ai-ml-engineer
This copilot guides you through machine learning workflows—from model design and data preparation through training, evaluation, and production deployment. It covers supervised and unsupervised learning, deep learning, NLP, computer vision, and LLM applications, with structured dialogue to clarify your project needs and constraints.
AI/ML Engineer helps you develop, train, and deploy machine learning models with MLOps best practices.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-01-01
AI/ML Engineer helps you develop, train, and deploy machine learning models with MLOps best practices. This copilot guides you through machine learning workflows—from model design and data preparation through training, evaluation, and production deployment. It covers supervised and unsupervised learning, deep learning, NLP, computer vision, and LLM applications, with structured dialogue to clarify your project needs and constraints.
Use it when
- ai-ml-engineer helps you deploy ML models to production following MLOps best practices.
- Yes.
Verify before relying
Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.
Install
nahisaho/MUSUBI/ai-ml-engineer · repository language: HTML
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
How do I build ML models from scratch with ai-ml-engineer?
ai-ml-engineer guides you through end-to-end model development: defining your problem, preparing and engineering features, selecting algorithms, training with hyperparameter tuning, and rigorous evaluation. The copilot clarifies your project constraints and recommends supervised or unsupervised approaches, deep learning architectures, or specialized methods like NLP transformers and computer vision models based on your use case.
What does ai-ml-engineer cover for model deployment and MLOps?
ai-ml-engineer helps you deploy ML models to production following MLOps best practices. It covers containerization, orchestration with Kubernetes, experiment tracking with MLflow, versioning, and CI/CD pipelines. The copilot ensures your models are reproducible, scalable, and maintainable in production environments.
Can ai-ml-engineer help with deep learning neural networks?
Yes. ai-ml-engineer provides tutorials and guidance on deep learning architectures for NLP and computer vision applications. It covers transformer-based models for text classification, image recognition systems, and helps you choose between frameworks like PyTorch and TensorFlow based on your project needs.
Does ai-ml-engineer support LLM fine-tuning and RAG systems?
ai-ml-engineer includes support for implementing LLM fine-tuning, prompt engineering, and retrieval-augmented generation (RAG) systems. It helps you build generative AI features and integrate large language models into your applications with structured guidance on best practices.
How does ai-ml-engineer help monitor model performance?
ai-ml-engineer guides you on monitoring model performance in production and detecting data drift and concept drift. It covers evaluation metrics, validation strategies, and drift detection techniques to ensure your models remain reliable and accurate over time.
What machine learning model development topics does ai-ml-engineer cover?
ai-ml-engineer covers feature engineering, hyperparameter tuning, model optimization, ensemble learning, time series forecasting, anomaly detection, reinforcement learning, and evaluation metrics. It helps you understand trade-offs between approaches and select the right techniques for your specific problem.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
AI/ML Engineer AI
1. Role Definition
You are an AI/ML Engineer AI. You design, develop, train, evaluate, and deploy machine learning models while implementing MLOps practices through structured dialogue in Japanese.
2. Areas of Expertise
- Machine Learning Model Development: Supervised Learning (Classification, Regression, Time Series Forecasting), Unsupervised Learning (Clustering, Dimensionality Reduction, Anomaly Detection), Deep Learning (CNN, RNN, LSTM, Transformer, GAN), Reinforcement Learning (Q-learning, Policy Gradient, Actor-Critic)
- Data Processing and Feature Engineering: Data Preprocessing (Missing Value Handling, Outlier Handling, Normalization), Feature Engineering (Feature Selection, Feature Generation), Data
(truncated - see the full file via the links below)
File tree — 3 files
.claude/skills/ai-ml-engineer/SKILL.md
.claude/skills/ai-ml-engineer/mlops-guide.md
.claude/skills/ai-ml-engineer/model-card-template.md
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 › “Develop, train, and evaluate machine learning models end-to-end”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
ml-expert delivers comprehensive guidance on machine learning systems, from supervised and unsupervised learning through deep neural networks to production deployment. It covers model training workflows, hyperparameter optimization, and MLOps practices including versioning and monitoring. Includes practical code patterns for scikit-learn pipelines, PyTorch training loops, and FastAPI model serving.
AI Architect Expert provides in-depth guidance on building production-grade AI systems, covering model registries, feature stores, distributed training pipelines, and inference optimization. Learn MLOps best practices, from CI/CD automation to monitoring strategies, and implement scalable patterns for real-time and batch workloads.
Learn to build and operate production machine learning systems with guidance on model deployment, infrastructure setup, and monitoring. Covers MLOps workflows, LLM integration patterns, and best practices for scaling models in real-world environments.
Master the full lifecycle of production machine learning systems, from experiment tracking and model versioning through deployment and monitoring. Learn to build reproducible workflows using MLflow, implement feature stores, serve models at scale, and automate ML pipelines with CI/CD. This advanced skill covers everything needed to operationalize models reliably in production environments.
MLOps Workflows guides you through production-grade machine learning operations using MLflow, covering experiment tracking, model registry management, deployment patterns, and monitoring. Learn to version models, run A/B tests, and implement CI/CD practices for reliable ML systems.
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.
More skills Datawhale Agent Learning Hub (NOASSERTION) · Embedded Ai Deployment (NOASSERTION) · ml-engineering (MIT) · implementing-mlops (MIT)