start-discussion

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Invoke the technical-discussion skill for this conversation.

⚠️ ZERO OUTPUT RULE: Do not narrate your processing. Produce no output until a step or reference file explicitly specifies display content. No "proceeding with...", no discovery summaries, no routing decisions, no transition text. Your first output must be content explicitly called for by the instructions.

请针对本次对话调用technical-discussion skill。

⚠️ 零输出规则：不要叙述你的处理过程。除非某一步骤或参考文件明确指定要展示内容，否则不要产生任何输出。禁止出现“正在进行……”、研究总结、路由决策、过渡性文本等内容。你的首次输出必须是指令明确要求的内容。

Workflow Context

工作流背景

This is Phase 2 of the six-phase workflow:

Phase	Focus	You
1. Research	EXPLORE - ideas, feasibility, market, business
2. Discussion	WHAT and WHY - decisions, architecture, edge cases	◀ HERE
3. Specification	REFINE - validate into standalone spec
4. Planning	HOW - phases, tasks, acceptance criteria
5. Implementation	DOING - tests first, then code
6. Review	VALIDATING - check work against artifacts

Stay in your lane: Capture the WHAT and WHY - decisions, rationale, competing approaches, edge cases. Don't jump to specifications, plans, or code. This is the time for debate and documentation.

这是六阶段工作流的第二阶段：

阶段	核心关注点	当前位置
1. 研究阶段	探索——创意、可行性、市场、业务层面
2. 讨论阶段	核心问题与原因——决策、架构、边缘案例	◀ 此处
3. 规范阶段	细化——验证并形成独立规范文档
4. 规划阶段	实施路径——阶段划分、任务、验收标准
5. 执行阶段	落地——先测试，再编码
6. 评审阶段	验证——对照产出物检查工作成果

坚守当前阶段职责：聚焦核心问题与原因——决策、架构、边缘案例。不要提前进入规范、规划或编码阶段。此阶段的重点是辩论与文档记录。

Instructions

操作说明

Follow these steps EXACTLY as written. Do not skip steps or combine them. Present output using the EXACT format shown in examples - do not simplify or alter the formatting.

CRITICAL: This guidance is mandatory.

After each user interaction, STOP and wait for their response before proceeding
Never assume or anticipate user choices
Even if the user's initial prompt seems to answer a question, still confirm with them at the appropriate step
Complete each step fully before moving to the next
Do not act on gathered information until the skill is loaded - it contains the instructions for how to proceed

严格按照以下步骤执行，不得跳过或合并步骤。输出格式必须与示例完全一致——不得简化或修改格式。

关键要求：以下指导为强制性要求。

每次用户交互后，暂停并等待用户回复后再继续
切勿假设或预判用户的选择
即使用户的初始提示看似回答了某个问题，仍需在适当步骤与用户确认
完成当前步骤的全部内容后，再进入下一个步骤
在加载skill之前，不要对收集到的信息采取任何行动——skill中包含后续操作的具体指令

Step 0: Run Migrations

步骤0：执行迁移

This step is mandatory. You must complete it before proceeding.

Invoke the

/migrate

skill and assess its output.

If files were updated: STOP and wait for the user to review the changes (e.g., via

git diff

) and confirm before proceeding to Step 1. Do not continue automatically.

If no updates needed: Proceed to Step 1.

此步骤为必填项，必须完成后才能继续。

调用

/migrate

skill并评估其输出结果。

若文件已更新：暂停并等待用户查看变更（例如通过

git diff

命令）并确认后，再进入步骤1。不得自动继续。

若无需更新：直接进入步骤1。

Step 1: Discovery State

步骤1：检索当前状态

.claude/skills/start-discussion/scripts/discovery.sh

If the above shows a script invocation rather than YAML output, the dynamic content preprocessor did not run. Execute the script before continuing:

bash

.claude/skills/start-discussion/scripts/discovery.sh

If YAML content is already displayed, it has been run on your behalf.

Parse the discovery output to understand:

From
research
section:

```
exists
```
- whether research files exist
```
files
```
- each research file's name and topic
```
checksum
```
- current checksum of all research files

From
discussions
section:

```
exists
```
- whether discussion files exist
```
files
```
- each discussion's name, status, and date
```
counts.in_progress
```
and
```
counts.concluded
```
- totals for routing

From
cache
section:

```
status
```
- one of three values:
- ```
"valid"
```
  - cache exists and checksums match (safe to load)
- ```
"stale"
```
  - cache exists but research has changed (needs re-analysis)
- ```
"none"
```
  - no cache file exists
```
reason
```
- explanation of the status
```
generated
```
- when the cache was created (null if none)
```
research_files
```
- list of files that were analyzed

From
state
section:

scenario

- one of:

"fresh"

"research_only"

"discussions_only"

"research_and_discussions"

IMPORTANT: Use ONLY this script for discovery. Do NOT run additional bash commands (ls, head, cat, etc.) to gather state - the script provides everything needed.

→ Proceed to Step 2.

.claude/skills/start-discussion/scripts/discovery.sh

如果上述内容显示的是脚本调用而非YAML输出，说明动态内容预处理器未运行。请先执行以下脚本：

bash

.claude/skills/start-discussion/scripts/discovery.sh

如果已显示YAML内容，则代表该脚本已代为执行。

解析检索输出内容，明确以下信息：

来自
research
板块：

```
exists
```
- 是否存在研究文件
```
files
```
- 每个研究文件的名称与主题
```
checksum
```
- 所有研究文件的当前校验和

来自
discussions
板块：

```
exists
```
- 是否存在讨论文件
```
files
```
- 每个讨论的名称、状态与日期
```
counts.in_progress
```
和
```
counts.concluded
```
- 用于路由的统计总数

来自
cache
板块：

```
status
```
- 三种状态之一：
- ```
"valid"
```
  - 缓存存在且校验和匹配（可安全加载）
- ```
"stale"
```
  - 缓存存在但研究内容已变更（需要重新分析）
- ```
"none"
```
  - 不存在缓存文件
```
reason
```
- 状态说明
```
generated
```
- 缓存创建时间（若不存在则为null）
```
research_files
```
- 已分析的文件列表

来自
state
板块：

scenario

- 四种场景之一：

"fresh"

、

"research_only"

、

"discussions_only"

、

"research_and_discussions"

重要提示：仅可使用此脚本进行检索。不得运行其他bash命令（如ls、head、cat等）来收集状态信息——该脚本已提供所有所需内容。

→ 进入步骤2。

Step 2: Route Based on Scenario

步骤2：根据场景选择路径

Use

state.scenario

from the discovery output to determine the path:

根据检索输出中的

state.scenario

确定后续路径：

If scenario is "research_only" or "research_and_discussions"

若场景为"research_only"或"research_and_discussions"

Research exists and may need analysis.

→ Proceed to Step 3.

存在研究内容，可能需要进行分析。

→ 进入步骤3。

If scenario is "discussions_only"

若场景为"discussions_only"

No research exists, but discussions do. Skip research analysis.

→ Proceed to Step 4.

不存在研究内容，但存在讨论文件。跳过研究分析步骤。

→ 进入步骤4。

If scenario is "fresh"

若场景为"fresh"

No research or discussions exist yet.

Starting fresh - no prior research or discussions found.

What topic would you like to discuss?

STOP. Wait for user response.

When user responds, proceed with their topic.

→ Proceed to Step 6.

尚未存在任何研究或讨论内容。

当前为全新状态——未发现任何过往研究或讨论内容。

你希望讨论什么主题？

暂停，等待用户回复。

用户回复后，根据其指定的主题继续。

→ 进入步骤6。

Step 3: Research Analysis

步骤3：研究分析

Load research-analysis.md and follow its instructions as written.

→ Proceed to Step 4.

加载**research-analysis.md**并严格按照其中的说明执行。

→ 进入步骤4。

Step 4: Present Options

步骤4：展示选项

Load display-options.md and follow its instructions as written.

→ Proceed to Step 5.

加载**display-options.md**并严格按照其中的说明执行。

→ 进入步骤5。

Step 5: Handle Selection

步骤5：处理选项选择

Load handle-selection.md and follow its instructions as written.

→ Proceed to Step 6.

加载**handle-selection.md**并严格按照其中的说明执行。

→ 进入步骤6。

Step 6: Gather Context

步骤6：收集上下文信息

Load gather-context.md and follow its instructions as written.

→ Proceed to Step 7.

加载**gather-context.md**并严格按照其中的说明执行。

→ 进入步骤7。

Step 7: Invoke the Skill

步骤7：调用Skill

Load invoke-skill.md and follow its instructions as written.

加载**invoke-skill.md**并严格按照其中的说明执行。