skills.rest
lmanchu
lmanchuCOMMUNITY
Explore all skills by this author →
GitHub

browse

Operate a headless Chromium daemon for web navigation, interaction, and extraction.

5|2|Updated Nov 1, 2025
Search Tags:#web browsing#playwright#web automation#data scraping#headless chrome#ai agent tool
One-click install
npx skills add https://github.com/lmanchu/iris-system --skill browse-lmanchu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/lmanchu/iris-system/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/lmanchu/iris-system --skill browse-lmanchu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a fast, reliable, and programmatic way for AI agents to interact with web pages, overcoming the limitations of slow browser extensions or complex web scraping setups.

Core Features & Use Cases

  • Web Navigation: Navigate to any URL, go back/forward, reload pages.
  • Content Interaction: Click elements, fill forms, type text, select options, hover.
  • Data Extraction: Read cleaned page text, extract HTML, get links, forms, and accessibility trees.
  • Inspection: Run JavaScript, get CSS properties, inspect attributes, capture console/network logs.
  • Visuals: Take screenshots, save as PDF, generate responsive layout images.
  • Use Case: An AI agent needs to check the status of a web application deployment. It uses browse goto http://localhost:3000, then browse text to read the page content, and finally browse screenshot /tmp/deployment.png to capture a visual confirmation.

Quick Start

Use the browse skill to navigate to https://example.com and then read the page's title.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate web browsing tasks with an AI agent?▼

AI agent web automation is achieved by using a persistent headless Chromium daemon to execute CLI commands for navigation, element interaction, and data extraction without launching a full browser interface.

Can I extract cleaned text and HTML from web pages using headless Chrome?▼

Yes, headless Chrome data extraction supports reading cleaned page text, extracting raw HTML, pulling links, and generating accessibility trees to provide structured content for processing.

How do I fill out forms and click elements during web automation?▼

Form filling and element interaction are handled by executing specific CLI commands that trigger clicks, type text, select dropdown options, and perform hover actions on targeted page elements.

How does persistent state management work across multiple CLI calls?▼

Persistent state management operates via a background Chromium daemon that keeps browser sessions active, allowing sequential CLI commands to maintain navigation history and page state across multiple executions.

Does this web automation tool support capturing screenshots and network logs?▼

Yes, web automation inspection supports capturing visual screenshots, saving pages as PDFs, and retrieving console and network logs to debug page behavior and verify deployment statuses.

What is the best way to debug a deployed web application with an AI agent?▼

AI agent web debugging is best performed by navigating to the target URL, reading the cleaned page text to check content, and capturing a screenshot to visually confirm the application deployment status.

Related Skills

Explore More Software Engineering Skills→
Chang-Shih-YungChang-Shih-Yung

gstack

Run a persistent headless Chromium daemon with Playwright under Bun via HTTP.

Community
Advanced
ComwrapUkReplyComwrapUkReply

scrape-webpage

Scrape webpages to extract content, metadata, and images for migration workflows.

Community
Advanced
docaohieu2808docaohieu2808

chrome-devtools

Automate browser interactions with Puppeteer scripts for scraping, forms, and screenshots.

Community
Intermediate
zhayujiezhayujie
46.4k

web-fetch

Fetch web page HTML and extract title and readable text.

Community
Basic