moai-domain-ml
Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.
npx skills add majiayu000/claude-skill-registry --skill moai-domain-ml-ajbcoding-claude-skill-eval --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Provides a structured ML workflow for enterprise settings: data preprocessing with a MlDataProcessor, model training with integrated ExperimentTracker using MLflow, and comprehensive ModelEvaluator for evaluation and validation (classification metrics, cross-validation, learning curves, and evaluation report).
How it works
- Data Processing Pipeline: MlDataProcessor identifies numeric and categorical features, builds a ColumnTransformer with numeric and categorical pipelines (imputers, scaler, one-hot encoding), fits/transforms data, and generates feature names.
- Model Training with Experiment Tracking: ExperimentTracker initializes an MLflow experiment, logs parameters and tags, trains the model, computes train/val predictions, calculates metrics (accuracy, precision, recall, f1 for both train and validation), logs metrics, logs feature importance if available, and logs the model or fallback artifact; also supports comparing experiments by top metric.
- Model Evaluation and Validation: ModelEvaluator can evaluate classification models by computing accuracy, precision/recall/F1 (macro and weighted), ROC AUC for binary cases, generates a classification report and confusion matrix, stores predictions and probabilities, and supports cross-validation and learning curve analysis; can generate a markdown evaluation report.
When to use it
Use when building an end-to-end ML pipeline that requires standardized data preprocessing, tracked experiments, and thorough evaluation in a production or research setting.
What it can touch
- Libraries: sklearn (ColumnTransformer, pipelines, imputers, preprocessing, metrics), mlflow (experiments, logging, models), numpy, pandas, matplotlib/seaborn (for plotting imports present but not strictly required in code).
- No explicit file system paths or external data sources are invoked in the visible code beyond typical objects; artifacts are managed via MLflow logging.
Caveats
- The code assumes models expose fit/predict interfaces and, optionally, predict_proba for ROC AUC.
- No explicit handling of GPU or distributed training; device management is not shown in the evaluation components.
- Logging relies on MLflow configuration; missing tracking URI or experiment setup may require external setup.
# Enterprise Machine Learning ## Level 1: Quick Reference ### Core Capabilities - **Deep Learning**: TensorFlow 2.20.0, PyTorch 2.9.0, JAX 0.4.33 - **Classical ML**: Scikit-learn 1.7.2, XGBoost 2.0.3, LightGBM 4.4.0 - **AutoML**: H2O AutoML 3.44.0, AutoGluon 1.0.0, TPOT 0.12.2 - **MLOps**: MLflow 2.9.0, Kubeflow 1.8.0, DVC 3.48.0 - **Deployment**: ONNX 1.16.0, TensorFlow Serving, TorchServe, Seldon Core ### Quick Setup Examples ```python # TensorFlow 2.20.0 with modern Keras API import tensorflow as tf from tensorflow import keras # Create a simple neural network model = keras.Sequential([ keras.layers.Dense(128, activation='relu', input_shape=(784,)), keras.layers.Dropout(0.2), keras.layers.Dense(64, activation='relu'), keras.layers.Dropout(0.2), keras.layers.Dense(10, activation='softmax') ]) model.compile( optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'] ) # Train with modern callbacks callbacks = [ keras.callbacks.EarlyStopping(patience=5, restore_best_weights=True), keras.callbacks.ReduceLROnPlateau(factor=0.5, patience=3), keras.callbacks.ModelCheckpoint('best_model.h5', save_best_only=True) ] # model.fit(X_train, y_train, validation_data=(X_val,
- Level 1: Quick Reference
- Core Capabilities
- Quick Setup Examples
- Level 2: Practical Implementation
- ML Pipeline Architecture
- AutoML Implementation
- Level 3: Advanced Integration
- MLOps and Production Deployment
- Related Skills
- Quick Start Checklist
- Performance Optimization Tips
What does the moai-domain-ml skill do?
Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill moai-domain-ml-ajbcoding-claude-skill-eval --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.