brainstorming

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Brainstorming

头脑风暴

You are facilitating interactive exploration of ideas through Socratic Q&A. The goal is understanding before implementation — documents grow progressively during the session and end as lightweight pre-PRDs that feed into

/research

/create-plan

你将通过苏格拉底式问答引导交互式的想法探索。核心目标是先理解再落地——会话期间文档会逐步完善，最终成为轻量化的预PRD文档，为

/research

或

/create-plan

提供输入。

Working Agreement

工作约定

Brainstorming is interactive by design — Q&A is the whole point. Use

AskUserQuestion

for every prompt, one question at a time (see Step 3 for the loop). This skill intentionally does not follow the

desplega:ask-user

batching convention — Socratic exploration needs single, focused questions.

File-review is on by default — invoke it on the brainstorm doc after synthesis.

头脑风暴本质是交互式的——问答是核心环节。每次提示都使用

AskUserQuestion

，一次只提一个问题（详见步骤3的循环逻辑）。本技能特意不遵循

desplega:ask-user

的批量提问惯例——苏格拉底式探索需要单一、聚焦的问题。

文件审核默认开启——在完成归纳后，对头脑风暴文档调用该功能。

When to Use

适用场景

This skill activates when:

User invokes
```
/brainstorm
```
command

Another skill references

**REQUIRED SUB-SKILL:** Use desplega:brainstorming

User wants to explore an idea before committing to research or planning
User isn't ready for formal research yet

在以下场景激活本技能：

用户调用
```
/brainstorm
```
命令

其他技能引用

**REQUIRED SUB-SKILL:** Use desplega:brainstorming

用户希望在开展研究或规划前探索某个想法
用户尚未准备好进行正式研究

Autonomy Mode

自主模式

Brainstorming is inherently interactive, so only two modes are supported:

Mode	Behavior
Verbose (Default)	Full Socratic exploration, ask one question at a time, rich discussion
Critical	Fewer questions, focus on the most impactful areas, reach synthesis faster

Autopilot is not supported — brainstorming requires human input by design. If Autopilot is requested, fall back to Critical with a note explaining why.

The autonomy mode is passed by the invoking command. If not specified, default to Verbose.

头脑风暴天生需要交互，因此仅支持两种模式：

模式	行为
Verbose（默认）	完整的苏格拉底式探索，每次提出一个问题，进行充分讨论
Critical	提出更少的问题，聚焦最具影响力的领域，更快达成结论

不支持Autopilot模式——头脑风暴设计上需要人工输入。若用户请求Autopilot模式，则默认切换为Critical模式，并附带说明原因。

自主模式由调用命令传入。若未指定，默认使用Verbose模式。

Process Steps

流程步骤

Step 1: Initialize Document

步骤1：初始化文档

Create

thoughts/<username|shared>/brainstorms/YYYY-MM-DD-<topic>.md

using the template at

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

Path selection: Use the user's name (e.g.,

thoughts/taras/brainstorms/

) if known from context. Fall back to

thoughts/shared/brainstorms/

when unclear.

Fill in the frontmatter and the Context section with whatever is known: the topic, any context provided, initial thoughts. Write what we know so far.

使用

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

中的模板，创建

thoughts/<username|shared>/brainstorms/YYYY-MM-DD-<topic>.md

文件。

路径选择：若上下文已知用户名，则使用用户名称路径（例如

thoughts/taras/brainstorms/

）。若信息不明确，则 fallback 至

thoughts/shared/brainstorms/

路径。

填写文档前置元数据（frontmatter）和“上下文”部分，填入已知信息：主题、任何提供的背景信息、初始想法。记录当前已了解的内容。

Prior Learning Recall

过往学习回忆

OPTIONAL SUB-SKILL: If

~/.agentic-learnings.json

exists, run

/learning recall <current topic>

to check for relevant prior learnings before proceeding.

可选子技能：若存在

~/.agentic-learnings.json

文件，在继续流程前运行

/learning recall <current topic>

，检查是否有相关的过往学习内容。

Step 2: Assess Phase

步骤2：评估阶段

Understand the shape of the exploration. Use AskUserQuestion with:

Question	Options
"What kind of exploration is this?"	1. Problem to solve, 2. Idea to develop, 3. Comparison to make, 4. Workflow to improve, 5. Other (describe)

Update the document's

exploration_type

frontmatter and Context section with the exploration framing.

明确探索的方向。使用AskUserQuestion提出以下问题：

问题	选项
"本次探索的类型是什么？"	1. 需要解决的问题，2. 需要发展的想法，3. 需要进行的对比，4. 需要优化的工作流，5. 其他（请描述）

更新文档前置元数据中的

exploration_type

字段，以及“上下文”部分的探索框架内容。

Step 3: Explore Phase

步骤3：探索阶段

Socratic Q&A loop. The goal is to systematically uncover requirements, constraints, and insights.

Rules:

Ask ONE question at a time via AskUserQuestion

After each answer, append a new section to the document under

## Exploration

markdown

### Q: [Your question]
[User's answer]

**Insights:** [Any observations, implications, or connections you noticed]

Identify the next most important question to narrow scope or deepen understanding
Continue until the user signals they're satisfied or natural saturation is reached

Question strategy:

Start broad: understand the problem space and goals
Narrow progressively: constraints, existing solutions, non-functional requirements
Probe edges: "What would make this fail?", "What's the simplest version?", "What are you NOT trying to solve?"

苏格拉底式问答循环。目标是系统性地挖掘需求、约束条件和洞察。

规则：

通过AskUserQuestion一次只提一个问题

用户回答后，在文档的

## Exploration

部分追加新章节：

markdown

### Q: [Your question]
[User's answer]

**Insights:** [Any observations, implications, or connections you noticed]

确定下一个最重要的问题，以缩小范围或深化理解
持续循环，直到用户表示满意或自然达到探索饱和状态

提问策略：

从宽泛问题开始：理解问题空间和目标
逐步缩小范围：约束条件、现有解决方案、非功能性需求
探索边界情况：“什么会导致这个失败？”、“最简版本是什么样的？”、“你不打算解决的问题是什么？”

YAGNI Principle

YAGNI原则

CRITICAL: Resist premature solutions during the Explore phase. The goal is understanding, not implementation. If the user starts solutioning too early:

Acknowledge the idea briefly
Redirect to requirements: "That's an interesting approach. Before we commit to it, let's make sure we understand [relevant constraint/requirement]. [Follow-up question]"
Solutions belong in the Synthesis or in a subsequent
```
/create-plan
```

关键提示：在探索阶段避免过早提出解决方案。核心目标是理解，而非落地。若用户过早开始讨论解决方案：

简要认可该想法
引导回需求讨论：“这是个有趣的思路。在我们确定这个方案前，先确保我们理解[相关约束/需求]。[跟进问题]”
解决方案应放在归纳阶段或后续的
```
/create-plan
```
流程中

Step 4: Synthesize Phase

步骤4：归纳阶段

When exploration is complete (user signals done, or natural saturation), append a

## Synthesis

section:

markdown

undefined

当探索完成（用户示意结束或自然达到饱和），追加

## Synthesis

章节：

markdown

undefined

Synthesis

Key Decisions

[Decision 1]
[Decision 2]

[Decision 1]
[Decision 2]

Open Questions

[Question that still needs investigation]

[Question that still needs investigation]

Constraints Identified

[Constraint 1]
[Constraint 2]

[Constraint 1]
[Constraint 2]

Core Requirements

[Requirement 1 — lightweight PRD-style]
[Requirement 2]

undefined

[Requirement 1 — lightweight PRD-style]
[Requirement 2]

undefined

Learning Capture

学习内容留存

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：若本次工作流中产生了重要的洞察、模式、注意事项或决策，可以考虑使用

desplega:learning

通过

/learning capture

命令留存这些内容。重点留存能帮助他人在未来会话中提升效率的学习内容。

Step 5: Handoff Phase

步骤5：交接阶段

Before handoff, offer to run

/review

on the brainstorm document to identify unexplored areas.

Then use AskUserQuestion with:

Question	Options
"What's the next step?"	1. Start research based on this brainstorm (→ `/research` ), 2. Create a plan directly (→ `/create-plan` ), 3. Done for now (park the brainstorm)

Based on the answer:

Research: Suggest the
```
/research
```
command with the brainstorm file as input context
Plan: Suggest the
```
/create-plan
```
command with the brainstorm file as input context
Done: Set the document's
```
status
```
to
```
parked
```
or
```
complete
```
as appropriate

交接前，主动提出对头脑风暴文档运行

/review

，以识别未探索的领域。

然后使用AskUserQuestion提出以下问题：

问题	选项
"下一步计划是什么？"	1. 基于本次头脑风暴启动研究（→ `/research` ），2. 直接创建计划（→ `/create-plan` ），3. 暂时结束（归档本次头脑风暴）

根据用户回答执行：

研究：建议使用
```
/research
```
命令，并将头脑风暴文件作为输入上下文
计划：建议使用
```
/create-plan
```
命令，并将头脑风暴文件作为输入上下文
结束：将文档的
```
status
```
设置为
```
parked
```
或
```
complete
```
（根据实际情况）

Document Evolution

文档演进

The brainstorm document is a living artifact during the session. It starts rough and gains structure through the Q&A process. By the end, it should be readable as a standalone context document that someone else could pick up and understand.

头脑风暴文档在会话期间是动态更新的产物。初始状态较为粗糙，通过问答过程逐步形成结构。会话结束时，它应成为一份独立可读的上下文文档，其他人接手后也能理解内容。

Review Integration

审核集成

File-review is on by default:

After synthesis, invoke
```
/file-review:file-review <path>
```
for inline human comments
Process feedback with the
```
file-review:process-review
```
skill

文件审核默认开启：

归纳完成后，调用
```
/file-review:file-review <path>
```
获取人工 inline 评论
使用
```
file-review:process-review
```
技能处理反馈