agent-browser

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

Updated Aug 17, 2023
One-click install
npx skills add https://github.com/kuroRy/dotfiles --skill agent-browser-kurory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/kuroRy/dotfiles/tree/main/config/claude/skills/agent-browser
Command: npx skills add https://github.com/kuroRy/dotfiles --skill agent-browser-kurory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

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

Core Features & Use Cases

  • Navigate and snapshot pages to identify elements and structure.
  • Interact with elements via refs or semantic locators to automate forms, clicks, and navigation.
  • Capture screenshots, generate reports, and record sessions for demonstrations.
  • Retrieve page data (text, HTML, attributes) for validation and data collection.
  • Use in QA, CI, and demos to automate repetitive browser tasks across web apps.

Quick Start

Open a URL, capture a snapshot, then interact with elements using refs to automate a form submission.

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 testing and form filling without writing complex scripts?

Browser automation can be performed through a CLI tool to handle web testing, form filling, and data extraction. You navigate to a URL, snapshot the page to identify elements, and interact using refs or semantic locators to automate clicks and submissions.

What is the best way to capture screenshots and record web sessions for UI testing demonstrations?

Capturing screenshots and recording sessions for UI testing demonstrations is done via browser automation media capture commands. You navigate and interact with single-page apps or dashboards, then trigger optional media capture to generate reports.

Can I use browser automation to extract data and retrieve HTML attributes from single-page apps?

Browser automation allows you to retrieve page data including text, HTML, and attributes from single-page apps and dashboards. It uses interaction commands and information retrieval functions to validate and collect data across web apps.

Does browser automation require external dependencies to run web testing workflows in CI?

No dependencies are required to run browser automation for web testing workflows in CI. The Skill operates independently to navigate pages, apply interaction commands, and extract information across websites without external packages.

How do I identify page elements and structure before automating a form submission?

To identify elements and structure before automating a form submission, you open a URL and capture a page snapshot. This snapshot provides element refs and semantic locators used to target forms, clicks, and navigation interactions.

What are the limitations of using a CLI tool for browser automation in web scraping workflows?

CLI-based browser automation for web scraping relies on navigation, element snapshots, and interaction commands, which may require handling dynamic content loading manually. It provides a comprehensive command surface but may face limitations with highly complex single-page app state management.