Validate Evaluator

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

hamelsmu Updated

File contents

hamelsmu/evals-skills commit 9609b1b3c0

Frequently asked questions

npx get-skill add hamelsmu/validate-evaluator