Use Case
smart_ocr is a powerful AI agent skill that extends your assistant with new capabilities. Extract text from images and scanned documents using PaddleOCR - supports 100+ languages This guide walks you through installing smart_ocr, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install smart_ocr: npx clawhub@latest --dir ~/.claude/skills install smar
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to documents & notes to trigger smart_ocr
Review the output and refine your prompt for better results
Combine smart_ocr with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing smart_ocr
Help me get started with smart_ocr
What can smart_ocr do for my documents & notes workflow?
Show me an example of using smart_ocr
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install smarOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install smarβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/smar/π‘Extract and place the folder at the path above, then restart your agent.