splitting-datasets

Files (8)

• SKILL.md
• README.md · assets/
• dataset_schema.json · assets/
• example_dataset.csv · assets/
• split_data_config.yaml · assets/
• README.md · references/
• README.md · scripts/
• split_data.py · scripts/

SKILL.md (first lines)

# Dataset Splitter

## Positioning

Treat this skill as a narrow helper for partition strategy.

## When to Use

Use this skill when:
- Prepare a dataset for machine learning model training.
- Create training, validation, and testing sets.
- Partition data to evaluate model performance.

## Not For / Boundaries

- Full preprocessing-pipeline ownership: use `preprocessing-data-with-automated-pipelines`
- Leakage audits and prediction-time checks: use `ml-data-leakage-guard`
- Model training and tuning after the split: use `scikit-learn`

## Typical Outputs

- Partition strategy with ratios, random seeds, and stratification rules
- Notes on temporal or grouped split constraints
- Handoff guidance for leakage review and downstream training

## Related Skills

- `preprocessing-data-with-automated-pipelines` for the broader preprocessing sequence
- `ml-data-leakage-guard` to verify the split does not leak future or test information

From foryourhealth111-pixel/Vibe-Skills, MIT.

More from foryourhealth111-pixel/Vibe-Skills