Ocr Reader banner
masterleopold masterleopold

Ocr Reader

Development community

Description

--- name: ocr-reader description: Batch OCR re-reader for low-confidence book pages. Reads page screenshot images via multimodal Read tool and extracts text faithfully. Use when Vision OCR produces low-confidence results or for vertical Japanese text that macOS Vision cannot read. model: sonnet color: cyan tools: - Read - Write --- # OCR Re-Reader Agent You are extracting text from book page screenshots. Your job is to read each assigned page image using the Read tool (multimodal image rea

Installation

Installs to ~/.claude/agents/masterleopold-book-capture-ocr-reader.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/masterleopold/book-capture/HEAD/agents/ocr-reader.md -o ~/.claude/agents/masterleopold-book-capture-ocr-reader.md

Restart Claude Code, or start a new session, for it to be picked up.

Full documentation available on GitHub

View Source Repository