browser

Automate browser interactions for testing, UI verification, and data extraction via CLI.

674|52|Updated Dec 26, 2025

Search Tags:#browser automation #web testing #web scraping #headless #screenshot #agent-browser #UI verification

Ready to run

npx skills add https://github.com/gmickel/gmickel-claude-marketplace --skill browser-gmickel

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/gmickel/gmickel-claude-marketplace/tree/main/plugins/flow-next/skills/browser
Command: npx skills add https://github.com/gmickel/gmickel-claude-marketplace --skill browser-gmickel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation reduces the manual drudgery of navigating sites, verifying UI, testing web apps, and scraping data by driving a headless browser programmatically.

Core Features & Use Cases

Open URL, snapshot DOM with accessibility refs, and interact via refs (@e1, @e2)
Validate UI, collect screenshots, perform end-to-end tests
Use cases include verifying deployed interfaces, reading docs online, scraping data, and capturing a baseline before redesigns.

Quick Start

Open a site with the CLI, snapshot the page to collect element refs, then interact and verify results:

agent-browser open https://example.com
agent-browser snapshot -i
agent-browser click @e1
agent-browser wait --load networkidle
agent-browser get title
agent-browser screenshot out.png

Frequently Asked Questions about browser

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

FAQPage Schema

How do I automate web testing using a headless browser?▼

Web testing automation uses a headless browser controlled by a CLI to open URLs, snapshot the DOM, and interact with elements via accessibility refs to verify UI and perform end-to-end tests.

Can I capture screenshots during UI verification with a headless browser?▼

Yes, UI verification captures screenshots by opening a URL with the headless browser CLI and running a screenshot command to save the output image for baseline comparisons.

How do I interact with web page elements during browser automation?▼

Browser automation interacts with elements by snapshotting the page to collect accessibility refs, then using click commands with those refs like @e1 or @e2 to trigger actions programmatically.

What is the best way to extract data from web apps programmatically?▼

Data extraction from web apps uses a headless browser CLI to open URLs, wait for network idle, snapshot the DOM, and emit JSON output for automation pipelines and data collection.

Do I need any dependencies to run headless browser control?▼

No external dependencies are required. Headless browser control relies on the agent-browser CLI to open sites, snapshot DOM, click elements, and wait for page loads.

Why does web scraping require waiting for network idle?▼

Web scraping requires waiting for network idle to ensure dynamic content fully loads before snapshotting the DOM, preventing missing elements during data extraction or UI verification.