loop-run

What problem does it solve?

This Skill helps you operate a long-running agent loop without losing state, skipping verification, or pretending a task is finished before the gate proves it.

Core Features & Use Cases

• Advance the loop one transition at a time from intake through planning, execution, verification, repair, and terminal states.
• Persist checkpoints, task status, run logs, approvals, and verification evidence so the run can survive compaction and resumption.
• Use it when resuming an existing run, handling approval pauses, or coordinating bounded repair after a verification failure.

Quick Start

Use the loop-run skill to resume the existing loop workspace, advance exactly one transition, verify the result, and stop only when the next explicit terminal state is reached.