← Back to Skills Marketplace
322
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install image-deduplicator
Description
Detect and remove exact or similar duplicate images in folders using perceptual and MD5 hashing with configurable similarity and actions.
README (SKILL.md)
Image Deduplicator
Find and remove duplicate or similar images in a folder using perceptual hashing. Use when user wants to clean up duplicate images, find near-duplicates, or deduplicate an image dataset.
Features
- Exact Duplicates: Find images with identical content
- Similar Images: Detect visually similar images (threshold configurable)
- Hash-based: Fast MD5 hashing for exact duplicates
- Perceptual Hash: pHash for finding similar images
- Batch Processing: Process large image folders
- Multiple Actions: List, delete, or move duplicates
Usage
# Find exact duplicates
python scripts/dedupe.py scan /path/to/images/
# Find similar images (90% similarity)
python scripts/dedupe.py scan /path/to/images/ --threshold 90
# Delete duplicates (keeps first occurrence)
python scripts/dedupe.py scan /path/to/images/ --action delete
# Move duplicates to a folder
python scripts/dedupe.py scan /path/to/images/ --action move --output /path/to/dupes/
Examples
$ python scripts/dedupe.py scan ./images/
Scanning images...
Found 150 images
Computing hashes...
Found 5 duplicate groups:
Group 1 (3 files):
./images/photo1.jpg
./images/photo1_copy.jpg
./images/photo1_final.jpg
Group 2 (2 files):
./images/screenshot.png
./images/screenshot (1).png
Total: 5 duplicate groups, 8 duplicate files
Installation
pip install pillow imagehash
Options
--threshold: Similarity threshold (0-100), default: 100 (exact)--action: What to do with duplicates (list, delete, move)--output: Output folder for --action move--extensions: File extensions to scan (default: jpg,jpeg,png,bmp)
Usage Guidance
This skill is coherent with its stated purpose (finding and removing duplicate image files) and does not request credentials or network access. However, the documentation claims a configurable similarity threshold (e.g., 90% similarity) while the included script does not implement a similarity-distance comparison — it only groups images whose perceptual hash strings are identical. Before using destructive actions (delete/move): 1) run with --action list to review groups, 2) back up your images or test on a small subset, 3) inspect or modify the script if you need true similarity (implement Hamming-distance comparisons of phash values), and 4) ensure pillow and imagehash are installed in a controlled environment. If you rely on the threshold feature, treat the current implementation as incomplete and contact the author or modify the code to compute and compare hash distances rather than string equality.
Capability Analysis
Type: OpenClaw Skill
Name: image-deduplicator
Version: 1.0.0
The skill bundle provides a legitimate utility for finding and removing duplicate images using MD5 and perceptual hashing (pHash). The Python script `scripts/dedupe.py` performs standard file operations such as directory traversal, hashing, and file deletion/movement based on explicit user commands, and it includes a confirmation prompt before deleting files.
Capability Assessment
Purpose & Capability
Name and description match the provided code and SKILL.md: the script scans folders, computes MD5 and perceptual hashes, and can list/delete/move duplicate files. The required capabilities (none) are proportionate to the task.
Instruction Scope
SKILL.md claims a configurable similarity threshold (e.g., 90%) for finding similar images. The script only uses the threshold to decide whether to call perceptual hashing (use_phash when threshold < 100) but then groups files by exact hash string equality. There is no comparison of Hamming distance or other similarity measure to support a numeric threshold. This is a functional mismatch: the instructions promise near-duplicate detection by threshold but the code only finds exact hash matches (or identical perceptual hash strings).
Install Mechanism
There is no install spec (instruction-only install). SKILL.md recommends 'pip install pillow imagehash', which is reasonable. No remote downloads or obscure installers are used. Because the code is included, nothing is written to disk by an installer beyond normal package installation.
Credentials
The skill requests no environment variables, no credentials, and references only local file system paths supplied by the user. This is proportionate to an image dedupe tool.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skill configurations. It runs as a user-invoked CLI script and performs local file operations only.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install image-deduplicator - After installation, invoke the skill by name or use
/image-deduplicator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Image Deduplicator.
- Find and remove exact or similar images using MD5 and perceptual hash.
- Configurable similarity threshold for near-duplicate detection.
- Supports batch processing and large image folders.
- Multiple actions for duplicates: list, delete, or move.
- Easy CLI usage with clear options for customizing scans.
Metadata
Frequently Asked Questions
What is Image Deduplicator?
Detect and remove exact or similar duplicate images in folders using perceptual and MD5 hashing with configurable similarity and actions. It is an AI Agent Skill for Claude Code / OpenClaw, with 322 downloads so far.
How do I install Image Deduplicator?
Run "/install image-deduplicator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Image Deduplicator free?
Yes, Image Deduplicator is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Image Deduplicator support?
Image Deduplicator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Image Deduplicator?
It is built and maintained by Mingo_318 (@mingo-318); the current version is v1.0.0.
More Skills