document-ocr
70 / 100 · Review before installing
Check before installing.
Convert scanned PDFs and document images into clean Markdown using docling for layout (figures, tables, reading order) plus a vision-language OCR model. Use when a user needs high-quality OCR of scanned documents, historical literature, or photographed pages — preserving multi-column reading order, diacritics, special characters, and figures. Supports local vLLM/Ollama servers and cloud vision APIs (OpenAI, Anthropic). Assumes an OCR backend already exists.
What this skill can do
Runs commands on your computer
Can call paid AI services billed to you
Downloads and installs other software
Sends data to these websites: api.anthropic.com
Safer alternatives
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'document-ocr' ] || [ -L ~/.agents/skills/'document-ocr' ]; then echo 'A skill folder named document-ocr already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/boisenoise/skills-collections' "$d" && git -C "$d" checkout --quiet '419c39fde874b8baecbb36a397b967e0190a2ece' -- 'skills/brunoasm-document_ocr' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/brunoasm-document_ocr' ~/.agents/skills/'document-ocr' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'document-ocr' ~/.claude/skills/'document-ocr' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/boisenoise/skills-collections/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | 419c39f | 70 |
| 2026-11-08 | 5fe45e5 | 70 |
| 2026-11-06 | b89b2f5 | 50 |