vision-click

What problem does it solve?

This Skill enables interaction with non-DOM elements on a webpage by using AI to interpret visual information and determine click coordinates, overcoming limitations of traditional element-based clicking.

Core Features & Use Cases

• Vision-Based Clicking: Clicks elements based on their visual appearance in a screenshot, not their DOM ID or selector.
• Fallback for Complex UIs: Ideal for clicking elements within canvas, iframes, Shadow DOM, or dynamically rendered content where standard selectors fail.
• Use Case: Clicking a "Submit" button within a complex web application's canvas element where no standard HTML element is available for selection.

Quick Start

Use the vision-click skill to click the "Submit button" on the current screen.