image-ocr
Expert guide and implementations for OCR using Tesseract, EasyOCR, and cloud APIs with Python and Node.js.
Install
npx skills add https://github.com/fearovex/claude-config --skill image-ocrStats
| Total installs | 910 |
| Weekly installs | 902 |
| GitHub stars | — |
| First seen | Mar 4, 2026 |
| Source | @fearovex/claude-config |
Summary
- Supports six OCR tools with decision tree: Tesseract and EasyOCR for local processing, PaddleOCR for CJK and tables, Google Vision and AWS Textract for cloud accuracy, Claude Vision for semantic understanding
- Includes full preprocessing pipeline (grayscale, deskew, denoise, binarization, morphological cleanup) to maximize accuracy on real-world images
- Provides Python and Node.js implementations with confidence filtering, bounding box extraction, and form/table parsing for invoices and structured documents
- Covers PDF text extraction with OCR fallback for scanned pages, post-processing regex patterns, and batch processing templates
Tags
Related skills
| Skill | Installs | vs image-ocr |
|---|---|---|
| nano-banana | 0 | -910 |
| read-arxiv-paper | 906 | -4 |
| agent-memory-systems | 909 | -1 |
| trigger-tasks | 923 | +13 |
| grimoire-uniswap | 946 | +36 |
FAQ
- How many installs does image-ocr have?
- image-ocr has 910 total installs and 902 installs this week.
- Where is image-ocr hosted?
- image-ocr is published by @fearovex/claude-config at https://github.com/fearovex/claude-config.
- When was image-ocr first indexed?
- OrangeBot.AI first indexed image-ocr on Mar 4, 2026.
- How do I install image-ocr?
- Run: npx skills add https://github.com/fearovex/claude-config --skill image-ocr