Setup & Installation
openclaw skills install @xejrax/image-ocr
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install image-ocr
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
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: extract the text from this scanned invoice 'invoice.png'
AGENT
- 1Receives the image path 'invoice.png'
- 2Runs Tesseract OCR on the file with default English language setting
- 3Captures stdout from the Tesseract process
- 4Returns the extracted text to the user
OUTPUT
Plain text content parsed from the invoice image
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
tesseract binary installed on the system