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.
Install
npx skills add aktsmm/Agent-Skills --skill ocr-super-suryanpx skills add aktsmm/Agent-Skills --skill ocr-super-surya -a claude-code -gnpx skills add aktsmm/Agent-Skills --skill ocr-super-surya -a codex -ggemini skills install https://github.com/aktsmm/Agent-Skills.git --path ocr-super-suryagh skill install aktsmm/Agent-Skills ocr-super-suryagit clone --depth 1 https://github.com/aktsmm/Agent-Skills /tmp/aktsmm__Agent-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/aktsmm__Agent-Skills/ocr-super-surya ~/.claude/skills/ocr-super-surya # Claude Code
cp -R /tmp/aktsmm__Agent-Skills/ocr-super-surya ~/.agents/skills/ocr-super-surya # Codex, Cursor, Gemini CLI, Copilot, OpenCode