Back to skills
image-ocr
by xejrax
PDF & Documents—Not yet rated
Your rating
Brief
Extract text from images using Tesseract OCR.
Description
What This Skill Does
Extracts text from images using Tesseract OCR. Supports PNG, JPEG, TIFF, and BMP formats. Language can be specified per run.
Runs entirely locally, so images are never sent to a cloud service.
When to Use It
- Pulling text from a screenshot to copy into a document
- Converting a scanned form into editable text
- Reading printed labels from product photos
- Extracting captions from saved social media images
- Batch processing image files to get searchable text
Example Workflow
INPUT
User asks: extract the text from this scanned invoice 'invoice.png'
AGENT
- 1
Receives the image path 'invoice.png'
- 2
Runs Tesseract OCR on the file with default English language setting
- 3
Captures stdout from the Tesseract process
- 4
Returns the extracted text to the user
OUTPUT
Plain text content parsed from the invoice image
Requirements
- tesseract binary installed on the system
Installation
clawhub install xejrax/image-ocrRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.