Extract text from images and scanned PDFs using OCR. Supports 100+ languages, table detection, structured output (markdown/JSON), and batch processing.
Install
npx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processornpx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a claude-code -gnpx skills add dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor -a codex -ggemini skills install https://github.com/dkyazzentwatwa/chatgpt-skills.git --path ocr-document-processorgh skill install dkyazzentwatwa/chatgpt-skills ocr-document-processorgit clone --depth 1 https://github.com/dkyazzentwatwa/chatgpt-skills /tmp/dkyazzentwatwa__chatgpt-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/dkyazzentwatwa__chatgpt-skills/ocr-document-processor ~/.claude/skills/ocr-document-processor # Claude Code
cp -R /tmp/dkyazzentwatwa__chatgpt-skills/ocr-document-processor ~/.agents/skills/ocr-document-processor # Codex, Cursor, Gemini CLI, Copilot, OpenCode