skills.rest
junchenghuo
junchenghuoCOMMUNITY
Explore all skills by this author →
GitHub

image-content-search

Extract text from images via OCR and search for keywords.

3|Updated Mar 11, 2026
Search Tags:#ocr#text extraction#document analysis#image search#computer vision#keyword search
One-click install
npx skills add https://github.com/junchenghuo/openclaw-biz-agent --skill image-content-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-content-search
Source: https://github.com/junchenghuo/openclaw-biz-agent/tree/main/qa/.agents/skills/image-content-search
Command: npx skills add https://github.com/junchenghuo/openclaw-biz-agent --skill image-content-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pillow, pytesseract, and includes scripts (resource) components.

What problem does it solve?

This Skill allows you to search through a directory of images by extracting text from them using Optical Character Recognition (OCR) and then performing keyword searches on the extracted text.

Core Features & Use Cases

  • OCR on Images: Extracts text content from various image formats (JPG, PNG, etc.).
  • Keyword Search: Finds images containing specific keywords within their OCR'd text.
  • Use Case: Useful for searching through collections of screenshots, posters, or scanned documents where you need to find specific information embedded within the images.

Quick Start

Use the image-content-search skill to find images in the '/path/to/screenshots' directory that contain the keyword 'error'.

Frequently Asked Questions about image-content-search

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

FAQPage Schema
How do I search for text inside a directory of images?▼

To search for text inside images, this Skill performs Optical Character Recognition (OCR) on a specified directory to extract text content, then matches your specific keywords against the extracted text to find relevant images.

Can I use OCR to find specific keywords in scanned documents and screenshots?▼

Yes, you can use OCR to find specific keywords in scanned documents and screenshots. The Skill extracts text from various image formats like JPG and PNG, enabling you to locate specific information embedded within your image collections.

Does pytesseract support language-specific OCR for image text extraction?▼

Yes, pytesseract supports language-specific OCR for image text extraction. The Skill allows you to specify languages to accurately extract text content from images before performing keyword searches on the results.

What is the best way to extract text content from multiple image formats?▼

The best way to extract text content from multiple image formats is using this Skill, which leverages pillow and pytesseract to process images in a specified directory and enables keyword search across the extracted text.

What are the limitations of using computer vision for keyword search in images?▼

A limitation of using computer vision for keyword search is that accuracy depends entirely on the OCR results. If pytesseract cannot clearly extract text from an image, the keyword search will fail to find matching content.

Related Skills

Explore More Software Engineering Skills→
ekkus93ekkus93

image-ocr

Extract text from image files using Tesseract OCR.

Community
Intermediate
DaddyElonMusk69DaddyElonMusk69

doc-reader

Extract text from PDFs with OCR for scanned pages.

Community
Intermediate
johnlindquistjohnlindquist
24

gemini-image

Analyze images and extract text using Gemini Pro's vision API.

Community
Basic
richardnguyen0715richardnguyen0715

ocr-and-documents

Extract text from PDFs and scanned documents using OCR.

Community
Advanced