agile-router

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Router

Use this skill to decide which agile skill is appropriate and get directed to the correct one.

Initial context received via slash: $ARGUMENTS

$ARGUMENTS

is filled, use as context to determine the right skill. If empty, ask the user what they need help with.

使用此技能来决定合适的敏捷技能，并引导至正确的技能。

通过斜杠接收初始上下文：$ARGUMENTS

如果

$ARGUMENTS

已填写，则将其用作上下文来确定合适的技能。如果为空，请询问用户需要什么帮助。

Prompting

提示规范

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.

Decision point	Why structured	Suggested options
Suggested skill when ambiguous	Routes the work	list the 2–4 candidates with the recommendation flagged

Free-form prompts (no structured tool):

Problem description (so the router can decide)

No-pause mode: if the user has explicitly disabled mid-skill clarification, pick the highest-confidence recommendation and proceed; surface the decision and reasoning rather than asking.

遵循

CLAUDE.md

AGENTS.md

中的项目通用规范（"Skill Prompting Conventions"）。在以下决策点使用工具的结构化问题功能 —— Claude Code使用

AskUserQuestion

，Codex使用

ask_user_question

，OpenCode使用

question

。

决策点	为何使用结构化方式	建议选项
存在歧义时推荐技能	引导工作流向	列出2–4个候选技能，并标记推荐项

自由格式提示（不使用结构化工具）：

问题描述（以便路由技能做出判断）

无暂停模式：如果用户明确禁用了技能执行中的澄清环节，则选择置信度最高的推荐项并继续执行；需告知用户决策结果及理由，而非询问。

Scope

适用范围

This skill replaces both the planning router and the ceremonies router. It covers three areas:

Area	Question	Skills
What to create	What planning artifact fits this work?	`/agile-intake` , `/agile-roadmap` , `/agile-epic` , `/agile-story`
What ceremony to run	Where are we in the sprint cycle?	`/agile-sprint` , `/agile-review` , `/agile-retro`
What to track	How should I report progress?	`/agile-status` (checkpoint, consolidation, closure)
What to improve in the process	Did real usage expose a skill/template gap or overlap?	`/agile-skill-feedback`

此技能替代了规划路由和仪式路由。它涵盖三个领域：

领域	问题	技能
需创建什么	哪种规划工件适合此项工作？	`/agile-intake` , `/agile-roadmap` , `/agile-epic` , `/agile-story`
需开展什么仪式	我们处于冲刺周期的哪个阶段？	`/agile-sprint` , `/agile-review` , `/agile-retro`
需跟踪什么	我应如何汇报进度？	`/agile-status` （检查点、汇总、收尾）
流程中需改进什么	实际使用是否暴露了技能/模板的缺口或重叠？	`/agile-skill-feedback`

Decision tree

决策树

Planning: What artifact do I need?

规划：我需要哪种工件？

mermaid

flowchart TD
    A[New problem or request] --> B{Is the problem clear?}
    B -- No --> C["/agile-intake"]
    B -- Yes --> D{Multi-phase trajectory<br/>with dependencies?}
    D -- Yes --> I["/agile-roadmap"]
    I --> G["/agile-epic"]
    D -- "No, single initiative" --> E{What size?}
    E -- "Small, localized" --> F["/agile-story"]
    E -- "Medium/large, needs decomposition" --> G
    C --> H{Intake recommends...}
    H -- Multi-phase trajectory --> I
    H -- Single initiative --> G
    H -- Small/clear --> F

Note on
/agile-roadmap
: Roadmap is NOT defined by time horizon (e.g., "3-12 months"). It is defined by trajectory complexity. Even a 4-week initiative benefits from a roadmap if it has multiple sequenced phases with dependencies between them.

Note on
/agile-epic
: Handles both the epic overview and story decomposition. There is no separate story skill. Medium work that needs richer acceptance criteria goes through
/agile-epic
for structure, or directly to
/agile-story
if it's a single vertical delivery.

mermaid

flowchart TD
    A[New problem or request] --> B{Is the problem clear?}
    B -- No --> C["/agile-intake"]
    B -- Yes --> D{Multi-phase trajectory<br/>with dependencies?}
    D -- Yes --> I["/agile-roadmap"]
    I --> G["/agile-epic"]
    D -- "No, single initiative" --> E{What size?}
    E -- "Small, localized" --> F["/agile-story"]
    E -- "Medium/large, needs decomposition" --> G["/agile-epic"]
    C --> H{Intake recommends...}
    H -- Multi-phase trajectory --> I
    H -- Single initiative --> G
    H -- Small/clear --> F

关于
/agile-roadmap
的说明： Roadmap并非由时间范围（例如"3-12个月"）定义，而是由轨迹复杂度决定。即使是一个4周的项目，如果包含多个有依赖关系的有序阶段，使用Roadmap也会有所帮助。

关于
/agile-epic
的说明：该技能同时处理epic概述和用户故事拆分。没有单独的用户故事技能。需要更丰富验收标准的中等规模工作，可通过
/agile-epic
构建结构；如果是单一垂直交付，则可直接使用
/agile-story
。

Ceremonies: Where am I in the cycle?

仪式：我处于冲刺周期的哪个阶段？

Starting a sprint? →
```
/agile-sprint
```
Sprint just ended? →
```
/agile-review
```
(demo deliveries) then
```
/agile-retro
```
(reflect on process)
Backlog items unclear? →
```
/agile-epic
```
(decompose) or run
```
/agile-refinement
```
(validate)
Need metrics? →
```
/agile-metrics
```
(before review or retro)
A skill/template caused friction or overlaps with another? →
```
/agile-skill-feedback
```

即将启动冲刺？ →
```
/agile-sprint
```
刚结束冲刺？ →
```
/agile-review
```
（演示交付成果），然后是
```
/agile-retro
```
（反思流程）
待办事项不明确？ →
```
/agile-epic
```
（拆分）或运行
```
/agile-refinement
```
（验证）
需要指标数据？ →
```
/agile-metrics
```
（在评审或回顾之前使用）
某个技能/模板造成了阻碍或与其他技能/模板重叠？ →
```
/agile-skill-feedback
```

Tracking: How do I report progress?

跟踪：我应如何汇报进度？

Quick daily checkpoint? →
```
/agile-status
```
(checkpoint mode)
Period or milestone consolidation? →
```
/agile-status
```
(consolidation mode)
Delivery finished? →
```
/agile-status
```
(closure mode)
Skill library needs merge, split, deprecation, removal, or template refinement? →
```
/agile-skill-feedback
```

快速每日检查？ →
```
/agile-status
```
（检查点模式）
周期或里程碑汇总？ →
```
/agile-status
```
（汇总模式）
交付完成？ →
```
/agile-status
```
（收尾模式）
技能库需要合并、拆分、弃用、移除或模板优化？ →
```
/agile-skill-feedback
```

Light sizing

轻量级规模划分

Internal reference for AI agent — not exposed to users. Use plain language when communicating the recommendation.

Size	Description	Artifact	Skill
Extra small	Localized adjustment, 1 file, low risk	Task	`/agile-story`
Small	Small delivery, few files, simple validation	Task	`/agile-story`
Medium	Vertical delivery, several files, moderate validation	Epic story file or Task	`/agile-epic` or `/agile-story`
Large	Multiple coordinated stories, needs decomposition	Epic	`/agile-epic`
Extra large	Multi-story initiative, coordination needed	Epic	`/agile-epic`

AI Agent内部参考——不向用户展示。 向用户传达推荐时使用通俗易懂的语言。

规模	描述	工件	技能
特小	局部调整，仅涉及1个文件，低风险	任务	`/agile-story`
小	小型交付，涉及少量文件，验证简单	任务	`/agile-story`
中	垂直交付，涉及多个文件，验证中等	Epic用户故事文件或任务	`/agile-epic` 或 `/agile-story`
大	多个协同用户故事，需要拆分	Epic	`/agile-epic`
特大	多用户故事项目，需要协同	Epic	`/agile-epic`

When to use roadmap vs epic

何时使用Roadmap vs Epic

Sizing alone is not enough to decide between roadmap and epic. Use this checklist:

Use
/agile-roadmap
when 2+ apply (regardless of duration):

Multiple initiatives need sequencing (can't all run in parallel)
Decisions today affect future decisions (local optimization can become tech debt)
Stakeholders need to see the whole journey before approving individual steps
External dependencies (other teams, vendors, deadlines)
Total complexity exceeds what fits in a single epic

Use
/agile-epic
when:

Single coordinated initiative with clear scope
Can be broken into stories without needing a parent plan
Fits on one delivery wave (no distinct phases with different goals)

Anti-pattern: Assume roadmap = "long-term strategic plan". A 4-week work with 5 phases and hard ordering also benefits from a roadmap. The criterion is trajectory complexity, not duration.

仅靠规模划分不足以决定使用Roadmap还是Epic，请使用以下检查清单：

满足以下2项及以上时使用
/agile-roadmap
（无论时长）：

多个项目需要按顺序执行（无法全部并行）
当前决策会影响未来决策（局部优化可能导致技术债务）
利益相关者需要看到完整流程后才批准单个步骤
存在外部依赖（其他团队、供应商、截止日期）
总复杂度超出单个Epic的承载范围

满足以下条件时使用
/agile-epic
：

单个协同项目，范围明确
无需上级计划即可拆分为用户故事
可在一个交付周期内完成（没有不同目标的独立阶段）

反模式： 认为Roadmap等同于“长期战略计划”。一个包含5个阶段且必须按顺序执行的4周项目，同样能从Roadmap中获益。判断标准是轨迹复杂度，而非时长。

Process

流程

Listen to the user's context.
Determine which area applies: planning, ceremony, or tracking.
Apply the decision tree for that area.
Recommend the specific skill with a brief explanation.
Confirm with the user before they proceed.

接收用户的上下文信息。
判断适用领域：规划、仪式或跟踪。
应用对应领域的决策树。
推荐具体技能并附上简短说明。
在用户继续操作前确认推荐内容。

Rules

规则

This is a router skill — it evaluates and directs, but does not produce artifacts.
If the problem isn't clear, suggest
```
/agile-intake
```
before routing.
Use plain language when explaining the recommendation. Do not reference size codes.
Always confirm the recommendation with the user.

这是一个路由技能——仅负责评估和引导，不生成工件。
如果问题不明确，在路由前建议使用
```
/agile-intake
```
。
解释推荐内容时使用通俗易懂的语言，不要提及规模代码。
始终与用户确认推荐内容。

Available skills

可用技能

Skill	Purpose
`/agile-intake`	Capture vague problems
`/agile-roadmap`	Map multi-phase trajectories with dependencies (any duration)
`/agile-epic`	Structure initiatives, decompose into stories
`/agile-story`	Execution plan for localized changes
`/agile-refinement`	Validate planning artifacts and review code
`/agile-status`	Track progress (checkpoint, consolidation, closure)
`/agile-sprint`	Sprint planning ceremony
`/agile-review`	Sprint review and demo
`/agile-metrics`	Quantitative sprint metrics
`/agile-retro`	Retrospective with improvement actions
`/agile-proto`	Interactive UI prototypes
`/agile-onboarding`	New team member onboarding
`/agile-skill-feedback`	Improve, merge, split, deprecate, or remove skills from real usage evidence
`/agile-router`	This skill — guidance on which skill to use

技能	用途
`/agile-intake`	记录模糊问题
`/agile-roadmap`	绘制带有依赖关系的多阶段轨迹（无论时长）
`/agile-epic`	构建项目结构，拆分为用户故事
`/agile-story`	局部变更的执行计划
`/agile-refinement`	验证规划工件并评审代码
`/agile-status`	跟踪进度（检查点、汇总、收尾）
`/agile-sprint`	冲刺规划仪式
`/agile-review`	冲刺评审与演示
`/agile-metrics`	冲刺量化指标
`/agile-retro`	回顾并制定改进措施
`/agile-proto`	交互式UI原型
`/agile-onboarding`	新团队成员入职
`/agile-skill-feedback`	根据实际使用反馈改进、合并、拆分、弃用或移除技能
`/agile-router`	本技能——指导选择合适的技能

Relationship with the flow

与流程的关系

mermaid

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

This skill is a router. It evaluates and directs, but does not produce the final artifact. For specific work, use the recommended skill directly.

mermaid

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

本技能是一个路由技能，仅负责评估和引导，不生成最终工件。如需开展具体工作，请直接使用推荐的技能。