# ML model evaluation (/ml--model-evaluation)

/ml--model-evaluation is a Claude Code skill in the AI & Agents section. Evaluates a model beyond one headline number: metrics matched to error costs, calibration, per-slice performance and error-by-error analysis.

- Web version: https://skills.sgomez.dev/en/s/ml--model-evaluation
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ml/model-evaluation.md
- Updated 10 Jul 2026

## How to ask for it

- `/ml--model-evaluation evaluate this fraud classification model`
- `/ml--model-evaluation check whether the model is well calibrated`
- `/ml--model-evaluation break down errors by user segment`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ml-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*.py`, `**/*.ipynb`, `**/*.csv`, `**/*.parquet`, `**/*.json`, `models/**`, `requirements.txt`, `pyproject.toml`
- Writes: `**/*.py`, `**/*.ipynb`, `reports/**`, `**/*.md`
- Runs: `python`, `pip`
- Network: No
- Destructive: No

## Author's description

Evaluate a model properly — right metrics, calibration, slices, error analysis

- [How we review this](https://skills.sgomez.dev/en/methodology.md)