Skip to main content

Evaluation

Skills/MLOps
MLOps

Evaluation

Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.

On demandAvailable when invokedBuilt In
Install from Aegisaegis skills install evaluation
Install guide
Overview

Bundled with the packaged Aegis CLI as a built-in procedural skill.

Already ships inside the packaged Aegis bundle. Use `aegis skills install evaluation` only when you want an explicit local materialization record.

Aliases

evalevaluationbenchmark models

Trigger phrases

evaluate this modelbenchmark these promptsset up an eval harness

Keywords

evaluationbenchmarkdatasetmetricbaselinereproducibility
Same section

More from MLOps

5 skills in this section

Hugging Face Hub

Guides model, dataset, and space workflows around Hugging Face Hub with explicit auth, artifact, and cache assumptions.

On demandAvailable when invoked
Usage and install
Slash command
/huggingface-hub
Install
aegis skills install huggingface-hub
Reference
huggingface-hub
Runtime posture
Available when invoked
Open details
Inference

Guides model-serving and runtime-inference decisions across local, remote, and packaged deployment paths.

On demandAvailable when invoked
Usage and install
Slash command
/inference
Install
aegis skills install inference
Reference
inference
Runtime posture
Available when invoked
Open details
Training

Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.

On demandAvailable when invoked
Usage and install
Slash command
/training
Install
aegis skills install training
Reference
training
Runtime posture
Available when invoked
Open details