ocr-scan

Community

OCR handwritten notes to Markdown.

Authorjeff-hamm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OCR is a practical solution for turning handwritten or scanned documents into searchable, editable Markdown text. This skill streamlines archival, note-taking, and information sharing by producing consistent Markdown output from image-based sources.

Core Features & Use Cases

  • Multi-backend OCR: supports copilot-cli, github-api, gemini, openai, anthropic, cursor, and easyocr to maximize transcription accuracy.
  • Per-image outputs: writes a .ocr.md file next to each source image with provenance and source references.
  • Directory support: recursively scans directories for image files and processes them in batch for large collections.
  • Model-quality selection: automatically selects the best available backend/model via a centralized registry.

Quick Start

Provide an image file path or directory to OCR and generate per-image Markdown transcripts.

Dependency Matrix

Required Modules

ai-backendseasyocr

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ocr-scan
Download link: https://github.com/jeff-hamm/ai-tools/archive/main.zip#ocr-scan

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.