Help us improve
Share bugs, ideas, or general feedback.
From oh-my-agent
Enforces repeated execute-verify-fix loops on task chunks until acceptance criteria pass or blocking issues identified. Use after partial task execution with remaining todos or unresolved verification findings.
npx claudepluginhub sswym/oh-my-agent --plugin oh-my-agentHow this skill is triggered — by the user, by Claude, or both
Slash command
/oh-my-agent:loopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
当任务部分完成且必须继续通过严格验证循环时,使用此技能。
Runs autonomous multi-stage execution loops (team-plan, exec-verify-fix cycles) for complex tasks until acceptance criteria pass, blocker hit, or max loops. Tracks progress via checkpoints.
Iterative task loop with Definition of Done verification. Claude proposes DoD criteria, user confirms, then Claude works autonomously until all items are verified or max iterations reached.
Autonomously drives a single feature or fix to verified completion by looping through plan, work, review, and live verification until the map is clean and evidence proves the feature runs.
Share bugs, ideas, or general feedback.
当任务部分完成且必须继续通过严格验证循环时,使用此技能。
team-exec -> team-verify -> team-fix。continue、done 或 blocked。.oma/state/config.json 读取(loopLimits.speed 或 loopLimits.default),如果未配置则回退到 3。## 循环状态
- 循环:
- 状态:
## 证据
| 阶段 | 结果 | 证据 |
| --- | --- | --- |
## 剩余待办列表
1. ...
## 下一个命令
- ...