# fiftyone-model-evaluation

> Claude/Codex skill by [@voxel51](https://omgskills.com/library/voxel51/index.md) · 47 stars · Updated 2026-10-18

Evaluate model predictions against ground truth using COCO, Open Images, or custom protocols. Use when computing mAP, precision, recall, confusion matrices, or analyzing TP/FP/FN examples for detection, classification, segmentation, or regression tasks.

## Install

```sh
git clone https://github.com/voxel51/fiftyone-skills /tmp/fiftyone-skills && ln -s /tmp/fiftyone-skills/skills/fiftyone-model-evaluation ~/.claude/skills/fiftyone-model-evaluation
```

## From README

Evaluate Model Predictions in FiftyOne Key Directives ALWAYS follow these rules: Check if dataset exists and has required fields Verify the dataset has both prediction and ground truth fields of compatible types.

## Links

- HTML page: https://omgskills.com/library/voxel51/fiftyone-skills/skills/fiftyone-model-evaluation/
- GitHub: https://github.com/voxel51/fiftyone-skills
- Author: [@voxel51](https://omgskills.com/library/voxel51/index.md)

## More from this repo

- [fiftyone-app-playwright](https://omgskills.com/library/voxel51/fiftyone-skills/skills/fiftyone-app-playwright/index.md) — Used when driving the FiftyOne App via the Playwright MCP — plugin/operator verification, demo or screencast recording,...
   - [@voxel51](https://omgskills.com/library/voxel51/index.md) · 47 stars
- [fiftyone-code-style](https://omgskills.com/library/voxel51/fiftyone-skills/skills/fiftyone-code-style/index.md) — Writes Python code following FiftyOne's official conventions.
   - [@voxel51](https://omgskills.com/library/voxel51/index.md) · 47 stars
- [fiftyone-dataset-curation](https://omgskills.com/library/voxel51/fiftyone-skills/skills/fiftyone-dataset-curation/index.md) — End-to-end dataset curation for FiftyOne: inspect schema and quality, audit annotations, analyze class distributions,...
   - [@voxel51](https://omgskills.com/library/voxel51/index.md) · 47 stars