using-training-optimization

Route training problems to optimization specialists based on symptoms.

14|3|Updated Oct 28, 2025

Search Tags:#optimization #training #gradient #autodiff #learning-rate

Ready to run

npx skills add https://github.com/tachyon-beep/skillpacks --skill using-training-optimization

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: using-training-optimization
Source: https://github.com/tachyon-beep/skillpacks/tree/main/plugins/yzmir-training-optimization/skills/using-training-optimization
Command: npx skills add https://github.com/tachyon-beep/skillpacks --skill using-training-optimization

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This meta-skill routes you to the right training optimization specialist based on symptoms. Training issues often have multiple potential causes—this skill helps diagnose symptoms and route to the appropriate specialist.

Core Features & Use Cases

Diagnostic routing for learning-rate scheduling, gradient management, loss functions, and optimizer choices
Guidance to escalate to targeted optimization techniques when needed
Combines multiple optimization patterns for complex training scenarios

Quick Start

When training stalls or diverges, say: "My model isn't learning; which optimization should I try first?" for a routing to gradient-management or learning-rate-scheduling

Frequently Asked Questions about using-training-optimization

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

FAQPage Schema

How do I diagnose why my model isn't learning during training?▼

Model learning failures stem from multiple causes—gradient flow issues, learning-rate misconfiguration, or optimizer choice. This skill routes you through diagnostic questions to identify the root symptom, then connects you to the specialist skill for that specific problem, such as gradient-management or learning-rate-scheduling.

What should I check first when training becomes unstable or diverges?▼

Training instability typically traces to learning-rate settings, gradient scaling, or optimizer configuration. Start by clarifying your symptoms—loss spiking, oscillating, or exploding—and this skill routes you to the appropriate optimization specialist to stabilize convergence.

How do I set up a new training pipeline with proper optimization?▼

Setting up training optimization involves selecting an optimizer, configuring learning-rate scheduling, managing gradient flow, and tracking experiments. This skill diagnoses your setup requirements and routes you through hyperparameter-tuning, learning-rate-scheduling, gradient-management, and experiment-tracking skills as needed.

When should I use gradient clipping versus learning-rate adjustment to fix training problems?▼

Gradient clipping prevents explosion from large gradients; learning-rate adjustment controls convergence speed and stability. This skill asks clarifying questions about your training symptoms—gradient magnitude, loss behavior, convergence rate—then routes to gradient-management or learning-rate-scheduling based on the root cause.

How do I know if my training problem is overfitting, underfitting, or an optimization issue?▼

Overfitting shows high train accuracy and low validation accuracy; underfitting shows poor performance on both; optimization issues show stalled or diverging loss. This skill routes you to overfitting-prevention, data-augmentation-strategies, or learning-rate-scheduling based on which symptom you describe.

What's the best approach to find the right hyperparameters for my training setup?▼

Hyperparameter selection depends on your optimizer, learning-rate range, batch size, and dataset scale. This skill routes you to hyperparameter-tuning and experiment-tracking skills to systematically search and log configurations, then validates which choices resolve your training symptoms.