AGENT SKILL

image-ocr

Extract text from images using Tesseract OCR

License 许可
MIT
最近更新
2026-07-28
Stars
★ 40
Forks
1

01 前言 Front Matter

name
image-ocr
metadata
{ "openclaw": { "emoji": "👁️", "requires": { "bins": [ "tesseract" ] } } }
description
Extract text from images using Tesseract OCR

02 资源文件 1

03 SKILL.md 正文

Image OCR

Extract text from images using Tesseract OCR. Supports multiple languages and image formats including PNG, JPEG, TIFF, and BMP.

Commands

# Extract text from an image (default: English)
tesseract "screenshot.png" stdout -l eng

# Extract text with a specific language
tesseract "document.jpg" stdout -l deu+eng --psm 6

Runtime

The task workspace provides tesseract during setup. If it is unavailable, report the missing command as an environment problem instead of installing packages during the user task.

04 同仓库更多 Skills