$npx skillfedfor your agent

Computer Vision

Computer Vision provides ready-to-use implementations for core visual recognition tasks including classification, detection, segmentation, and pose estimation. The skill includes model architectures, transfer learning with pre-trained networks, and data preprocessing pipelines to accelerate development.

Computer Vision implements image classification, object detection, segmentation, and pose estimation using PyTorch and TensorFlow.

AI-generated summary based on this skill's SKILL.md

299 45 MITupdated by aj-geddes

Decision gist · record as of 2026-03-04

Computer Vision implements image classification, object detection, segmentation, and pose estimation using PyTorch and TensorFlow. Computer Vision provides ready-to-use implementations for core visual recognition tasks including classification, detection, segmentation, and pose estimation. The skill includes model architectures, transfer learning with pre-trained networks, and data preprocessing pipelines to accelerate development.

manual: git clone https://github.com/aj-geddes/useful-ai-prompts → cp -r useful-ai-prompts/skills/computer-vision ~/.claude/skills/computer-vision
skills/computer-vision/SKILL.md · version f4d8a4e7

Use it when

  • Computer Vision includes object detection implementations covering architectures like YOLO and Faster R-CNN.
  • Yes, Computer Vision covers both semantic and instance segmentation techniques for pixel-level analysis.

Verify before relying

Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

aj-geddes/useful-ai-prompts/computer-vision · repository language: Shell

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What computer vision image classification approaches does this skill support?

Computer Vision supports image classification through PyTorch and TensorFlow implementations, including CNN architectures and transfer learning with pre-trained models like ResNet. The skill provides ready-to-use model implementations and data preprocessing pipelines to accelerate your classification projects.

How does Computer Vision handle object detection tasks?

Computer Vision includes object detection implementations covering architectures like YOLO and Faster R-CNN. The skill provides bounding box detection and localization frameworks with transfer learning capabilities, enabling you to build detection systems efficiently using pre-trained networks.

Can Computer Vision perform semantic segmentation and instance segmentation?

Yes, Computer Vision covers both semantic and instance segmentation techniques for pixel-level analysis. The skill includes implementations of architectures like U-Net, DeepLab, and Mask R-CNN, providing comprehensive segmentation solutions for detailed visual understanding tasks.

What pose estimation and activity recognition capabilities are included?

Computer Vision provides implementations for building pose estimation and human activity recognition systems. These tools enable you to develop applications that analyze human movement and behavior, complementing the skill's broader visual understanding capabilities.

How can I apply transfer learning with Computer Vision models?

Computer Vision facilitates transfer learning through pre-trained architectures and ready-to-use model implementations. The skill accelerates development by providing transfer learning pipelines with established networks, reducing training time and improving performance on your specific vision tasks.

What preprocessing and augmentation features does Computer Vision offer?

Computer Vision includes image preprocessing and data augmentation pipelines to prepare your datasets effectively. These tools support various visual recognition tasks and help optimize model training across classification, detection, segmentation, and other computer vision applications.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

Computer Vision

Overview

Computer vision enables machines to understand visual information from images and videos, powering applications like autonomous driving, medical imaging, and surveillance.

When to Use

  • Image classification and object recognition tasks
  • Object detection and localization in images
  • Semantic or instance segmentation projects
  • Pose estimation and human activity recognition
  • Face recognition and biometric systems
  • Medical imaging analysis and diagnostics

Computer Vision Tasks

  • Image Classification: Categorizing images into classes
  • Object Detection: Locating and classifying objects in images
  • Semantic Segmentation: Pixel-level classification
  • Instance Segmentation: Detecting individual object instances
  • Pose Estimation: Identifying human body joints
  • Face Recognition: Identifying individuals in images

Popular Architectures

  • Classification: ResNet, VGG, EfficientNet, Vision Transformer
  • Detection: YOLO, Faster

(truncated - see the full file via the links below)

File tree — 3 files
skills/computer-vision/SKILL.md
skills/computer-vision/scripts/scaffold-analysis.sh
skills/computer-vision/templates/notebook-template.py

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Implement image classification and object detection models using PyTorch/TensorFlow”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Neural Network Design
by aj-geddes · aj-geddes/useful-ai-prompts

Master the fundamentals of constructing neural networks across multiple paradigms—from convolutional layers for image processing to recurrent units for sequences and transformer blocks for attention-based learning. This skill covers architecture selection, layer composition, normalization strategies, and regularization approaches to help you tailor models to your problem domain.

MITupdated Mar 2026
★ 299repo stars
Deep Learning
by pluginagentmarketplace · pluginagentmarketplace/custom-plugin-data-engineer

Master production-grade deep learning using PyTorch, covering neural architectures, transformer models, and optimization techniques. Learn training best practices including mixed precision, gradient management, and deployment strategies for real-world applications.

no license declared → metadata onlyupdated Jan 2026
★ 4repo stars
pytorch-lightning
by NousResearch · NousResearch/hermes-agent

PyTorch Lightning transforms raw PyTorch code into clean, organized training workflows by handling device management, distributed strategies (DDP, FSDP, DeepSpeed), and logging automatically. Define your model as a LightningModule, pass it to Trainer with your data, and let the framework manage GPU/TPU switching, mixed precision, checkpointing, and callbacks—reducing typical training code from 40+ lines to 15.

MITupdated Jul 2026
★ 221,503repo stars
ml-model-training
by secondsky · secondsky/claude-skills

Build and evaluate machine learning models across scikit-learn, PyTorch, and TensorFlow with a structured workflow covering data preparation, feature engineering, model selection, and performance assessment. Learn to handle common pitfalls like data leakage, class imbalance, overfitting, and hyperparameter tuning mistakes through best practices and code examples.

MITupdated Jul 2026
★ 196repo stars
ML Model Training
by aj-geddes · aj-geddes/useful-ai-prompts

ML Model Training guides you through building and optimizing machine learning models across three major frameworks. Learn data preparation, feature engineering, algorithm selection, and hyperparameter tuning with practical examples for classification, regression, and clustering.

MITupdated Mar 2026
★ 299repo stars
Matlab Import External Ai Model
by matlab · matlab/matlab-agentic-toolkit

Bring trained deep learning models from PyTorch, ONNX, or Keras into MATLAB as dlnetwork objects. The skill handles .pt2 exported programs, traced .pt files, .onnx models, and Keras 3 files, with guidance on input sizing, custom layer implementation, and numeric verification against source frameworks.

no license declared → metadata onlyupdated Jul 2026
★ 841repo stars

More skills Classification Modeling (MIT) · Model Hyperparameter Tuning (MIT)

Tags
neural-networksimage-processingdeep-learning-frameworksmodel-architecturesreal-world-applicationstraining-evaluationfeature-extractionvisual-analytics