agile-sprint

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Sprint Planning

Sprint规划

Use this skill to plan a work cycle (sprint) with clear objective, selected items, and execution order.

Initial context received via slash: $ARGUMENTS

$ARGUMENTS

is filled, use as reference (e.g., epic, backlog, period). If empty, ask which backlog or initiative will be planned.

使用该Skill来规划一个具有明确目标、选定任务和执行顺序的工作周期（Sprint）。

通过斜杠命令接收初始上下文：$ARGUMENTS

如果

$ARGUMENTS

已填写，将其作为参考信息（例如：史诗任务epic、待办事项列表backlog、周期）。如果为空，则询问将要规划哪个待办事项列表或项目计划。

Language

语言要求

Write the artifact in the user's language. Apply correct grammar and any required diacritics or script-specific characters. If the user's language is unclear, ask before generating output. Templates are in English — translate headers and content to match.

以用户使用的语言编写产出物。确保语法正确，并使用必要的变音符号或特定脚本字符。如果用户的语言不明确，在生成输出前先询问。模板为英文版本，请将标题和内容翻译为对应语言。

Project root

项目根目录

This skill writes artifacts at paths relative to the project root (the repo where the work happens), not the agent's current working directory.

If invoked from inside the project, use the relative paths shown in this skill.
If invoked from another directory (e.g., a sibling repo, or when the project lives elsewhere), prepend
```
<project-root>/
```
to every artifact path.
When the project root is ambiguous, confirm with the user via the harness question tool before writing.

该Skill将产出物写入相对于项目根目录（即工作所在的代码仓库）的路径下，而非Agent当前的工作目录。

如果从项目内部调用，使用本Skill中显示的相对路径。
如果从其他目录调用（例如：同级代码仓库，或项目位于其他位置），请在所有产出物路径前添加
```
<project-root>/
```
。
当项目根目录不明确时，在写入前通过工具的提问功能与用户确认。

Prompting

提示规则

Follow the project-wide convention in

CLAUDE.md

AGENTS.md

("Skill Prompting Conventions"). Use the harness's structured-question tool —

AskUserQuestion

(Claude Code),

ask_user_question

(Codex), or

question

(OpenCode) — for the decision points below. Use free-form text only where a path/name/value cannot be enumerated.

Decision point	Why structured	Suggested options
Backlog items to include (multi-select)	Affects sprint scope	select from backlog list
Sprint duration	Affects capacity math	1 week · 2 weeks · custom

Free-form prompts (no structured tool):

Sprint goal text
Capacity overrides

No-pause mode: if the user has explicitly disabled mid-skill clarification, convert every structured prompt into an entry under Open questions (or equivalent) and proceed without blocking.

遵循

CLAUDE.md

AGENTS.md

中的项目全局约定（“Skill提示约定”）。对于以下决策点，使用工具的结构化提问功能：

AskUserQuestion

（Claude Code）、

ask_user_question

（Codex）或

question

（OpenCode）。仅当路径/名称/值无法枚举时，才使用自由格式文本。

决策点	使用结构化提问的原因	建议选项
待包含的Backlog事项（多选）	影响Sprint范围	从Backlog列表中选择
Sprint时长	影响产能计算	1周 · 2周 · 自定义

自由格式提示（不使用结构化工具）：

Sprint目标文本
产能调整

无暂停模式：如果用户明确禁用了Skill执行过程中的澄清环节，请将所有结构化提示转换为“开放式问题”（或等效模块）下的条目，无需等待回复即可继续执行。

Objective

目标

Declare the sprint objective
Select backlog items based on value, risk, and dependency
Record capacity and constraints
Define execution order and highlight blockers
Validate that each item has Definition of Ready

明确Sprint目标
根据价值、风险和依赖关系选择Backlog事项
记录产能和约束条件
定义执行顺序并突出阻塞点
验证每个事项是否符合就绪标准（Definition of Ready，简称DoR）

Process

流程

1. Declare objective

1. 明确目标

What should the sprint deliver as an observable result?
One phrase that guides trade-off decisions during the sprint

Sprint应交付哪些可观测的成果？
用一句话描述，作为Sprint过程中权衡决策的指导原则

2. Review backlog

2. 评审待办事项列表

Consult:

Epic with pending stories
Retro with pending improvement actions
Backlog items that have been validated via
```
/agile-refinement
```

参考内容：

包含未完成用户故事的史诗任务（Epic）
包含未完成改进行动的回顾会议（Retro）结果
已通过
```
/agile-refinement
```
验证的Backlog事项

3. Select items

3. 选择事项

For each selected item, register:

Name and objective
Estimated size
Value (why now?)
Dependencies and blockers

对于每个选定的事项，记录以下信息：

名称与目标
预估规模
价值（为什么选择现在做？）
依赖关系与阻塞点

4. Validate DoR

4. 验证就绪标准（DoR）

Each item must have:

Clear problem and objective
Scope and out of scope recorded
Files/areas mapped
Verifiable acceptance criteria
Test-first path for product behavior, especially validation, API contracts, permissions, offline/sync behavior, and critical flows

If an item doesn't have DoR, it doesn't enter the sprint — needs decomposition via

/agile-epic

or validation via

/agile-refinement

每个事项必须具备以下条件：

明确的问题与目标
已记录的范围与非范围内容
已映射的文件/涉及区域
可验证的验收标准
针对产品行为的测试先行路径，尤其是验证环节、API契约、权限、离线/同步行为以及关键流程

如果事项不符合DoR标准，则不能纳入Sprint，需要通过

/agile-epic

进行分解或通过

/agile-refinement

进行验证。

5. Order execution

5. 确定执行顺序

What must be done first (unblocks the rest)?
What can run in parallel?
What is the critical path?

哪些任务必须优先完成（以解除其他任务的阻塞）？
哪些任务可以并行执行？
关键路径是什么？

6. Distribute across team

6. 团队任务分配

When 2+ developers are available:

Assign items to developers or tracks (e.g., Backend, Frontend)
Identify items that can be worked on simultaneously
Define interface contracts or mocks to avoid blocking between tracks
Use Mermaid diagrams to visualize parallel assignments

当有2名及以上开发人员时：

将事项分配给开发人员或对应赛道（例如：Backend、Frontend）
识别可同时开展的事项
定义接口契约或模拟数据，以避免不同赛道间的阻塞
使用Mermaid图表可视化并行任务分配

7. Register commitments

7. 记录承诺内容

Available capacity (days, constraints, number of developers)
Sprint commitment (selected items, assigned to whom)
What is left out (postponed items)

可用产能（天数、约束条件、开发人员数量）
Sprint承诺内容（选定的事项、分配对象）
未纳入的事项（延期处理的任务）

Where to save

存储位置

planning/<initiative>/sprints/sprint-YYYY-MM-DD.md

(co-located with the initiative)

```
planning/sprints/sprint-YYYY-MM-DD.md
```
(if the sprint spans multiple initiatives)

planning/<initiative>/sprints/sprint-YYYY-MM-DD.md

（与对应项目计划存放在一起）

```
planning/sprints/sprint-YYYY-MM-DD.md
```
（当Sprint涉及多个项目计划时）

Chaining

关联Skill

To detail the first item: suggest
```
/agile-story
```
for the first story in the backlog
For items that need decomposition: suggest
```
/agile-epic
```
For items that need validation: suggest
```
/agile-refinement
```
For process or skill friction discovered while planning: suggest
```
/agile-skill-feedback
```

如需细化首个事项：建议对Backlog中的第一个用户故事使用
```
/agile-story
```
对于需要分解的事项：建议使用
```
/agile-epic
```
对于需要验证的事项：建议使用
```
/agile-refinement
```
对于规划过程中发现的流程或Skill问题：建议使用
```
/agile-skill-feedback
```

Reference template

参考模板

Use

templates/sprint.md

from this skill as base.

以本Skill中的

templates/sprint.md

为基础模板。

Rules

规则

Don't select more items than capacity allows. Over-commitment generates frustration and inconsistency.
Each item must have DoR. Without DoR, it doesn't enter the sprint.
The sprint objective must be observable, not vague.
Dependencies must be explicit — don't assume "it will fit".
Sprint planning feeds execution. If planning doesn't generate clarity, execution will suffer.

不要选择超出产能范围的事项。过度承诺会导致团队挫败感和工作成果不一致。
每个事项必须符合DoR标准。不符合标准的事项不能纳入Sprint。
Sprint目标必须是可观测的，不能模糊不清。
依赖关系必须明确，不要假设“自然能衔接”。
Sprint规划为执行提供指导。如果规划过程未明确方向，执行环节会受到影响。

Relationship with the flow

与工作流的关系

mermaid

flowchart LR
    A["/agile-retro"] --> B["/agile-sprint"]
    B --> C["/agile-story"]
    C --> D[execution]
    D --> E["/agile-status"]
    E --> F["/agile-review"]
    F --> G["/agile-retro"]

This skill starts the sprint cycle. For decomposing work, use

/agile-epic

. For execution plans, use

/agile-story

. For tracking during the sprint, use

/agile-status

mermaid

flowchart LR
    A["/agile-retro"] --> B["/agile-sprint"]
    B --> C["/agile-story"]
    C --> D[execution]
    D --> E["/agile-status"]
    E --> F["/agile-review"]
    F --> G["/agile-retro"]

该Skill启动Sprint周期。如需分解工作，请使用

/agile-epic

；如需制定执行计划，请使用

/agile-story

；如需在Sprint期间跟踪进度，请使用

/agile-status

。