meta skill commands

HubWizard/second-pass

Command

Toggle Second Pass re-judge after revision. true = verify lift in a loop (more tokens, more confidence). false = trust judge's feedback, ship after one revision (default, cheaper).

HubWizard/second-pass

Command

Set the Second Pass iteration cap — the max number of revision attempts before the skill delivers the best attempt and stops. Accepts a positive integer.

HubWizard/second-pass

Command

Set the Second Pass passing grade. Any output graded below this bar triggers a revision loop. Accepts A, B, C, D, or F.

IISweetHeartII/oh-my-harness

Command

A read-only audit that checks whether a project has a consistent set of agent instructions and tools, including agents, skills, and project documentation. The description is partly in Korean and says it compares written records with the files that actually exist.

IISweetHeartII/oh-my-harness

Command

A command for reviewing how a harness was used and feeding improvements back into the agent, skill, or orchestrator setup. A harness is the surrounding workflow that guides and checks an AI coding agent.

IISweetHeartII/oh-my-harness

Command

A command that checks a generated agent harness against nine fixed rules. A harness is the project setup that runs and controls an agent.