agent-browser

Automate web browser interactions via CLI for navigation, form filling, and data extraction.

5|Updated Oct 22, 2025
One-click install
npx skills add https://github.com/marchatton/agent-skills --skill agent-browser-marchatton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/marchatton/agent-skills/tree/main/.agents/skills/00-utilities/agent-browser
Command: npx skills add https://github.com/marchatton/agent-skills --skill agent-browser-marchatton

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates web browser interactions, allowing for tasks like filling forms, taking screenshots, and scraping data directly from web pages using a command-line interface.

Core Features & Use Cases

  • Web Navigation: Open, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, type, fill, check, and select elements using reference IDs or semantic locators.
  • Data Scraping & Screenshots: Capture page content, specific element data, or full-page screenshots.
  • Use Case: Automate the process of logging into a website, filling out a contact form, and then taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the website https://example.com and take a screenshot.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web scraping and form filling from the command line?

You can automate web scraping and form filling from the command line by using a headless browser CLI to navigate websites, interact with elements via reference IDs, and extract page data. This approach enables deterministic task execution without a graphical interface.

What is headless browser automation for AI agents?

Headless browser automation for AI agents is the process of controlling web page interactions through a command-line interface. It allows automated scripts to navigate URLs, click elements, type text, and take screenshots using Chromium without displaying a UI.

Do I need to install Chromium to run headless browser automation with Bash?

Yes, you need to install Chromium and the Vercel agent-browser CLI to run headless browser automation with Bash. These dependencies provide the underlying browser engine and command-line interface required to execute automated web interactions.

Can I take full-page screenshots using a command-line interface?

Yes, you can take full-page screenshots using a command-line interface. The browser automation Skill supports capturing complete page content or specific element data, allowing you to save visual confirmations of your automated web navigation sessions.

How do I select web elements deterministically during browser automation?

You can select web elements deterministically during browser automation by using ref-based element selection and semantic locators. This method ensures precise targeting for clicking, typing, or extracting data from specific page components.

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

Using a CLI for browser automation limits you to headless operation without visual feedback during execution. Complex interactions requiring manual visual inspection or highly dynamic single-page applications may pose challenges for purely command-line driven workflows.