prd-to-issues

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PRD to Issues

PRD 转 Issues

Break a PRD into independently-grabbable issues using vertical slices (tracer bullets), written as local markdown files.

将PRD拆分为可独立承接的任务（采用垂直切片/追踪式任务方式），并写入本地Markdown文件。

Process

流程

1. Locate the PRD

1. 定位PRD文件

Ask the user for the PRD file path (e.g.

issues/prd.md

If the PRD is not already in your context window, read it from the file.

向用户询问PRD文件路径（例如

issues/prd.md

）。

如果PRD未在当前上下文窗口中，从文件中读取内容。

2. Explore the codebase (optional)

2. 探索代码库（可选）

If you have not already explored the codebase, do so to understand the current state of the code.

如果尚未探索过代码库，需进行探索以了解代码的当前状态。

3. Draft vertical slices

3. 草拟垂直切片任务

Break the PRD into tracer bullet issues. Each issue is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.

Slices may be 'HITL' or 'AFK'. HITL slices require human interaction, such as an architectural decision or a design review. AFK slices can be implemented and merged without human interaction. Prefer AFK over HITL where possible.

<vertical-slice-rules> - Each slice delivers a narrow but COMPLETE path through every layer (schema, API, UI, tests) - A completed slice is demoable or verifiable on its own - Prefer many thin slices over few thick ones </vertical-slice-rules>

将PRD拆分为追踪式任务（tracer bullet）。每个任务是贯穿所有集成层的细粒度垂直切片，而非单一层级的水平切片。

切片分为“HITL”或“AFK”类型。HITL类型的任务需要人工参与，例如架构决策或设计评审。AFK类型的任务无需人工参与即可实现并合并。尽可能优先选择AFK类型。

<vertical-slice-rules> - 每个切片需覆盖所有层级（schema、API、UI、测试）的完整路径，范围虽窄但功能完整 - 完成后的切片可独立演示或验证 - 优先拆分为多个细粒度切片，而非少量粗粒度切片 </vertical-slice-rules>

4. Quiz the user

4. 与用户确认

Present the proposed breakdown as a numbered list. For each slice, show:

Title: short descriptive name
Type: HITL / AFK
Blocked by: which other slices (if any) must complete first
User stories covered: which user stories from the PRD this addresses

Ask the user:

Does the granularity feel right? (too coarse / too fine)
Are the dependency relationships correct?
Should any slices be merged or split further?
Are the correct slices marked as HITL and AFK?

Iterate until the user approves the breakdown.

将拟议的拆分方案以编号列表形式呈现。每个切片需展示：

标题：简短描述性名称
类型：HITL / AFK
依赖项：哪些其他切片需先完成（如有）
覆盖用户故事：此切片对应PRD中的哪些用户故事

向用户询问：

拆分粒度是否合适？（过粗 / 过细）
依赖关系是否正确？
是否需要合并或进一步拆分某些切片？
HITL和AFK类型的标记是否正确？

反复迭代直至用户认可拆分方案。

5. Create the issue files

5. 创建任务文件

For each approved slice, write a markdown file in

issues/

using the naming pattern

issues/NNN-short-title.md

(e.g.

issues/001-add-user-auth.md

Number issues starting from the next available number (check what files already exist in

issues/

Create files in dependency order (blockers first) so you can reference real filenames in the "Blocked by" field.

Do NOT use

gh issue create

or any GitHub CLI commands. Do NOT reference GitHub issue numbers. Use local filenames for all cross-references.

<issue-template>

针对每个已认可的切片，在

issues/

目录下创建Markdown文件，命名格式为

issues/NNN-short-title.md

（例如

issues/001-add-user-auth.md

）。

从下一个可用编号开始为任务编号（检查

issues/

目录中已有的文件）。

按依赖顺序创建文件（先创建被依赖的任务），以便在“依赖项”字段中引用真实文件名。

请勿使用

gh issue create

或任何GitHub CLI命令。请勿引用GitHub任务编号。所有交叉引用均使用本地文件名。

<issue-template>

Parent PRD

父PRD文件

issues/prd.md

(or whichever PRD file was used)

issues/prd.md

（或所使用的其他PRD文件）

What to build

需实现内容

A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation. Reference specific sections of the parent PRD rather than duplicating content.

此垂直切片的简要描述。描述端到端行为，而非分层实现细节。引用父PRD的特定章节，而非重复内容。

Acceptance criteria

验收标准

Blocked by

依赖项

Blocked by
```
issues/NNN-title.md
```
(if any)

Or "None - can start immediately" if no blockers.

依赖于
```
issues/NNN-title.md
```
（如有）

若无依赖项则填写“无 - 可立即开始”。

User stories addressed

覆盖用户故事

Reference by number from the parent PRD:

User story 3
User story 7

</issue-template>

Do NOT close or modify the parent PRD file.

引用父PRD中的用户故事编号：

用户故事3
用户故事7

</issue-template>

请勿关闭或修改父PRD文件。