book-image-renamer

Extract book metadata from cover images with PaddleOCR and generate safe filenames.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/pingqLIN/UniText --skill book-image-renamer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: book-image-renamer
Source: https://github.com/pingqLIN/UniText/tree/main/runtime/skills/book-image-renamer
Command: npx skills add https://github.com/pingqLIN/UniText --skill book-image-renamer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, Pillow, paddleocr, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates the identification of book cover images, extracts visible metadata via OCR, and builds safe rename plans to organize large image collections without overwriting existing files.

Core Features & Use Cases

  • OCR-based extraction of book title and author from covers and backs using PaddleOCR.
  • Compare extracted data against a curated metadata template to generate edition-level filenames.
  • Plan and apply renames while validating against collisions and ensuring only verified matches are renamed.
  • Use when a folder contains mixed images or multiple shots per book to consolidate into a canonical filename.

Quick Start

Place your book images folder and run the scan, plan, and apply workflow to generate and apply safe renames.

Frequently Asked Questions about book-image-renamer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically rename book cover images using OCR metadata?

Book cover image renaming works by running local PaddleOCR to extract visible metadata, matching it against a curated template, and generating verified, edition-level filenames. The scan, plan, and apply workflow ensures only validated matches are renamed to prevent file overwrites.

Can I use PaddleOCR to extract ISBN and publisher data from book photos?

Yes, PaddleOCR extracts ISBN and publisher data from book photos during the local OCR scan. Optional AI-assisted verification further validates this extracted metadata against author, title, publisher, year, and ISBN levels to ensure accuracy and safety before applying renames.

Does this book image renaming tool prevent file overwrites and naming collisions?

Yes, the book image renaming process prevents file overwrites and naming collisions by validating against existing files during the plan phase. It ensures only verified matches are renamed, safely organizing large image collections without overwriting your existing files.

How do I handle folders with multi-shot book cover sets?

Handle folders with multi-shot book cover sets by running the scan, plan, and apply workflow. The process consolidates mixed images and multiple shots per book into a single canonical, edition-level filename using local OCR validation and metadata matching.

Do I need an internet connection for on-device book cover OCR?

No, you do not need an internet connection for on-device book cover OCR. The skill uses local PaddleOCR for on-device extraction, though an optional AI-assisted verification feature is available to improve metadata accuracy and safety if needed.