agent-browser

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

3|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/ryryo/dot-claude-dev --skill agent-browser-ryryo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ryryo/dot-claude-dev/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/ryryo/dot-claude-dev --skill agent-browser-ryryo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for testing, form filling, screenshots, and data extraction.

Core Features & Use Cases

  • Navigate pages, snapshot interactive elements, and perform actions by element refs.
  • Capture screenshots, extract page data, and automate repetitive web tasks for QA, demos, and data collection.
  • Use Case: QA automation on web apps, filling forms on staging sites, and generating demonstration recordings.

Quick Start

agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e2 "text" agent-browser screenshot 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 form filling?

Automate browser interactions for web testing using a Bash-based CLI to navigate pages, snapshot interactive elements, fill inputs, and capture screenshots. It provides commands like open, click, fill, and screenshot to support deterministic workflows across web applications.

Can I capture screenshots and extract page data from web dashboards via CLI?

Yes, you can capture screenshots and extract page data from web dashboards via CLI. The tool provides dedicated commands to navigate URLs, snapshot elements, and generate screenshots for QA, demos, and data collection tasks.

How do I click elements and fill forms in automated browser testing?

To click elements and fill forms in automated browser testing, use the snapshot command to capture interactive elements and generate element refs. Then, use the click command with the element ref like @e1, and the fill command with the ref and input text.

What is the best way to automate repetitive web tasks for QA without heavy dependencies?

Automate repetitive web tasks for QA using a lightweight Bash-based CLI with zero external dependencies. It enables deterministic workflows by navigating pages, interacting with elements via refs, and extracting information without complex frameworks.

Does this browser automation CLI support staging sites for QA automation?

Yes, this browser automation CLI supports staging sites for QA automation. You can navigate to staging URLs, fill forms, interact with elements, and capture screenshots to automate repetitive testing and generate demonstration recordings.

Why does my browser automation workflow need element refs to click and fill inputs?

Browser automation workflows need element refs to click and fill inputs because the snapshot command captures interactive elements and assigns deterministic references like @e1. This ensures accurate targeting of page elements during automated testing and data extraction.