What problem does it solve?
This Skill removes the friction of manual browser work by letting an AI control a real Chrome session for navigation, inspection, interaction, and capture.
Core Features & Use Cases
- Web Navigation: Open pages, move through history, and wait for pages to settle before taking the next action.
- Page Inspection: Read visible text, list interactive elements, inspect current URLs, and capture screenshots for analysis.
- Automation and Testing: Click, type, fill forms, run JavaScript in page context, handle tabs, record screencasts, and perform design or accessibility audits.
- Use Case: Ask the agent to log into a site, extract the page contents, capture a screenshot, and verify the layout or accessibility of the result.
Quick Start
Use the mini-browser skill to open the target website, inspect the page, and interact with any form or button you want the agent to operate.