Web Reader

Quick web scraping when you need clean article content without wrestling with BeautifulSoup or parsing HTML yourself. Point it at a URL and get back the title, main content as HTML, plain text, and publication time if available. Works through the z-ai-web-dev-sdk's page_reader function, which handles the extraction automatically. The CLI option is handy for one-off scrapes or testing URLs before you write any code. Backend only, obviously. Good for building news aggregators, content archives, or anything that needs to pull text from web pages programmatically. Caches results if you're hitting the same URLs repeatedly.

skills.sh installs: 1.7K
GitHub stars: 26
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add answerzhao/agent-skills --skill web-reader --agent claude-code

Installs into .claude/skills of the current project.

Files

Web Reader Skill

This skill guides the implementation of web page reading and content extraction functionality using the z-ai-web-dev-sdk package, enabling applications to fetch and process web page content programmatically.

Skills Path

Skill Location: {project_path}/skills/web-reader

This skill is located at the above path in your project.

Reference Scripts: Example test scripts are available in the {Skill Location}/scripts/ directory for quick testing and reference. See {Skill Location}/scripts/web-reader.ts for a working example.

Overview

Web Reader allows you to build applications that can extract content from web pages, retrieve article metadata, and process HTML content. The API automatically handles content extraction, providing clean, structured data from any web URL.

IMPORTANT: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.