agent-browser

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

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/lovincyrus/claude-config --skill agent-browser-lovincyrus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/lovincyrus/claude-config/tree/main/skills/agent-browser
Command: npx skills add https://github.com/lovincyrus/claude-config --skill agent-browser-lovincyrus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when you need to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Core Features & Use Cases

  • Browser navigation and interactions via a Bash-based CLI.
  • Snapshotting, element refs, and interactions like click, fill, and get data.
  • Use cases include automated form submission, UI testing, and data gathering from web pages.

Quick Start

agent-browser open <url> agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e2 "text" 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 web testing and data extraction?

You can automate browser interactions for web testing by using a Bash CLI workflow to navigate pages, fill forms, take screenshots, and extract data. It handles element clicking and text input via command-line commands.

Can I fill out and submit web forms automatically from a Bash environment?

Yes, you can fill out and submit web forms automatically from a Bash environment. The CLI supports form filling by targeting element references and injecting text, enabling automated form submission workflows.

What is the best way to take screenshots during automated web testing?

Taking screenshots during automated web testing is done by navigating to the target URL and executing a snapshot command in the Bash CLI. This captures the web page state for UI testing and verification.

Do I need any specific dependencies to run browser task automation in Bash?

You need a Bash environment with the agent-browser CLI installed and compatible system utilities. No additional software dependencies are required, making it straightforward to set up browser task automation.

How do I extract data from web pages using command-line interface tools?

Data extraction from web pages using command-line interface tools involves navigating to the URL and taking a snapshot to generate element references. You can then target specific elements to retrieve the text or data they contain.

When should I not use a Bash CLI for web automation tasks?

You should not use a Bash CLI for web automation when you need complex visual scripting or lack a Bash-compatible environment. It is strictly command-line driven and relies on terminal access for executing browser actions.