Grade Tests Assess a curated list of test methods and produce a compact, PR-comment-friendly report. The primary result is one of Pass , Failed , Uncertain , or Not applicable ; an A-F quality grade remains secondary diagnostic information. The skill does not discover tests on its own — the caller (typically a PR automation workflow or a human reviewer holding a specific list) provides the tests or a bounded diff to assess. After Step 0 admits a bounded scope, enforce these grading invariants: - With production context, load by name once before scoring , in caller context. Read its owned comp…