loop
SkillAI & modelsEnforces a repeated execute-verify-fix loop until acceptance criteria pass or a blocking issue is clearly identified.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the loop skill
What this skill tells your AI
The instructions your AI receives, as published by sswym/oh-my-agent in skills/loop/SKILL.md and read by ahel’s review.
目的
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。
触发条件
- 执行片段后剩余待办事项
- 验证产生未解决的发现
- 团队有过早声明完成的风险
工作流程
- 读取验收标准和当前修复待办列表。
- 选择最小的下一个范围片段。
- 运行
team-exec -> team-verify -> team-fix。 - 报告状态为
continue、done或blocked。 - 重复直到标准通过或阻塞成为硬约束。
护栏
- 不要在有未解决的主要/阻塞发现时声明"完成"。
- 每次调用的最大循环次数:从
.oma/state/config.json读取(loopLimits.speed或loopLimits.default),如果未配置则回退到 3。
输出模板
## 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
- ...
Signals
- GitHub stars
- 76
- Forks
- 13
- Last commit
- Apr 2026
Advanced
- Catalog kind
- skill
- Gateway key
loop-sswym- Source
- github.com/sswym/oh-my-agent