agent-browser

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

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/Blake-John/agent-config --skill agent-browser-blake-john
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Blake-John/agent-config/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/Blake-John/agent-config --skill agent-browser-blake-john

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automate browser interactions for testing, form filling, screenshots, and data extraction to speed up web workflows and reduce manual repetitive tasks.

Core Features & Use Cases

  • Automates web testing, form completion, and visual validation across web apps.
  • Captures page state with snapshots and refs for efficient, low-token interactions.
  • Supports navigation, interaction, data extraction, and recording for debugging and documentation.

Quick Start

Run a browser automation task to open a URL, snapshot the page to obtain element refs, and perform actions using those refs.

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 and data extraction?

Browser automation for web testing and data extraction is handled by navigating to URLs, capturing page snapshots, and performing actions using element refs to minimize token usage. It supports headless and headed modes for validating UI behavior and extracting information.

Can I use snapshots and refs to reduce AI token usage during browser automation?

Yes, snapshots and refs minimize AI token usage during browser automation by capturing the page state and assigning references to elements. You use these refs to perform navigation, interaction, and data extraction commands efficiently.

What is the best way to automate form filling and visual validation across web apps?

Automating form filling and visual validation across web apps is achieved through a comprehensive command set for navigation and interaction. You open a URL, snapshot the page to obtain element refs, and execute actions to complete forms and capture screenshots.

Does headless browser automation support recording for debugging and documentation?

Headless browser automation supports navigation, interaction, data extraction, and recording for debugging and documentation. It works with both headless and headed modes to speed up web workflows and reduce manual repetitive tasks.

Can I extract specific information from pages using browser automation scripts?

Yes, you can extract specific information from pages using browser automation scripts. The automation captures page states with snapshots and refs, allowing you to target and extract data efficiently while validating UI behavior across websites.

Do I need any external dependencies to run browser automation tasks end-to-end?

No external dependencies are required to run browser automation tasks end-to-end. The automation provides a comprehensive command set for navigation, interaction, data extraction, and recording, working natively in both headless and headed modes.