ocr-super-surya
✓GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection. Supports 90+ languages with 2x accuracy over Tesseract.
Installation
SKILL.md
GPU-optimized OCR skill using Surya - a modern, high-accuracy OCR engine.
| Accuracy | 2x better than Tesseract (0.97 vs 0.88 similarity) | | GPU Support | PyTorch-based, CUDA optimized | | Languages | 90+ languages including CJK | | Layout | Document layout analysis, table recognition | | LaTeX | Inline math equation recognition |
⚠️ If CUDA = False but you have an NVIDIA GPU:
GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection. Supports 90+ languages with 2x accuracy over Tesseract. Source: aktsmm/agent-skills.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/aktsmm/agent-skills --skill ocr-super-surya- Source
- aktsmm/agent-skills
- Category
- #Documents
- Verified
- ✓
- First Seen
- 2026-02-01
- Updated
- 2026-02-18
Quick answers
What is ocr-super-surya?
GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection. Supports 90+ languages with 2x accuracy over Tesseract. Source: aktsmm/agent-skills.
How do I install ocr-super-surya?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/aktsmm/agent-skills --skill ocr-super-surya Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/aktsmm/agent-skills
Details
- Category
- #Documents
- Source
- skills.sh
- First Seen
- 2026-02-01