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

gstack

Controls a headless Chromium browser via CLI to navigate, extract, and interact with web pages.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides AI agents with the ability to interact with web pages programmatically, overcoming the limitation of being unable to "see" or interact with live web content.

Core Features & Use Cases

  • Web Interaction: Navigate websites, fill forms, click buttons, and extract data.
  • Visual Verification: Take screenshots and capture visual layouts for analysis.
  • Use Case: An AI agent needs to verify a new feature deployed to staging. It uses /browse to log in, navigate through the feature's user flow, take screenshots of key pages, and check the console for errors, reporting back on the success or failure of the deployment.

Quick Start

Use the browse skill to navigate to the URL https://example.com and then extract all the text content from the page.

Frequently Asked Questions about gstack

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

FAQPage Schema
How do I automate web scraping with a headless Chrome browser?▼

Headless Chrome web scraping is achieved by controlling a Chromium instance via CLI commands, allowing automated agents to navigate URLs, extract text content, and interact with page elements without a graphical interface.

Can I use Playwright for AI agent web interaction tasks?▼

Playwright web interaction tasks are supported through a CLI-controlled headless Chromium environment, enabling automated agents to fill forms, click buttons, extract data, and navigate complex user flows programmatically.

What is the best way to verify a deployed staging website using browser automation?▼

Website staging verification using browser automation involves navigating the deployed feature's user flow, capturing screenshots of key pages, and checking console logs for errors to report deployment success or failure.

Does headless Chrome support capturing network and console logs for debugging?▼

Headless Chrome supports debugging by capturing both network and console logs during automated browsing sessions, allowing agents to analyze page behavior and identify errors encountered during web interaction tasks.

How do I extract page content and take screenshots during automated web browsing?▼

Page content extraction and screenshot capture during web browsing are performed via CLI commands that control a headless Chromium instance, enabling visual layout analysis and text retrieval from target URLs.

What are the limitations of using a CLI tool for browser automation?▼

CLI tool browser automation limitations include reliance on a headless Chromium environment, meaning tasks requiring direct visual user interaction or complex graphical rendering may not execute as expected.

Related Skills

Explore More Software Engineering Skills→
henkisdabrohenkisdabro
77

webapp-testing

Automate local web app testing with Playwright and headless Chromium.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

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

Official
Intermediate
yyopcyyopc
7

agent-browser

Automate web navigation, form submission, and data extraction via Chrome CDP.

Official
Advanced
SecurityRoninSecurityRonin
1

browser-automation

Automate browser tasks and testing across Playwright, Puppeteer, Selenium, and CDP workflows.

Official
Intermediate