moai-domain-ml

ML model training automates PyTorch 2.5.0 and TensorFlow 2.18.0 workflows with built-in evaluation and monitoring. The Skill handles model initialization, data pipeline setup, and training loops while enforcing TDD patterns and integrating MLflow 2.19.0 for experiment tracking and reproducibility across development environments.

Yes, this Skill covers the full MLOps lifecycle: training, evaluation, deployment, and monitoring. It integrates with moai-foundation-trust for TRUST 5 checkpoints and provides migration guidance, ensuring models move safely from development through testing to production with enforced quality gates.

The Skill enforces TDD patterns for ML pipelines with mandatory test coverage ≥85% and integrates with moai-foundation-langs for lint execution plans. It generates test/lint execution plans and quality checkpoints to maintain best practices throughout model training and evaluation.

This Skill uses PyTorch 2.5.0, TensorFlow 2.18.0, and MLflow 2.19.0. It has no external dependencies and works across development, testing, and migration scenarios with up-to-date tooling, ensuring compatibility with modern ML workflows and moai ecosystem integration.

The Skill abstracts MLOps complexity by automating training, evaluation, and deployment workflows. It's designed for domain ML projects requiring structured pipelines; familiarity with PyTorch or TensorFlow and basic testing concepts helps, but the Skill enforces best practices and generates guidance automatically.

The Skill integrates with moai-foundation-trust and moai-foundation-langs to produce TRUST 5 checkpoints and migration guidance. It works within TDD workflows and generates test/lint execution plans, making it suitable for migrating existing projects or bootstrapping new domain ML initiatives.