Back to Details

to-prd

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

To PRD

生成PRD

Convert current conversation context into a structured PRD for publication to the project issue tracker.
将当前对话上下文转换为结构化PRD，以便发布到项目问题追踪器。

When to use this skill

适用场景

  • Documenting requirements from existing discussion
  • Creating a formal spec before breaking work into issues
  • Recording architectural decisions alongside user stories
  • 从现有讨论中记录需求
  • 在拆分任务为问题之前创建正式规范
  • 结合用户故事记录架构决策

When not to use this skill

不适用场景

  • Breaking work into tickets → use 
    to-issues
  • Writing technical internal docs → use 
    technical-writing
  • Quick task notes → use 
    task-planning
  • 拆分任务为工单 → 使用
    to-issues
  • 撰写技术内部文档 → 使用
    technical-writing
  • 快速任务笔记 → 使用
    task-planning

Process

流程

1. Explore and understand

1. 探索与理解

Review the codebase using the project's domain vocabulary (CONTEXT.md) and relevant ADRs. Do not interview the user — synthesize from existing context.
使用项目的领域词汇表（CONTEXT.md）和相关架构决策记录（ADRs）审查代码库。无需与用户沟通，直接从现有上下文整合信息。

2. Design modules

2. 模块设计

Identify the major components to build or modify. Emphasize deep modules: simple, testable interfaces with stable contracts. Validate assumptions with the user and confirm which modules need test coverage.
确定需要构建或修改的主要组件。强调深度模块：具备稳定契约的简单、可测试接口。与用户验证假设，并确认哪些模块需要测试覆盖。

3. Document and publish

3. 文档撰写与发布

Complete the PRD template and submit to the issue tracker with the 
needs-triage
label.
完成PRD模板并提交至问题追踪器，添加
needs-triage
标签。

PRD template

PRD模板

markdown
undefined
markdown
undefined

[Feature/Change Name]

[Feature/Change Name]

Problem Statement

Problem Statement

[User-facing description of the issue or opportunity. What pain does this solve?]
[User-facing description of the issue or opportunity. What pain does this solve?]

Solution

Solution

[User-facing description of the resolution approach.]
[User-facing description of the resolution approach.]

User Stories

User Stories

  1. As a [actor], I want [feature], so that [benefit].
  2. As a [actor], I want [feature], so that [benefit]. [... comprehensive list covering all use cases]
  1. As a [actor], I want [feature], so that [benefit].
  2. As a [actor], I want [feature], so that [benefit]. [... comprehensive list covering all use cases]

Implementation Decisions

Implementation Decisions

Modules

Modules

[Major components to build/modify with interface descriptions]
[Major components to build/modify with interface descriptions]

Technical Choices

Technical Choices

[Architecture decisions, schema design, API contracts — avoid file paths and code snippets]
[Architecture decisions, schema design, API contracts — avoid file paths and code snippets]

ADR References

ADR References

[Links to relevant Architecture Decision Records]
[Links to relevant Architecture Decision Records]

Testing Decisions

Testing Decisions

[Testing philosophy for this feature, which modules need coverage, relevant test precedents]
[Testing philosophy for this feature, which modules need coverage, relevant test precedents]

Out of Scope

Out of Scope

  • [Explicitly excluded item]
  • [Explicitly excluded item]
  • [Explicitly excluded item]
  • [Explicitly excluded item]

Further Notes

Further Notes

[Additional context, open questions, or dependencies]
undefined
[Additional context, open questions, or dependencies]
undefined

Quality checklist

质量检查清单

  • Problem statement is user-facing (not technical)
  • User stories cover all actors and use cases
  • Implementation decisions reference existing domain vocabulary
  • Out of scope section prevents scope creep
  • No file paths or code in the PRD (these belong in issues)
  • 问题描述面向用户（非技术向）
  • 用户故事覆盖所有角色和使用场景
  • 实现决策参考现有领域词汇
  • 超出范围部分可防止范围蔓延
  • PRD中不包含文件路径或代码（这些内容应放在问题工单中）

Instructions

操作说明

  1. Identify the task trigger and expected output.
  2. Follow the workflow steps in this skill from top to bottom.
  3. Validate outputs before moving to the next step.
  4. Capture blockers and fallback path if any step fails.
  1. 确定任务触发条件和预期输出。
  2. 从上到下遵循本Skill中的工作流程步骤。
  3. 进入下一步前验证输出内容。
  4. 记录阻塞点，以及若某步骤失败时的备选方案。

Examples

示例

  • Example: Apply this skill to a small scope first, then scale to full scope after validation passes.
  • 示例：先将本Skill应用于小范围场景，验证通过后再扩展至完整范围。

Best practices

最佳实践

  • Keep outputs deterministic and auditable.
  • Prefer small reversible changes over broad risky edits.
  • Record assumptions explicitly.
  • 确保输出可预测且可审计。
  • 优先选择小型可逆变更，而非大范围高风险修改。
  • 明确记录假设条件。

References

参考资料

  • Project standards: 
    .agent-skills/skill-standardization/SKILL.md
  • Validator script: 
    .agent-skills/skill-standardization/scripts/validate_skill.sh
  • 项目标准：
    .agent-skills/skill-standardization/SKILL.md
  • 验证脚本：
    .agent-skills/skill-standardization/scripts/validate_skill.sh