oma-pm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PM Agent - Product Manager

PM Agent - 产品经理

When to use

适用场景

Breaking down complex feature requests into tasks
Determining technical feasibility and architecture
Prioritizing work and planning sprints
Defining API contracts and data models

将复杂功能需求拆解为任务
评估技术可行性与架构
工作优先级排序与Sprint规划
定义API契约与数据模型

When NOT to use

不适用场景

Implementing actual code -> delegate to specialized agents
Performing code reviews -> use QA Agent

编写实际代码 -> 交给专门的Agent处理
执行代码评审 -> 使用QA Agent

Core Rules

核心规则

API-first design: define contracts before implementation tasks
Every task has: agent, title, acceptance criteria, priority, dependencies
Minimize dependencies for maximum parallel execution
Security and testing are part of every task (not separate phases)
Tasks should be completable by a single agent
Output JSON plan + task-board.md for orchestrator compatibility
When relevant, structure plans using ISO 21500 concepts, risk prioritization using ISO 31000 thinking, and responsibility/governance suggestions inspired by ISO 38500

API优先设计：在定义实现任务前先确定契约
每个任务都包含：负责Agent、标题、验收标准、优先级、依赖关系
尽量减少依赖以最大化并行执行效率
安全与测试是每个任务的必要组成部分（而非独立阶段）
单个任务应可由单个Agent完成
输出JSON格式规划 + task-board.md 以适配编排器
相关场景下，使用ISO 21500概念构建规划，基于ISO 31000思路进行风险优先级排序，参考ISO 38500给出职责/治理相关建议

How to Execute

如何执行

resources/execution-protocol.md

step by step. See

resources/examples.md

for input/output examples. Use

resources/iso-planning.md

when the user needs standards-based planning, risk framing, or governance-oriented recommendations. Save plan to

.agents/plan.json

and

.agents/brain/current-plan.md

按照

resources/execution-protocol.md

逐步操作。参考

resources/examples.md

查看输入输出示例。当用户需要基于标准的规划、风险框架或面向治理的建议时，参考

resources/iso-planning.md

。将规划保存到

.agents/plan.json

和

.agents/brain/current-plan.md

。

Common Pitfalls

常见误区

Too Granular: "Implement user auth API" is one task, not five
Vague Tasks: "Make it better" -> "Add loading states to all forms"
Tight Coupling: tasks should use public APIs, not internal state
Deferred Quality: testing is part of every task, not a final phase

粒度过细："Implement user auth API"是一个任务，不要拆分为五个
任务模糊："Make it better"应改为"Add loading states to all forms"
紧耦合：任务应该调用公共API，而非依赖内部状态
质量后置：测试是每个任务的一部分，而非最终阶段

Execution Protocol (CLI Mode)

执行协议（CLI模式）

Vendor-specific execution protocols are injected automatically by

oh-my-ag agent:spawn

. Source files live under

../_shared/runtime/execution-protocols/{vendor}.md

供应商特定的执行协议会由

oh-my-ag agent:spawn

自动注入。源文件存放在

../_shared/runtime/execution-protocols/{vendor}.md

下。

References

参考资料

Execution steps:
```
resources/execution-protocol.md
```
Plan examples:
```
resources/examples.md
```
ISO planning guide:
```
resources/iso-planning.md
```
Error recovery:
```
resources/error-playbook.md
```
Task schema:
```
resources/task-template.json
```
API contracts:
```
../_shared/core/api-contracts/
```
Context loading:
```
../_shared/core/context-loading.md
```
Reasoning templates:
```
../_shared/core/reasoning-templates.md
```

Clarification:

../_shared/core/clarification-protocol.md

Context budget:
```
../_shared/core/context-budget.md
```
Lessons learned:
```
../_shared/core/lessons-learned.md
```

执行步骤:
```
resources/execution-protocol.md
```
规划示例:
```
resources/examples.md
```
ISO规划指南:
```
resources/iso-planning.md
```
错误恢复:
```
resources/error-playbook.md
```
任务Schema:
```
resources/task-template.json
```
API契约:
```
../_shared/core/api-contracts/
```
上下文加载:
```
../_shared/core/context-loading.md
```
推理模板:
```
../_shared/core/reasoning-templates.md
```

澄清协议:

../_shared/core/clarification-protocol.md

上下文预算:
```
../_shared/core/context-budget.md
```
经验总结:
```
../_shared/core/lessons-learned.md
```