skills.rest
flaz78
flaz78COMMUNITY
Explore all skills by this author →
GitHub

browser_automation

Navigate web pages with JavaScript and extract title and final URL.

9|1|Updated Mar 18, 2026
Search Tags:#web scraping#web automation#content retrieval#screenshot#javascript rendering#arm64 fallback#http extraction
One-click install
npx skills add https://github.com/flaz78/9Lives --skill browser-automation-flaz78
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser_automation
Source: https://github.com/flaz78/9Lives/tree/main/workspace/skills/browser_automation
Command: npx skills add https://github.com/flaz78/9Lives --skill browser-automation-flaz78

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

This Skill removes the friction of reading web pages that rely on JavaScript while staying reliable on Raspberry Pi ARM64 environments where a real browser may not always run.

Core Features & Use Cases

  • Real-browser navigation with JS support: Uses a real browser to navigate pages and wait for network to become idle.
  • HTTP-based fallback text extraction: If the browser fails or is unavailable, extracts text via HTTP in a way that is safer for ARM64 setups.
  • Proof with optional screenshots: Captures the current page visually when a screenshot is explicitly needed.
  • Use Case: Building a daily briefing agent that collects article text from multiple sites even when some pages fail to render in the browser runtime.

Quick Start

Ask the agent to extract the readable content from a given URL, and automatically fall back to HTTP extraction if browser automation is not available.

Frequently Asked Questions about browser_automation

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

FAQPage Schema
How do I extract readable text from dynamic web pages that require JavaScript rendering?▼

Web page content extraction for JavaScript-rendered pages is handled by attempting real browser navigation and waiting for the network to become idle before retrieving the text. If the browser fails, an HTTP-based text extraction fallback is used to ensure content retrieval.

Can I scrape web content reliably on ARM64 devices where a real browser might fail?▼

Yes, reliable web scraping on ARM64 environments is supported by falling back to HTTP text extraction when real browser automation fails or is unavailable, ensuring you still retrieve usable page content.

How do I capture a screenshot of a web page during browser automation?▼

Screenshots are captured during browser navigation only when explicitly requested. The tool performs real-browser navigation and can optionally take a visual snapshot of the current page as proof of content retrieval.

What is the best way to build a daily briefing agent that collects articles from multiple sites?▼

Building a daily briefing agent is best achieved by using browser automation to extract article text across multiple URLs, automatically falling back to HTTP extraction if browser rendering fails, and returning the final URL and title for each page.

Does web scraping with HTTP fallback return the final URL and page title accurately?▼

Yes, the HTTP fallback and browser navigation processes are designed to return the usable page title and final URL accurately, ensuring reliable content retrieval across both dynamic and static web pages.

Related Skills

Explore More Software Engineering Skills→
SelectXn00bSelectXn00b
198

browser-automation

Automate web browser navigation, data extraction, and element interaction via HTTP API.

Official
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
khw1031khw1031
1

document-consolidator

Consolidate multiple documents into a structured report with references.

Community
Advanced
Z43LZ43L

scrapling

Extract web content from static, dynamic, and Cloudflare-protected pages.

Community
Advanced