questioning

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Questioning

问答功能

You are answering a question directly and concisely using the research process. No documents are created by default — the answer is the deliverable.

你需要借助研究流程直接、简洁地回答问题。默认不创建文档——答案即为交付成果。

When to Use

使用场景

This skill activates when:

User invokes
```
/question
```
command
Another skill references
```
desplega:questioning
```
User asks a focused question that doesn't need a full research document

在以下情况激活此技能：

用户调用
```
/question
```
命令
其他技能引用
```
desplega:questioning
```
用户提出聚焦性问题，无需完整研究文档

Philosophy

设计理念

This is the fastest path from question to answer. Unlike

/research

(which documents comprehensively) or

/brainstorm

(which explores interactively),

/question

gets straight to the point:

Hear the question
Investigate as needed
Answer inline
Offer next steps

No ceremony — no autonomy prompts, no preference setup, no working agreement. Just answer the question.

When you do need to ask the user something (handoff, follow-up choice), use

AskUserQuestion

per

desplega:ask-user

conventions.

这是从问题到答案的最快路径。与

/research

（全面生成文档）或

/brainstorm

（交互式探索）不同，

/question

直奔主题：

接收问题
按需开展调研
在线给出答案
提供后续操作选项

无需繁琐流程——无需自主提示、偏好设置或工作协议，只需回答问题即可。

当你需要向用户询问信息（切换功能、后续选择）时，请遵循

desplega:ask-user

规范使用

AskUserQuestion

。

Process

流程步骤

Step 1: Analyze the Question

步骤1：分析问题

Classify the question to determine what investigation is needed:

Question Type	Investigation Needed	Example
Factual/locational	Quick codebase search	"Where is the auth middleware defined?"
Conceptual/how	Read relevant files	"How does the plugin system discover skills?"
Why/root cause	Deep read + history	"Why does brainstorming default to verbose?"
Comparative	Read multiple areas	"What's the difference between research and question skills?"
External/library	context7 or web search	"How does Bun's SQLite driver handle transactions?"

对问题进行分类，确定所需调研操作：

问题类型	所需调研操作	示例
事实/定位类	快速搜索代码库	"认证中间件定义在哪里？"
概念/方法类	阅读相关文件	"插件系统如何发现技能？"
原因/根源类	深度阅读+历史记录	"为什么头脑风暴默认采用 verbose 模式？"
对比类	阅读多个相关区域	"research 和 question 技能有什么区别？"
外部/库类	使用 context7 或网页搜索	"Bun's SQLite driver 如何处理事务？"

Step 2: Investigate

步骤2：开展调研

Based on the question type, use the appropriate tools. Spawn sub-agents only when needed — many questions can be answered by reading a few files directly.

For codebase questions:

Read directly mentioned files first (use Read tool WITHOUT limit/offset)
Use codebase-locator agent if you need to find WHERE something lives
Use codebase-analyzer agent if you need to understand HOW something works
Use codebase-pattern-finder agent if you need examples of a pattern

For library/framework questions:

Use context7 MCP to fetch documentation (
```
resolve-library-id
```
→
```
query-docs
```
)

For external/web questions:

Use web-search-researcher agent for documentation or examples

Efficiency rule: If you can answer by reading 1-3 files, just read them. Don't spawn sub-agents for simple lookups.

根据问题类型，使用合适的工具。仅在必要时启动子 Agent——许多问题只需直接阅读少量文件即可解答。

针对代码库问题：

优先阅读直接提及的文件（使用 Read 工具，无需设置 limit/offset）
若需查找内容位置，使用 codebase-locator agent
若需理解工作原理，使用 codebase-analyzer agent
若需查找模式示例，使用 codebase-pattern-finder agent

针对库/框架问题：

使用 context7 MCP 获取文档（
```
resolve-library-id
```
→
```
query-docs
```
）

针对外部/网页问题：

使用 web-search-researcher agent 获取文档或示例

效率规则：如果阅读1-3个文件即可解答，直接阅读即可。简单查询无需启动子 Agent。

Step 3: Answer

步骤3：给出答案

Present the answer as inline text (not a document). Structure it naturally based on the question:

Short answers: 1-3 sentences with a file:line reference
Medium answers: A paragraph or two with key references
Detailed answers: Structured with headings if needed, but keep it focused

Unlike research, you MAY:

Suggest improvements if the question implies a problem
Perform root cause analysis if the question asks "why"
Give opinions when asked ("which approach is better?")
Be direct and opinionated rather than exhaustively neutral

Always include:

Specific
```
file:line
```
references for any claims about the codebase
Code snippets when they clarify the answer (keep them short)

以在线文本形式呈现答案（而非文档）。根据问题类型自然组织内容：

简短答案：1-3句话，附带
```
文件:行号
```
引用
中等长度答案：1-2个段落，附带关键引用
详细答案：必要时可使用标题结构化内容，但需保持聚焦

与 research 不同，你可以：

若问题隐含需求，可提出改进建议
若问题询问“原因”，可进行根源分析
当被问及时给出观点（如“哪种方案更好？”）
直接表达观点，无需保持绝对中立

必须包含：

针对代码库相关结论，附带具体的
```
文件:行号
```
引用
若有助于说明答案，可附带简短代码片段

Step 4: Handoff

步骤4：功能切换

After answering, use AskUserQuestion with:

Question	Options
"What would you like to do next?"	1. Ask another question, 2. Save this answer to thoughts, 3. Start a brainstorm from this topic (→ `/brainstorm` ), 4. Start research from this topic (→ `/research` ), 5. Done

Based on the answer:

Ask another question: Use AskUserQuestion to ask "What's your next question?" and loop back to Step 1

Save this answer: Write the Q&A to

thoughts/<user>/questions/YYYY-MM-DD-<topic>.md

using the template at

cc-plugin/base/skills/questioning/template.md

. Path selection: use the user's name if known, fall back to

thoughts/shared/questions/

Brainstorm: Suggest
```
/brainstorm <topic>
```
with the question's topic as context
Research: Suggest
```
/research <topic>
```
with the question's topic as context
Done: No further action

回答完毕后，使用 AskUserQuestion 提供以下选项：

问题	选项
"接下来你想做什么？"	1. 提出另一个问题, 2. 将此答案保存至想法库, 3. 基于此主题启动头脑风暴（→ `/brainstorm` ）, 4. 基于此主题启动研究（→ `/research` ）, 5. 结束

根据用户选择执行对应操作：

提出另一个问题：使用 AskUserQuestion 询问“你的下一个问题是什么？”，并回到步骤1
保存此答案：使用
```
cc-plugin/base/skills/questioning/template.md
```
中的模板，将问答内容写入
```
thoughts/<user>/questions/YYYY-MM-DD-<topic>.md
```
。路径选择：已知用户名则使用该路径，否则 fallback 至
```
thoughts/shared/questions/
```
头脑风暴：建议使用
```
/brainstorm <topic>
```
，并以当前问题主题为上下文
研究：建议使用
```
/research <topic>
```
，并以当前问题主题为上下文
结束：无需进一步操作

Looping Behavior

循环机制

When the user selects "Ask another question," the skill loops:

Ask for the next question via AskUserQuestion
Investigate and answer (Steps 1-3)
Present handoff options again (Step 4)

Each iteration is independent — no state accumulates between questions unless the user explicitly connects them.

当用户选择“提出另一个问题”时，技能进入循环：

通过 AskUserQuestion 询问下一个问题
调研并回答（步骤1-3）
再次提供功能切换选项（步骤4）

每次迭代相互独立——除非用户明确关联，否则问题之间不会累积状态。

Learning Capture

经验留存

OPTIONAL SUB-SKILL: If significant insights, patterns, gotchas, or decisions emerged during this workflow, consider using

desplega:learning

to capture them via

/learning capture

. Focus on learnings that would help someone else in a future session.

可选子技能：若在此工作流程中获得重要见解、模式、注意事项或决策，可考虑使用

desplega:learning

通过

/learning capture

留存。重点留存能为未来会话中的其他用户提供帮助的经验。

What This Skill is NOT

本技能不具备的功能

Not research: No comprehensive document, no frontmatter ceremony, no multi-section output
Not brainstorming: No Socratic Q&A loop, no progressive document
Not a chatbot: Each question gets proper investigation with codebase evidence, not surface-level responses

不是研究工具：不生成全面文档，无需前置流程，不输出多章节内容
不是头脑风暴工具：无苏格拉底式问答循环，不生成渐进式文档
不是普通聊天机器人：每个问题都需基于代码库证据开展调研，而非给出表面化回复