find-ui-element

Identify UI elements in screenshots and generate bounding box coordinates.

19|14|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/X-School-Academy/skill-pilot --skill find-ui-element
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: find-ui-element
Source: https://github.com/X-School-Academy/skill-pilot/tree/main/core/skills/system/find-ui-element
Command: npx skills add https://github.com/X-School-Academy/skill-pilot --skill find-ui-element

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps locate specific user interface elements within screenshots, which is crucial for automating interactions with graphical applications or websites when direct element selectors are unavailable.

Core Features & Use Cases

  • Visual Element Identification: Finds buttons, links, text fields, checkboxes, and other interactive elements based on their visual appearance in an image.
  • Coordinate Extraction: Provides precise bounding box coordinates and center points for identified elements.
  • Iterative Refinement: Employs a strategy of initial visual estimation, followed by verification with small crops, and then grid-based searching in nearby regions if the initial guess is incorrect.
  • Use Case: Automating a desktop application where UI elements change dynamically or lack stable identifiers. You can use this skill to find a "Submit" button in a screenshot to click it.

Quick Start

Use the find-ui-element skill to locate the button with the text 'Login' in the provided screenshot.

Frequently Asked Questions about find-ui-element

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

FAQPage Schema
How do I locate UI elements in a screenshot for automation when direct selectors are unavailable?

You can locate UI elements visually by identifying buttons, links, and text fields based on their appearance in a screenshot. This visual analysis approach provides precise bounding box coordinates and center points for automated workflows when direct selectors are unavailable.

What is the best way to extract coordinates from a screenshot for UI testing?

The best way to extract coordinates is using image processing scripts that perform visual analysis to generate precise bounding boxes and center points for identified elements. This method supports UI testing by verifying locations through iterative crops and grid-based searching.

Can I find dynamically changing buttons in desktop applications using screenshot analysis?

Yes, you can find dynamically changing buttons in desktop applications using screenshot analysis. This visual identification method locates interactive elements based on appearance rather than stable identifiers, providing bounding box coordinates to automate clicks on dynamically changing interfaces.

How does visual search refine bounding box estimates for UI elements?

Visual search refines bounding box estimates through an iterative process of initial visual estimation, verification using small image crops, and grid-based searching in nearby regions. This strategy ensures precise coordinate extraction even when the initial visual guess for a UI element is incorrect.

When do I need visual element identification instead of DOM selectors for automated workflows?

You need visual element identification instead of DOM selectors when automating graphical applications or websites where UI elements change dynamically or lack stable identifiers. It enables interaction with buttons and text fields based purely on their visual appearance within a screenshot.

Does find-ui-element work with computer vision applications for coordinate extraction?

Yes, find-ui-element works with computer vision applications by utilizing image processing scripts for precise coordinate extraction. It identifies user interface elements within screenshots and generates bounding box coordinates to support automated workflows and computer vision applications.