Agent skill · writing content · claude-office-skills

smart-ocr

>

Why this skill is useful

Provides specific implementation details and configuration options for using PaddleOCR that the AI wouldn't reliably generate on its own.

What it needs

Requires paddleocr, pdf2image installed locally. About 5k tokens when loaded. Last updated 2026-01-31. 363 stars on the source repository.

What this skill does

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 Supported Languages Configuration Options Processing Different Sources Image Files PDF Files (Scanned) URLs and Bytes Result Processing Text Layout Reconstruction Best Practices 1. Preprocess Images: Improve quality before OCR 2. Choose Correct Language: Specify language for better accuracy 3. Handle Multi-column: Process columns separately 4. Filter Low Confidence: Skip results below threshold 5. Batch Processing: Process multiple images efficiently Common Patterns Image Preprocessing Batch OCR with Progress Examples Example 1: Business Card Reader Example 2: Receipt Scanner Example 3: Multi-language Document Limitations Handwritten text accuracy varies Very small text may not be detected Complex backgrounds reduce accuracy Rotated text needs angle classification GPU recommended for best performance Installation Resources PaddleOCR GitHub Model Zoo Multi-language Support

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills claude-office-skills/smart-ocr

View the source on GitHub

Browse the @skills marketplace