skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / Document Processing / Smart OCR Skill by @claude-office-skills
The skill is the smart-ocr folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Extracts text from photos, screenshots and scanned documents using PaddleOCR, with support for many languages.
Shows engine initialisation, how to read results with boxes and confidence scores and which languages are supported. A practical base for digitising paper records.
The original SKILL.md is organised into these sections:
Written and maintained by @claude-office-skills. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
# Smart OCR Skill
## Overview
This skill enables intelligent text extraction from images and scanned documents using **PaddleOCR** - a leading OCR engine supporting 100+ languages. Extract text from photos, screenshots, scanned PDFs, and handwritten documents with high accuracy.
## How to Use
1. Provide the image or scanned document
2. Optionally specify language(s) to detect
3. I'll extract text with position and confidence data
**Example prompts:**
- "Extract all text from this screenshot"
- "OCR this scanned PDF document"
- "Read the text from this business card photo"
- "Extract Chinese and English text from this image"
## Domain Knowledge
### PaddleOCR Fundamentals
```python
from paddleocr import PaddleOCR
# Initialize OCR engine
ocr = PaddleOCR(use_angle_cls=True, lang='en')
# Run OCR on image
result = ocr.ocr('image.png', cls=True)
# Result structure: [[box, (text, confidence)], ...]
for line in result[0]:
box = line[0] # [[x1,y1], [x2,y2], [x3,y3], [x4,y4]]
…
Excerpt only, quoted from the author's repository. Open the repository for the complete file.