agent-browser

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

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/tegnike/ai-agent-game-streamer --skill agent-browser-tegnike
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/tegnike/ai-agent-game-streamer/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/tegnike/ai-agent-game-streamer --skill agent-browser-tegnike

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables rapid, repeatable browser automation tasks—navigating pages, filling forms, taking screenshots, and extracting data—without manual scripting.

Core Features & Use Cases

  • Automated navigation and interaction with web pages (open, click, fill, snapshot, get)
  • Screenshots, text extraction, and data capture for QA, testing, and documentation
  • Real-world use: QA teams can script a 5-step test to verify login, fill, submit, and verify dashboard URL

Quick Start

Use the agent-browser Skill to automate a simple login test: agent-browser open https://example.com/login agent-browser snapshot -i agent-browser fill @e1 "[email protected]" agent-browser fill @e2 "password" agent-browser click @e3 agent-browser wait --url "**/dashboard"

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 form filling and testing without manual scripting?

Browser automation for web testing and form filling is achieved through command-based operations that navigate pages, fill forms, and take screenshots. You execute scripted actions via Bash using the agent-browser tool to create repeatable interactions without manual scripting.

What is a snapshot reference in browser automation and how does it work?

Snapshot references in browser automation capture element identifiers from the current page state. You generate a snapshot to locate elements, then use those derived references like @e1 or @e2 to target inputs and buttons for scripted interactions.

Can I run browser automation scripts using Bash for QA testing?

Yes, browser automation scripts support execution via Bash for QA testing. You can issue commands to open URLs, take snapshots, fill forms, and click elements, enabling automated test sequences like login verification and dashboard URL validation directly from the command line.

How do I extract text and capture screenshots during web testing?

To extract text and capture screenshots during web testing, you use browser automation commands to snapshot the page state. This allows you to capture data, extract text content, and generate visual records for documentation and QA verification.

Does this browser automation tool support session isolation for testing?

Yes, the browser automation tool supports optional session isolation for testing. This allows QA teams to run independent automated workflows, ensuring that browser interactions like form filling and navigation do not interfere with each other across different test cases.