Scan local archives for duplicate files, similar images, similar videos, empties, and related cleanup targets before deleting or reorganizing them.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Find duplicate and visually similar media before cleanup with Czkawka"
slug: "find-duplicate-and-visually-similar-media-before-cleanup-with-czkawka"
description: "Scan local archives for duplicate files, similar images, similar videos, empties, and related cleanup targets before deleting or reorganizing them."
github_stars: 30600
verification: "security_reviewed"
source: "https://github.com/qarmin/czkawka"
author: "qarmin"
publisher_type: "individual"
category: "Image & Creative Automation"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "qarmin/czkawka"
github_stars: 30600
---
# Find duplicate and visually similar media before cleanup with Czkawka
Scan local archives for duplicate files, similar images, similar videos, empties, and related cleanup targets before deleting or reorganizing them.
## Prerequisites
Czkawka CLI or GUI, local filesystem access
## Installation
Requirements and caveats from upstream:
- | Language | Rust | Rust | Rust | Python | Python/Obj-C | Python |
- **Python** - https://pypi.org/project/czkawka/
Basic usage or getting-started notes:
- **Easy to run, easy to compile** - minimal runtime and build dependencies, portable version available
- Each tool uses different technologies, so you can find instructions for each of them in the appropriate file:
- [Krokiet GUI (Slint frontend)](krokiet/README.md)</br>
- Source: https://github.com/qarmin/czkawka
- Extracted from upstream docs: https://raw.githubusercontent.com/qarmin/czkawka/HEAD/README.md
## Documentation
- https://github.com/qarmin/czkawka
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/find-duplicate-and-visually-similar-media-before-cleanup-with-czkawka/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.