agent-browser

Automate browser navigation, form filling, and UI verification via CLI.

1|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill agent-browser-xdrshjr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/xdrshjr/JR-Agent-Skills/tree/main/agent-browser
Command: npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill agent-browser-xdrshjr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps teams automate repetitive browser interactions, freeing time for more complex testing and data gathering.

Core Features & Use Cases

  • Automated Navigation & Form Filling: Open pages, fill inputs, and submit forms across websites.
  • Interaction & Verification: Snapshot page structure, click elements by reference, and validate UI flows.
  • Data Extraction & Screenshotting: Capture content and visuals for reports or QA artifacts.
  • Use Case: Imagine QA engineers continuously exercising a checkout flow across multiple sites with minimal manual effort.

Quick Start

  • agent-browser open https://example.com
  • agent-browser snapshot -i
  • agent-browser click @e1
  • 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 using a CLI?

Automating browser interactions via CLI involves opening pages, snapshotting structure, and clicking elements by reference to execute deterministic scripts. This approach enables reliable web testing and UI verification without manual effort.

What's the best way to extract data and capture screenshots from web pages?

Data extraction and screenshotting from web pages can be achieved by navigating to target sites and capturing content and visuals. This process generates reports and QA artifacts directly from the automated browser workflow.

Can I use a CLI tool to fill forms and verify UI flows across multiple sites?

Yes, a CLI-driven workflow supports filling inputs, submitting forms, and verifying UI flows across multiple websites. It applies deterministic script execution to ensure reliable interaction validation.

How does page snapshotting work for element interaction in browser automation?

Page snapshotting captures the current page structure and assigns references to interactive elements. You can then use these references with click commands to interact with specific elements deterministically.

Does deterministic script execution require any specific browser dependencies?

Deterministic script execution operates via a CLI-driven workflow with no external dependencies required. It uses page snapshotting and element references to ensure reliable and repeatable browser task automation.