jftuga

Claude Image Renamer — AI skill for Claude Code

AI community

AI-powered image renaming script that generates descriptive filenames for screenshots.

How to install Claude Image Renamer

This entry records only its repository, not the path inside it, so there is no exact command to give. Open jftuga/claude-image-renamer and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Image Renamer does

AI-powered image renaming script that generates descriptive filenames for screenshots.

Alternatives in AI

Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
Generative Media Skills — Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI) 3k ★
Claude Skill Aso Appstore Screenshots — A Claude Code skill that generates high-converting App Store screenshots for your iOS app 1.2k ★

README

claude-image-renamer

AI-powered image renaming script that generates descriptive filenames for screenshots. Uses OCR text extraction combined with Claude's vision capabilities to analyze image content and rename files to a searchable, lowercase, underscore-separated format.

Features

Automatically sanitizes macOS screenshot filenames containing special Unicode characters
Extracts text from images via OCR to improve rename accuracy
Uses Claude AI to analyze both the image and extracted text
Generates clean, descriptive filenames (max 64 characters, lowercase with underscores)
Handles naming conflicts by automatically appending numeric suffixes (_1, _2, etc.)
Supports batch processing of multiple images in a single invocation

AI Disclaimer

The code in this repository was developed with the assistance of the Claude Sonnet LLM model by Anthropic.

Requirements

Claude Code CLI (claude)
ocr binary (optional, macOS only)

Installation

git clone https://github.com/jftuga/claude-image-renamer.git
cd claude-image-renamer
chmod 755 claude-image-renamer.sh

To build the optional OCR tool (macOS only):

This compiles ocr.swift using the macOS Vision framework. The script will function without the ocr binary, but providing OCR text improves Claude's ability to generate accurate filenames.

make

Usage

# Single file
./claude-image-renamer.sh "Screenshot 2025-12-29 at 10.03.10 PM.png"
# Renames to something like: vscode_python_debug_settings.png

# Multiple files
./claude-image-renamer.sh image1.png image2.png image3.png

# Using shell globbing
./claude-image-renamer.sh *.png
./claude-image-renamer.sh Screenshots/*.png

When processing multiple files, the script displays progress for each file and prints a summary upon completion showing how many files were processed successfully.