skills.rest
smykla-skalski
smykla-skalskiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ocr-finder

Detects and extracts text from image files with bounding boxes and click coordinates using EasyOCR.

3|1|Updated Feb 12, 2026
Search Tags:#ocr#ui automation#coordinates#easyocr#screenshot analysis#image text
One-click install
npx skills add https://github.com/smykla-skalski/sai --skill ocr-finder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-finder
Source: https://github.com/smykla-skalski/sai/tree/main/ocr-finder/skills/ocr-finder
Command: npx skills add https://github.com/smykla-skalski/sai --skill ocr-finder

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you locate specific text within images and provides precise coordinates for interaction, which is crucial when graphical user interfaces lack accessibility features or when working with screenshots.

Core Features & Use Cases

  • Text Detection: Identifies and extracts text from various image formats.
  • Coordinate Extraction: Returns bounding boxes and click-ready coordinates for detected text.
  • Use Case: When automating UI interactions on a desktop application, you can use this Skill to find the exact position of a button labeled "Save" in a screenshot, allowing your automation script to click it accurately.

Quick Start

Use the ocr-finder skill to find the text "Confirm" in the image file named 'dialog.png'.

Frequently Asked Questions about ocr-finder

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

FAQPage Schema
How do I get click coordinates for text found in a screenshot?▼

To get click coordinates for text in a screenshot, this Skill detects the text and returns precise bounding boxes. You use these coordinates to automate UI interactions accurately.

What is the best way to extract text from an image for UI automation?▼

The best way to extract text for UI automation is using EasyOCR, which this Skill leverages to recognize text in any image format. It provides locations needed to interact with missing UI elements.

Can I find specific text like a button label in an image file?▼

Yes, you can locate specific text like a button labeled "Save" in an image file. The Skill searches the provided image and returns exact coordinates for that text string.

Does EasyOCR work with any image format for text detection?▼

Yes, EasyOCR works with any image format for text detection. The Skill processes your image files to extract text and bounding boxes without requiring programmatic access to UI elements.

When do I need to use image text coordinates for automation?▼

You need image text coordinates for automation when graphical interfaces lack accessibility features. This allows your scripts to click targets in screenshots when programmatic access is unavailable.

Related Skills

Explore More Software Engineering Skills→
manashmandalmanashmandal

imggen

Generate images from text prompts using OpenAI image APIs and extract OCR text from images.

Community
Basic
X-School-AcademyX-School-Academy
19

find-ui-element

Identify UI elements in screenshots and generate bounding box coordinates.

Official
Intermediate
glideappsglideapps
10

glide

Automate end-to-end Glide app building with agents, browser automation, and APIs.

Official
Advanced
code-yeongyucode-yeongyu
67.6k

frontend-ui-ux

Convert visual design ideas into responsive HTML/CSS/JS components.

Community
Intermediate