agent-browser

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

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/kazuph/dotfiles --skill agent-browser-kazuph
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/kazuph/dotfiles/tree/main/plugins/agent-browser/skills/agent-browser
Command: npx skills add https://github.com/kazuph/dotfiles --skill agent-browser-kazuph

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, streamlining tasks like web testing, form filling, capturing screenshots, and extracting data from web pages, eliminating manual navigation and repetitive actions.

Core Features & Use Cases

  • Web Navigation: Open, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, type, fill forms, hover, check/uncheck, and select options using element references or semantic locators.
  • Data Extraction & Screenshots: Extract text, values, page titles, URLs, and capture full-page or visible screenshots.
  • Use Case: Automate the process of logging into a web application, filling out a complex form, and submitting it, then verifying the success message.

Quick Start

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

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate form filling and web testing without manual navigation?

Automate form filling and web testing by controlling browser interactions for navigating websites, clicking, typing, and submitting forms. This eliminates repetitive manual actions and verifies success messages automatically.

Can I extract data and capture full-page screenshots from web pages?

Extract data and capture full-page or visible screenshots from web pages by automating browser interactions. You can extract text, values, page titles, and URLs, returning structured JSON output for easy parsing.

Do I need Chrome Canary to automate browser interactions for web tasks?

Yes, Chrome Canary is required to automate browser interactions for web tasks. It supports session management and provides the environment needed for element interaction, data extraction, and screenshot capture.

How do I interact with web page elements using semantic locators for automation?

Interact with web page elements using semantic locators or element references to click, type, hover, check/uncheck, and select options. This enables precise control over forms and navigation during web testing.

What's the best way to automate logging into a web application and verifying submission?

Automate logging into a web application by navigating to the URL, filling out the form, submitting it, and verifying the success message. This streamlines complex workflows into a single automated session.