Installs into .claude/skills of the current project.
Are you the author of Model Evaluation?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/aperivue-model-evaluation)
---
name: model-evaluation
description: Renamed to /model-assessment in v6 (removed in v7).
disable-model-invocation: true
---
`/model-evaluation` was renamed to `/model-assessment` in v6.0; this redirect is removed in v7.
Run `/model-assessment` now, passing the same arguments the user gave `/model-evaluation`.
Start at `/model-assessment` Part B, Phases 8–9 (task-correct held-out metrics and the metric-reporting gate).
Files in this skill
SKILL.md7.2 KB
references/metric_guide.md6 KB
references/metric_selection_grounding.md10 KB
scripts/check_metric_reporting.py17.6 KB
scripts/metric_reporting_challenge/fixture/clf_bad.md84 B
scripts/metric_reporting_challenge/fixture/clf_good.md186 B
scripts/metric_reporting_challenge/fixture/det_good_wrapped.md285 B
scripts/metric_reporting_challenge/fixture/det_no_iou.md224 B
scripts/metric_reporting_challenge/fixture/generative_bad.md134 B
scripts/metric_reporting_challenge/fixture/generative_good.md437 B
scripts/metric_reporting_challenge/fixture/interactive_bad.md128 B
scripts/metric_reporting_challenge/fixture/interactive_good.md500 B
scripts/metric_reporting_challenge/fixture/multiclass_bad.md128 B
scripts/metric_reporting_challenge/fixture/seg_bad.md119 B
scripts/metric_reporting_challenge/fixture/seg_good.md207 B
