Opencv
OpenCV computer vision library. Use for image processing.From its SKILL.md
npx -y skills add G1Joshi/Agent-Skills --skill opencvAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 12 stars12 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.1 KB, 263 tokens by cl100k_base, as published. Nobody here has run it
OpenCV
OpenCV is the fundamental library for Image Processing. v5.0 (2025) modernizes deep learning support and licensing.
When to Use
- Image Manipulation: Resizing, cropping, color space conversion (BGR -> RGB).
- Classic CV: Edge detection (Canny), Feature matching (SIFT/ORB).
- Video I/O: Reading/Writing webcams or video files.
Core Concepts
BGR
OpenCV reads images as Blue-Green-Red (not RGB) by default. History quirks.
cv::Mat
The core matrix structure (in C++). In Python, it's just a NumPy array.
DNN Module
Running darknet/onnx models directly in OpenCV (lightweight inference).
Best Practices (2025)
Do:
- Use it for Preprocessing:
cv2.resize()is highly optimized. - Use
headless:pip install opencv-python-headlessfor server deployments (smaller, no GUI deps).
Don't:
- Don't implement Deep Learning training: Use PyTorch. Use OpenCV only for inference/preprocessing.
References
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.