Eval Harness

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD). USE WHEN defining pass/fail criteria for agent tasks, measuring reliability with pass@k, or building regression suites for prompt or agent changes.

Sheshiyer Updated

File contents

Sheshiyer/skill-clusters commit 25f2adbfcf

Frequently asked questions

npx get-skill add sheshiyer/eval-harness