core-agent-browser

Automates web browser interactions via CLI for navigation, form filling, and screenshots.

51|6|Updated Mar 28, 2019
One-click install
npx skills add https://github.com/Mte90/dotfiles --skill core-agent-browser-mte90
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: core-agent-browser
Source: https://github.com/Mte90/dotfiles/tree/main/.config/opencode/skills/core-agent-browser
Command: npx skills add https://github.com/Mte90/dotfiles --skill core-agent-browser-mte90

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates web browser interactions, allowing for tasks like navigating websites, filling forms, clicking elements, and capturing screenshots, thereby streamlining repetitive online processes.

Core Features & Use Cases

  • Web Navigation: Open, close, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, double-click, type into, hover over, check/uncheck, and select options within web elements using semantic locators or element references.
  • Data Retrieval: Extract text content, input values, and page titles.
  • Visual Feedback: Capture screenshots of the entire page or specific elements.
  • Use Case: Automate the process of logging into a web application, filling out a user profile, and submitting the form.

Quick Start

Use the core-agent-browser skill to open the URL https://example.com.

Frequently Asked Questions about core-agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web browser interactions for form filling and navigation?

You can automate web browser interactions by using a CLI interface to navigate pages, fill forms, click elements, and capture screenshots. It streamlines repetitive online processes like web scraping and automated testing through semantic locators.

Can I extract text content and input values during web scraping tasks?

Yes, web scraping tasks support extracting text content, input values, and page titles. The automation retrieves data directly from web elements after navigating to the target URL, enabling efficient data collection from web pages.

What's the best way to click and interact with web elements using semantic locators?

The best way to interact with web elements is by using semantic locators or element references. This allows you to click, double-click, type into, hover over, check/uncheck, and select options within web elements accurately during browser automation.

Does browser automation support capturing screenshots of specific elements?

Yes, browser automation supports capturing screenshots of either the entire page or specific elements. This visual feedback mechanism helps verify automated testing results and user interface simulation scenarios effectively.

Do I need any dependencies to use core-agent-browser for user interface simulation?

No additional dependencies are required to use core-agent-browser for user interface simulation. It operates through direct browser control via a CLI interface, providing built-in support for element referencing and semantic locators.

When should I not use browser automation for repetitive online processes?

Browser automation for repetitive online processes may not be suitable for websites requiring complex human verification or dynamic content that changes unpredictably. It works best for structured navigation, form filling, and data retrieval tasks.