Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-ml/automl-pipeline-builder/skills/building-automl-pipelines

building-automl-pipelines

Verified

Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning. Use when automating ML workflows from data preparation through model deployment. Trigger with phrases like "build automl pipeline", "automate ml workflow", or "create automated training pipeline".

assets/pipeline_template.yaml

View on GitHub
# pipeline_template.yaml

# --- General Pipeline Configuration ---
pipeline_name: "AutoML Pipeline - example-value" # Name of the pipeline (e.g., Customer Churn Prediction)
description: "Automated Machine Learning pipeline for example-value." # Short description of the pipeline's purpose
version: "1.0.0" # Pipeline version

# --- Data Source Configuration ---
data_source:
  type: "csv" # Type of data source (e.g., csv, database, api)
  location: "data/YOUR_DATASET.csv" # Path to the data file or connection string
  target_column: "target" # Name of the target variable column
  index_column: null # Name of the index column (optional)
  delimiter: "," # Delimiter for CSV files (e.g., ",", ";", "\t")
  quotechar: '"' # Quote character for CSV files
  encoding: "utf-8" # Encoding of the data file

# --- Feature Engineering Configuration ---
feature_engineering:
  enabled: true # Enable or disable feature engineering
  numeric_imputation: "mean" # Strategy for handling missing numerical values (e.g., mean, median, most_frequent, constant)
  categorical_encoding: "onehot" # Method for encoding categorical features (e.g., onehot, ordinal, target)
  feature_scaling: "standard" # Scaling method for numeric features (e.g., standard, minmax, robust)
  feature_selection:
    enabled: false # Enable or disable feature selection
    method: "variance_threshold" # Feature selection method (e.g., variance_threshold, selectkbest)
    threshold: 0.01 # Threshold for feature selection (depends on the method)

# --- Model Training Configuration ---
model_training:
  algorithm: "xgboost" # Machine learning algorithm to use (e.g., xgboost, lightgbm, randomforest, logisticregression)
  hyperparameter_tuning:
    enabled: true # Enable or disable hyperparameter tuning
    method: "random_search" # Hyperparameter tuning method (e.g., random_search, grid_search, bayesian_optimization)
    n_trials: 50 # Number of trials for hyperparameter tuning
    scoring_metric: "roc_auc" # Metric to optimize for (e.g., roc_auc, accuracy, f1, precision, recall)
    hyperparameter_space: # Define hyperparameter ranges for each algorithm
      xgboost: # Example for XGBoost
        n_estimators: [100, 200, 300]
        learning_rate: [0.01, 0.1, 0.2]
        max_depth: [3, 5, 7]
      # Add hyperparameter spaces for other algorithms as needed

# --- Model Evaluation Configuration ---
model_evaluation:
  split_ratio: 0.2 # Ratio for splitting data into training and validation sets
  scoring_metrics: ["roc_auc", "accuracy", "f1", "precision", "recall"] # List of metrics to evaluate the model
  cross_validation:
    enabled: true # Enable or disable cross-validation
    n_folds: 5 # Number of folds for cross-validation

# --- Model Deployment Configuration ---
model_deployment:
  enabled: false # Enable or disable model deployment
  environment: "staging" # Target deployment environment (e.g., staging, production)
  model_registry: "local" # Location to store the trained model (e.g., local, s3, gcp)
  model_path: "models/YOUR_MODEL.pkl" # Path to save the trained model
  api_endpoint: "YOUR_API_ENDPOINT" # API endpoint for model deployment (if applicable)

# --- Logging Configuration ---
logging:
  level: "INFO" # Logging level (e.g., DEBUG, INFO, WARNING, ERROR)
  format: "%(asctime)s - %(levelname)s - %(message)s" # Logging format
  file_path: "logs/pipeline.log" # Path to the log file

# --- Error Handling Configuration ---
error_handling:
  on_failure: "email_notification" # Action to take on pipeline failure (e.g., email_notification, retry, stop)
  email_recipients: ["YOUR_EMAIL@example.com"] # List of email addresses to notify on failure
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall