Auto Review Loop: Autonomous Research Improvement 🔒 Do not wrap this skill in , , or . It already loops internally (review → fix → re-review) and the reviewer carries round-to-round memory in one ( ). An external timer re-enters from the top each tick — fresh , reviewer memory reset — firing the verdict on wall-clock time instead of on artifact change: zero new signal, full token cost. If you want to schedule something, schedule the external wait that precedes it (experiments done → then run this once). See . Autonomously iterate: review → implement fixes → re-review, until the external revi…