Building Automl Pipelines
Overview
Build an end-to-end AutoML pipeline: data checks, feature preprocessing, model search/tuning, evaluation, and exportable deployment artifacts. Use this when you want repeatable training runs with a clear budget (time/compute) and a structured output (configs, reports, and a runnable pipeline).
Prerequisites
Before using this skill, ensure you have:
- Python environment with AutoML libraries (Auto-sklearn, TPOT, H2O AutoML, or PyCaret)
- Training dataset in accessible format (CSV, Parquet, or database)
- Understanding of problem type (classification, regression, time-series)
- Sufficient computational resources for automated search
- Knowledge of evaluation metrics appropriate for task
- Target variable and feature columns clearly defined
Instructions
- Identify problem type (binary/multi-class classification, regression, etc.)
- Define evaluation metrics (accuracy, F1, RMSE, etc.)
- Set time and resource budgets for AutoML search
- Specify feature types and preprocessing needs
- Determine model interpretability requirements
- Load training data using Read tool
- Perform initial data quality assessment
- Configure train/validation/test split strategy
- Define feature engineering transformations
- Set up data validation checks
- Initialize AutoML pipeline with configuration
See ${CLAUDE_SKILL_DIR}/references/implementation.md for detailed implementation guide.
Output
- Complete Python implementation of AutoML pipeline
- Data loading and preprocessing functions
- Feature engineering transformations
- Model training and evaluation logic
- Hyperparameter search configuration
- Best model architecture and hyperparameters
Error Handling
See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.
Examples
See ${CLAUDE_SKILL_DIR}/references/examples.md for detailed examples.
Resources
- Auto-sklearn: Automated scikit-learn pipeline construction with metalearning
- TPOT: Genetic programming for pipeline optimization
- H2O AutoML: Scalable AutoML with ensemble methods
- PyCaret: Low-code ML library with automated workflows
- Automated feature selection techniques
1---
2name: building-automl-pipelines-2
3description: |
4 Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning.
5 Use when automating ML workflows from data preparation through model deployment.
6 Trigger with phrases like "build automl pipeline", "automate ml workflow", or "create automated training pipeline".
7
8allowed-tools: Read, Write, Edit, Grep, Glob, Bash(python:*)
9version: 1.0.0
10author: Jeremy Longshore <jeremy@intentsolutions.io>
11license: MIT
12compatible-with: claude-code, codex, openclaw
13tags: [ai, deployment, ml]
14
15---
16
17# Building Automl Pipelines
18
19## Overview
20
21Build an end-to-end AutoML pipeline: data checks, feature preprocessing, model search/tuning, evaluation, and exportable deployment artifacts. Use this when you want repeatable training runs with a clear budget (time/compute) and a structured output (configs, reports, and a runnable pipeline).
22
23## Prerequisites
24
25Before using this skill, ensure you have:
26- Python environment with AutoML libraries (Auto-sklearn, TPOT, H2O AutoML, or PyCaret)
27- Training dataset in accessible format (CSV, Parquet, or database)
28- Understanding of problem type (classification, regression, time-series)
29- Sufficient computational resources for automated search
30- Knowledge of evaluation metrics appropriate for task
31- Target variable and feature columns clearly defined
32
33## Instructions
34
351. Identify problem type (binary/multi-class classification, regression, etc.)
362. Define evaluation metrics (accuracy, F1, RMSE, etc.)
373. Set time and resource budgets for AutoML search
384. Specify feature types and preprocessing needs
395. Determine model interpretability requirements
401. Load training data using Read tool
412. Perform initial data quality assessment
423. Configure train/validation/test split strategy
434. Define feature engineering transformations
445. Set up data validation checks
451. Initialize AutoML pipeline with configuration
46
47
48See `${CLAUDE_SKILL_DIR}/references/implementation.md` for detailed implementation guide.
49
50## Output
51
52- Complete Python implementation of AutoML pipeline
53- Data loading and preprocessing functions
54- Feature engineering transformations
55- Model training and evaluation logic
56- Hyperparameter search configuration
57- Best model architecture and hyperparameters
58
59## Error Handling
60
61See `${CLAUDE_SKILL_DIR}/references/errors.md` for comprehensive error handling.
62
63## Examples
64
65See `${CLAUDE_SKILL_DIR}/references/examples.md` for detailed examples.
66
67## Resources
68
69- **Auto-sklearn**: Automated scikit-learn pipeline construction with metalearning
70- **TPOT**: Genetic programming for pipeline optimization
71- **H2O AutoML**: Scalable AutoML with ensemble methods
72- **PyCaret**: Low-code ML library with automated workflows
73- Automated feature selection techniques
jeremylongshore