# Explaining Machine Learning Models

> Explaining Machine Learning Models is an Agent Skill for general use published in the foryourhealth111-pixel/Vibe-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.

- Skill name: `explaining-machine-learning-models`
- Category: [Others](https://www.openparable.com/skill/others/1)
- Source: https://github.com/foryourhealth111-pixel/Vibe-Skills/blob/HEAD/bundled/skills/explaining-machine-learning-models/SKILL.md
- Repository: foryourhealth111-pixel/Vibe-Skills (2,381 GitHub stars when collected)

## SKILL.md

# Model Explainability Tool

## Positioning

Treat this skill as an explicit/manual helper for interpretability work.

## When to Use

Use this skill when:
- Understand why a machine learning model made a specific prediction.
- Identify the most important features influencing a model's output.
- Debug model performance issues by identifying unexpected feature interactions.
- Communicate model insights to non-technical stakeholders.
- Ensure fairness and transparency in model predictions.

## Not For / Boundaries

- Model training and hyperparameter search: use `scikit-learn`
- Benchmark comparison and threshold selection: use `evaluating-machine-learning-models`
- Leakage or prediction-time audits: use `ml-data-leakage-guard`

## Typical Outputs

- Feature importance or attribution summaries
- Local explanation workflow for a concrete prediction
- Notes on caveats, instability, or misleading explanations

## Related Skills

- `shap` for SHAP-specific workflows
- `evaluating-machine-learning-models` when the question is whether the model is good enough

---

Source: https://www.openparable.com/skill/others/explaining-machine-learning-models (OpenParable). Cite the canonical URL above.
