browser-automation

Automate browser interactions via Chromium CDP, including navigation, screenshots, and form input.

8|1|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/greghavens/triggerfish --skill browser-automation-greghavens
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-automation
Source: https://github.com/greghavens/triggerfish/tree/main/skills/bundled/browser-automation
Command: npx skills add https://github.com/greghavens/triggerfish --skill browser-automation-greghavens

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates common web browsing tasks, allowing AI agents to interact with websites programmatically, saving users time and effort on repetitive online activities.

Core Features & Use Cases

  • Navigate Websites: Go to any specified URL.
  • Content Extraction: Capture screenshots and extract visible text from web pages.
  • Form Interaction: Fill out forms by typing text and selecting options.
  • Element Interaction: Click buttons and scroll through pages.
  • Use Case: An AI agent can use this skill to automatically fill out a job application form on a website, navigate through multiple pages of search results, or extract key information from a news article.

Quick Start

Use the browser-automation skill to navigate to https://example.com and take a screenshot.

Frequently Asked Questions about browser-automation

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

FAQPage Schema
Can I automate web scraping and form filling without writing browser extension scripts?

Yes, you can automate web scraping and form filling directly by using the Chromium CDP. This approach allows AI agents to programmatically navigate URLs, type into forms, select dropdown options, and extract visible text without traditional browser extension scripts.

How do I take screenshots with text extraction during browser navigation?

You can take screenshots with text extraction during browser navigation by using the Chromium CDP. The automation skill captures visual screenshots of web pages and simultaneously extracts the visible text content from the specified URLs.

How do I automate clicking elements and scrolling through web pages programmatically?

You can automate clicking elements and scrolling through web pages programmatically via the Chromium CDP. This enables AI agents to interact with website buttons, navigate through multiple pages of search results, and scroll dynamically.

Does browser automation work with Flatpak Chrome or do I need a direct Chromium install?

Browser automation supports both direct Chromium installs and Flatpak Chrome environments. The system features auto-launch on first use, allowing it to automatically detect and start the appropriate browser instance for your web tasks.

What is the best way to extract key information from news articles using AI agents?

The best way to extract key information from news articles using AI agents is through Chromium CDP automation. Agents navigate to the article URL, capture screenshots, and extract visible text content directly from the web page for analysis.

Can I use browser automation to automatically fill out job application forms on websites?

Yes, you can use browser automation to automatically fill out job application forms on websites. The Chromium CDP integration allows AI agents to navigate form pages, type text into input fields, and select dropdown options programmatically.