cmd-speckit-clarify

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Agent skill wrapper for the Claude command

/speckit.clarify

When the original command text references

{{INPUT}}

$1

, or named arguments, map them from the user's current request.

用于Claude命令

/speckit.clarify

的Agent技能封装器。

当原始命令文本引用

{{INPUT}}

、

$1

或命名参数时，从用户当前请求中映射对应的内容。

Systematically resolve underspecified areas in a feature spec through structured questioning. Run before

/speckit.plan

通过结构化提问系统性地解决功能规格书中未明确的内容。需在运行

/speckit.plan

之前执行。

Locate the spec:
- If input names a feature or file path, use it.
- Otherwise check
```
.specify/specs/*/spec.md
```
  ; if multiple, ask which to clarify.
- Fall back to
```
spec.md
```
  in the project root.
Load context: Read
```
spec.md
```
and
```
.specify/memory/constitution.md
```
if present.
Scan for ambiguities across nine taxonomy categories:
- Functional scope, Data model, UX flows, Non-functional attributes, Integration points, Edge cases, Constraints, Terminology, Completion signals.
Select questions: Choose the 5 highest-impact ambiguities. Prioritize by: scope > security > UX > technical detail. Each question must materially affect architecture, data modeling, testing, UX, or compliance.
Ask one question at a time:
- Present the question with 2-5 multiple-choice options (or note that a short phrase is acceptable).
- Mark the recommended answer with reasoning.
- Wait for the user's answer before asking the next question.
Update spec incrementally: After each answer, incorporate the clarification naturally into the relevant spec section. Do not append a Q&A log — merge it into the prose.
Final validation: Check for duplicates, contradictions, and terminology drift across the updated spec.
Report: Coverage map across all nine ambiguity categories (resolved / deferred / clear / outstanding).

Next step: Run

/speckit.plan

to generate the technical implementation plan.

定位规格书：
- 如果输入指定了功能名称或文件路径，直接使用该路径。
- 否则检查
```
.specify/specs/*/spec.md
```
  ；若存在多个文件，询问用户要澄清哪一个。
- 若上述路径都不存在，默认使用项目根目录下的
```
spec.md
```
  。
加载上下文：读取
```
spec.md
```
，若存在
```
.specify/memory/constitution.md
```
也一并读取。
扫描模糊内容：覆盖九个分类维度：
- 功能范围、数据模型、用户体验流程、非功能属性、集成点、边缘案例、约束条件、术语定义、完成信号。
筛选问题：选择影响最大的5个模糊点。优先级排序：范围 > 安全 > 用户体验 > 技术细节。每个问题必须对架构、数据建模、测试、用户体验或合规性有实质性影响。
逐个提问：
- 提出问题时附带2-5个选择题选项（或说明可接受简短回答）。
- 标注推荐答案并给出理由。
- 等待用户回答后再提出下一个问题。
逐步更新规格书：每次得到回答后，将澄清内容自然整合到规格书的相关章节中。不要附加问答日志——直接合并到正文里。
最终验证：检查更新后的规格书是否存在重复内容、矛盾点以及术语不一致的问题。
生成报告：涵盖所有九个模糊分类维度的覆盖情况（已解决/延迟处理/清晰待确认/未解决）。

下一步：运行

/speckit.plan

生成技术实施方案。