Eval

Measure non-deterministic behavior — LLM features, agents, prompts, or a skill itself — with repeatable evals instead of one-shot checks. Use when building or tuning AI/LLM functionality (ranking, extraction, generation, agent loops), when a feature could pass once by luck, or when validating that a prompt or skill actually changes behavior.

vasu-devs Updated 1 repo stars

File contents

vasu-devs/forge commit 4a47e13f36

Frequently asked questions

npx get-skill add vasu-devs/eval