masterleopold

OCR — Development skill for Claude Code

Development community

Run OCR on existing book page captures (Vision + agent re-reading).

How to install OCR

Installs to ~/.claude/skills/masterleopold-book-capture-ocr/SKILL.md

Terminal

mkdir -p ~/.claude/skills/masterleopold-book-capture-ocr && curl -fsSL https://raw.githubusercontent.com/masterleopold/book-capture/HEAD/commands/ocr.md -o ~/.claude/skills/masterleopold-book-capture-ocr/SKILL.md

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

What OCR does

allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent argument-hint: " [--concurrency 5] [--claude-threshold 0.6]" description: "Run OCR on existing book page captures (Vision + agent re-reading)"

OCR Text Extraction

Run OCR on existing page captures. Requires `page_*` image files (WebP, or PNG for books captured before the WebP switch) to already exist in the captures directory.

Setup

PLUGIN_SCRIPTS = ${CLAUDE_PLUGIN_ROOT}/scripts
Resolve CAPTURES_BASE fro

Alternatives in Development

Product Vision — Brainstorm inspiring, achievable product vision statements 7.8k ★
Ccundo — Integrates seamlessly with Claude Code to provide granular undo functionality by reading directly from Claude 1.4k ★
Setup Video Vision — Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies 1.3k ★