Performs optical character recognition on local image files to extract text content.

Install

mkdir -p .claude/skills/ocr-scalyclaw && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19449" && unzip -o skill.zip -d .claude/skills/ocr-scalyclaw && rm skill.zip

Installs to .claude/skills/ocr-scalyclaw

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Extract text from images using Tesseract OCR
44 charsno explicit “when” trigger
Beginner

Key capabilities

  • Extract text from images
  • Support multiple image formats including PNG and JPG
  • Configure Tesseract language codes
  • Adjust page segmentation modes
  • Provide confidence scores for extracted text

How it works

The skill utilizes Tesseract OCR to process image files based on provided language and segmentation settings. It returns the recognized text along with metadata regarding accuracy and content volume.

Inputs & outputs

You give it
Image file path
You get back
Extracted text, confidence score, and line/word counts

When to use OCR

  • Extract text from screenshots
  • Read data from receipt images
  • Digitize text documents
  • Process images in automation pipelines

About this skill

OCR Skill

Extract text from images including receipts, screenshots, documents, and photos of text using Tesseract OCR.

Input

  • file_path (string, required): Path to image file (PNG, JPG, TIFF, BMP, WebP)
  • language (string, optional, default "eng"): Tesseract language code (e.g. "eng", "fra", "deu", "eng+fra" for multiple)
  • psm (integer, optional, default 3): Page segmentation mode (3=auto, 6=single block, 7=single line, 11=sparse text)

Output

  • text (string): Extracted text
  • confidence (float): Average confidence score (0-100)
  • line_count (integer): Number of text lines
  • word_count (integer): Number of words

Prerequisites

Tesseract OCR

How it compares

It provides structured output including confidence scores and line counts, which is more useful for automated pipelines than raw text extraction.

Compared to similar skills

OCR side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
OCR (this skill)04moReviewBeginner
data-engineering137moReviewAdvanced
crawl4ai218moReviewIntermediate
data-cleaning-pipeline134moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry