Monitor Experiment Results ⏱ External cadence is appropriate here. This skill waits on an external fact (job completion / progress), so it is a natural / surface: the wake reads status and self-judges only machine-checkable completion (exit code, file exists, epoch logged) — never quality. This is the additive external-wait shape in . If a scheduled wait here ends in a verdict step (e.g. then audit results), run that verdict once after the wait clears — not re-entered per tick. Monitor: $ARGUMENTS Workflow Step 1: Check What's Running SSH server: Vast.ai instance (read , from ): Also check va…