skills.rest
jetmobsol
jetmobsolCOMMUNITY
Explore all skills by this author →
GitHub

ml-cv-specialist

Select ML/CV models and design training and inference pipelines.

Updated Mar 9, 2026
Search Tags:#machine learning#model selection#ai systems#computer vision#inference#pipeline design
One-click install
npx skills add https://github.com/jetmobsol/serene --skill ml-cv-specialist-jetmobsol
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ml-cv-specialist
Source: https://github.com/jetmobsol/serene/tree/main/.claude/skills/ml-cv-specialist
Command: npx skills add https://github.com/jetmobsol/serene --skill ml-cv-specialist-jetmobsol

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides expert guidance for designing, selecting, and deploying machine learning and computer vision systems, helping you build robust and efficient AI solutions.

Core Features & Use Cases

  • Model Selection: Recommends appropriate ML/CV models based on use case, performance, and cost.
  • Pipeline Design: Outlines architectures for training and inference pipelines.
  • API vs. Self-Hosted: Helps decide the optimal deployment strategy for ML models.
  • Use Case: You need to build a real-time object detection system for a security camera feed. This Skill can guide you on selecting the best YOLO model, designing the inference pipeline for low latency, and optimizing it for GPU deployment.

Quick Start

Guide me through selecting the best object detection model for real-time video analysis.

Frequently Asked Questions about ml-cv-specialist

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I select the best machine learning model for a specific computer vision task?▼

Model selection for computer vision tasks involves evaluating use case requirements, performance metrics, and cost constraints to recommend appropriate ML models using structured decision trees and quick reference tables.

What's the best way to design a training pipeline for machine learning systems?▼

Designing a training pipeline for machine learning systems requires outlining architectures that handle data ingestion, model training, and validation, utilizing established frameworks to ensure robust and efficient pipeline operations.

Should I use an API or self-hosted deployment for my ML inference architecture?▼

Choosing between API and self-hosted deployment for ML inference architecture depends on comparing latency, cost, and control requirements, evaluating synchronous APIs, asynchronous processing, and edge inference patterns.

How do I optimize inference architecture for low latency in real-time object detection?▼

Optimizing inference architecture for low latency object detection involves applying optimization techniques and monitoring strategies to synchronous APIs or edge inference setups, ensuring efficient GPU deployment for real-time video feeds.

When do I need asynchronous processing in my AI inference pipeline?▼

Asynchronous processing is needed in an AI inference pipeline when handling high-throughput workloads or complex model executions that exceed synchronous API latency limits, ensuring system stability and responsiveness.

Related Skills

Explore More Software Engineering Skills→
nadicodeainadicodeai

modal-serverless-gpu

Deploy ML workloads on serverless GPUs with Modal.

Official
Advanced
grasberggrasberg
3

ml-ops-engineer

Coordinate ML model lifecycles from notebook to production deployment.

Community
Advanced
haJ1thaJ1t

ai-ml-pro

Build, train, deploy, and monitor ML systems with Python and scikit-learn, TensorFlow, or PyTorch.

Community
Advanced
Imad-OuteImad-Oute

transformers

Manage pre-trained transformer models for NLP, vision, audio, and multimodal tasks.

Community
Advanced