agent-browser

Automate browser interactions for web testing, form filling, and data extraction.

Updated Jan 16, 2026
One-click install
npx skills add https://github.com/jeninh/ampskills-dotfile --skill agent-browser-jeninh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jeninh/ampskills-dotfile/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/jeninh/ampskills-dotfile --skill agent-browser-jeninh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, and data extraction, reducing manual repetitive tasks and increasing reliability across web applications.

Core Features & Use Cases

  • Automated browser control: open URLs, interact with elements, take snapshots, and extract data.
  • Form automation and data capture: fill fields, submit forms, and collect results for testing and records.
  • Use Case: Perform end-to-end tests on dynamic sites, capture UI state across environments, and automate repetitive data collection tasks.

Quick Start

  1. Install the tool: npm install -g agent-browser
  2. Install the browser binary: agent-browser install
  3. Basic workflow:
  • agent-browser open https://example.com
  • agent-browser snapshot -i
  • agent-browser click @e1
  • agent-browser fill @e2 "text"
  • agent-browser wait --load networkidle
  • agent-browser close

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser interactions for end-to-end web testing?

Automating browser interactions for web testing involves using a CLI tool to open URLs, take snapshots, and interact with page elements. This enables scripted end-to-end testing, form filling, and UI state capture across dynamic web applications.

What is the best way to extract data from dynamic web pages via CLI?

The best way to extract data from dynamic web pages is to use a CLI browser automation tool that supports element references and snapshots. This allows you to locate semantic elements, script interactions, and collect results reliably without manual effort.

Do I need a specific browser engine to run automated web testing from the command line?

Yes, you need a browser engine and CLI tooling to run automated web testing. You typically install the CLI package globally and then download the required browser binary to support automated interactions and snapshot capture.

How does element reference and snapshot based browser automation work?

Element reference and snapshot based browser automation works by capturing a page snapshot with interactive element refs, allowing you to target specific elements like @e1 for clicking or filling. This semantic locating approach ensures accurate scripted interactions on dynamic pages.

Can I use CLI browser automation for form filling and data capture?

Yes, you can use CLI browser automation for form filling and data capture by opening a target URL, locating form fields via element refs, inputting text, and submitting the form. This automates repetitive data collection and records capture tasks.