using-ai-engineering

# Using AI Engineering

## Overview

This meta-skill routes you to the right AI/ML engineering pack based on your task. Load this skill when you need ML/AI expertise but aren't sure which specific pack to use.

**Core Principle**: Problem type determines routing - clarify before guessing.

## When to Use

Load this skill when:
- Starting any AI/ML engineering task
- User mentions: "neural network", "train a model", "RL agent", "fine-tune LLM", "deploy model"
- You recognize ML/AI work but unsure which pack applies
- Need to combine multiple domains (e.g., train RL + deploy)

## How to Access Reference Sheets

**IMPORTANT**: All reference sheets are located in the SAME DIRECTORY as this SKILL.md file.

When this skill is loaded from:
  `skills/using-ai-engineering/SKILL.md`

Reference sheets are at:
  `skills/using-ai-engineering/routing-examples.md`

NOT at:
  `skills/routing-examples.md` ← WRONG PATH

---

## STOP - Mandatory Clarification Triggers

Before routing, if query contains ANY of these ambiguous patterns, ASK ONE clarifying question:

| Ambiguous Term | What to Ask | Why |
|----------------|-------------|-----|
| "Model not working" | "What's not working - architecture, training, or deployment?" | Could be 3+ packs |
| "Improve performance" | "Performance in what sense - training speed, inference speed, or accuracy?" | Different domains |
| "Learning chatbot/agent" | "Fine-tuning language generation or optimizing dialogue policy?" | LLM vs RL vs both |
| "Train/deploy model" | "Both training AND deployment, or just one?" | May need multiple packs |
| Framework not mentioned | "What framework are you using?" | PyTorch-specific vs generic |

**If you catch yourself about to guess the domain, STOP and clarify.**

---

## Routing by Problem Type

| Keywords/Signals | Route To | Why |
|------------------|----------|-----|
| PyTorch, CUDA, memory, distributed, tensor, GPU | **pytorch-engineering** | Foundation issues |
| NaN loss, converge, unstable, hyperparam