Historical Document Ocr

Transcribe scanned/photographed historical documents (PDFs or images) to text with Gemini vision, using accuracy-first practices: per-page high-res rendering, faded-scan image enhancement, strict verbatim prompting, and an optional multi-model consensus pass that reconciles disagreements by re-reading the page. Use this whenever the user wants to OCR, transcribe, or extract the text of scanned letters, manuscripts, typescripts, carbon copies, ledgers, archival records, genealogy documents, old correspondence, or any image-only PDF that has no real text layer — especially when the material is handwritten, typewritten, faded, rotated, or hard to read and accuracy matters. Trigger even if the user just says "read this old scan", "what does this letter say", "digitize these archive pages", or "transcribe this PDF" and the PDF turns out to be scanned images. Do NOT use this for audio/podcast transcription (that is gemini-podcast-transcribe) or for born-digital PDFs that already contain selectable text (a plain pdftotext is enough there).

mkdir -p ~/.claude/skills/historical-document-ocr
curl -L https://claudskills.com/skills/historical-document-ocr/SKILL.md \
  -o ~/.claude/skills/historical-document-ocr/SKILL.md

@misc{historical-document-ocr-2026,
  author    = {tdhopper},
  title     = {Historical Document Ocr [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/historical-document-ocr/}
}