Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstruction, or cross-backend quality. Load for OCR behavior and A/B quality work, not ordinary PDF text extraction.
安装
npx skills add xberg-io/xberg --skill ocr-pipeline-and-qualitynpx skills add xberg-io/xberg --skill ocr-pipeline-and-quality -a claude-code -gnpx skills add xberg-io/xberg --skill ocr-pipeline-and-quality -a codex -ggemini skills install https://github.com/xberg-io/xberg.git --path .ai-rulez/skills/ocr-pipeline-and-qualitygh skill install xberg-io/xberg ocr-pipeline-and-qualitygit clone --depth 1 https://github.com/xberg-io/xberg /tmp/xberg-io__xberg
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/xberg-io__xberg/.ai-rulez/skills/ocr-pipeline-and-quality ~/.claude/skills/ocr-pipeline-and-quality # Claude Code
cp -R /tmp/xberg-io__xberg/.ai-rulez/skills/ocr-pipeline-and-quality ~/.agents/skills/ocr-pipeline-and-quality # Codex, Cursor, Gemini CLI, Copilot, OpenCode