reader
Command: npx skills add https://github.com/marktantongco/promptc-os --skill web-reader-marktantongco

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates manual web scraping and content harvesting by providing backend-ready functions to extract page titles, main HTML content, plain text, publication timestamps, and metadata in a structured format suitable for downstream processing.

Core Features & Use Cases

  • Automatic Extraction: Retrieve title, main HTML, plain text, publish_time, URL, and metadata from arbitrary web pages.
  • Integration & Automation: Examples include Express API endpoints, scheduled fetchers, RSS aggregation, and batch processors using the z-ai-web-dev-sdk.
  • Resilience & Performance: Demonstrated best practices for error handling, rate limiting, caching, parallel processing, and token usage monitoring.
  • Use Case: Aggregate news articles into a searchable feed, power SEO analysis pipelines, or build scheduled content monitors that persist extracted data.

Quick Start

Read and extract the title, HTML, plain text, publish_time, and metadata from https://example.com/article and return the result as JSON.

Frequently Asked Questions about web-reader

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

FAQPage Schema
How do I extract clean article text and metadata from arbitrary web pages for news aggregation?▼

Web content extraction for news aggregation retrieves clean article text, titles, HTML, publication timestamps, and metadata from arbitrary web pages. This Skill provides structured JSON outputs suitable for downstream processing in automated aggregation pipelines.

Can I use this for batch web scraping and RSS harvesting with rate limiting and caching?▼

Batch web scraping and RSS harvesting are supported with demonstrated best practices for rate limiting, caching, and parallel processing. The Skill handles backend workflows via the z-ai-web-dev-sdk, enabling resilient automated content fetching.

Does web content extraction work with the z-ai-web-dev-sdk in backend-only environments?▼

Web content extraction operates via the z-ai-web-dev-sdk in backend-only environments. It is designed for Node.js backend workflows like Express API endpoints and scheduled fetchers, returning structured page content including plain text and usage tokens.

What's the best way to build a scheduled content monitor that persists extracted article data?▼

Building a scheduled content monitor is achieved by applying this Skill's extraction functions to fetch titles, main HTML, and publish_time from target URLs. Extracted structured data can then be persisted for SEO analysis or content monitoring.

What structured outputs can I expect when extracting SEO metadata from web pages?▼

Extracting SEO metadata yields structured outputs including title, main HTML, plain text, publish_time, URL, metadata, and usage tokens. These fields are returned as JSON for direct integration into analysis pipelines.

Are there limitations when extracting main HTML content from heavily dynamic or JavaScript-rendered pages?▼

Limitations apply to extraction from heavily dynamic or JavaScript-rendered pages, as the Skill focuses on structured backend retrieval via the z-ai-web-dev-sdk. It handles arbitrary pages but relies on standard fetching without explicit browser rendering capabilities.

Related Skills

Explore More Software Engineering Skills→
skkarkiskkarki

LLM

Build LLM-driven chat experiences in Node.js backend services using the z-ai-web-dev-sdk.

Community
Intermediate
eesha000009-deveesha000009-dev
1

web-reader

Extract article content, metadata, and cleaned HTML from web pages.

Community
Intermediate
XJTLUmediaXJTLUmedia
28

web-reader

Extract structured content and metadata from public web URLs.

Community
Intermediate
aaronjmarsaaronjmars
17

RSS Digest

Fetch RSS/Atom feeds from a YAML file and summarize recent entries.

Community
Intermediate