agent-browser

Automate browser navigation, form filling, and screenshot capture via CLI.

Updated Jan 27, 2026
One-click install
npx skills add https://github.com/z-ph/newLab --skill agent-browser-z-ph
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/z-ph/newLab/tree/main/.opencode/skills/agent-browser
Command: npx skills add https://github.com/z-ph/newLab --skill agent-browser-z-ph

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates web browser interactions, allowing AI agents to navigate websites, fill forms, click buttons, take screenshots, and scrape data without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, type, fill, hover, check/uncheck, select dropdown options using accessible refs or semantic locators.
  • Data Scraping & Screenshots: Extract text, HTML, attributes, and capture full-page or viewport screenshots.
  • Use Case: An AI agent can use this skill to log into a website, fill out a complex form, and then save a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to navigate to https://example.com and take a screenshot.

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 browser interactions for an AI agent?

Automating web browser interactions for an AI agent is done through a command-line interface that enables navigation, form filling, element interaction, and data scraping on web pages. It uses accessibility snapshots with ref-based element selection for deterministic task execution.

What is the best way to take screenshots during web scraping with an AI agent?

Taking screenshots during web scraping is handled by capturing full-page or viewport images. The automation skill allows AI agents to navigate URLs, extract data, and save visual confirmation of the web page state without manual intervention.

How do I fill out complex web forms automatically using browser automation?

Filling out complex web forms automatically uses accessible refs or semantic locators to click, type, and select dropdown options. This allows AI agents to complete login processes and form submissions deterministically.

Can I use this browser automation tool to extract HTML and text from web pages?

Yes, you can use this browser automation tool to extract text, HTML, and attributes from web pages. It enables AI agents to scrape data efficiently by utilizing accessibility snapshots for accurate element selection.

Does this web automation skill require any external dependencies to run?

No, this web automation skill does not require any external dependencies to run. It operates independently through a command-line interface to perform navigation, element interaction, and screenshot capture.

Why use accessibility snapshots for deterministic web page task execution?

Accessibility snapshots are used for deterministic web page task execution because they provide ref-based element selection. This ensures precise interaction for clicking, typing, and scraping elements on web pages without relying on fragile visual coordinates.