guideline-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Guideline Generation

指南生成

Generate comprehensive, LLM-ready brand voice guidelines from any combination of sources — brand documents, sales call transcripts, discovery reports, or direct user input. Transform raw materials into structured, enforceable guidelines with confidence scoring and open questions.

从任意组合的来源（品牌文档、销售通话记录、调研报告或用户直接输入）生成全面的、适配LLM的品牌语音指南。将原始材料转化为结构化、可执行的指南，并附带置信度评分和待解决问题。

Inputs

输入内容

Accept any combination of:

Discovery report from the discover-brand skill (structured, pre-triaged)
Brand documents uploaded or from connected platforms (PDF, PPTX, DOCX, MD, TXT)
Conversation transcripts from Gong, Granola, manual uploads, or Notion meeting notes
Direct user input about their brand voice and values

When a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.

接受以下任意组合的输入：

来自discover-brand skill的调研报告（结构化、已预先分类）
上传或来自关联平台的品牌文档（PDF、PPTX、DOCX、MD、TXT格式）
来自Gong、Granola、手动上传或Notion会议纪要的对话记录
用户关于品牌语音与价值观的直接输入

若提供了调研报告，则将其作为主要输入——其中的来源已完成分类和排序。必要时可补充额外分析。

Generation Workflow

生成工作流

1. Identify and Classify Sources

1. 识别并分类来源

Determine what the user has provided. If no sources are available:

Check if a discovery report exists from a previous
```
/brand-voice:discover-brand
```
run
Check
```
.claude/brand-voice.local.md
```
for known brand material locations
Suggest running discovery first:
```
/brand-voice:discover-brand
```

确定用户提供的内容类型。若未提供任何来源：

检查是否存在之前运行
```
/brand-voice:discover-brand
```
生成的调研报告
检查
```
.claude/brand-voice.local.md
```
文件，查看已知品牌材料的存储位置
建议先运行调研命令：
```
/brand-voice:discover-brand
```

2. Process Sources

2. 处理来源

For documents: Delegate to the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.

For transcripts: Delegate to the conversation-analysis agent for pattern recognition. Extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.

For discovery reports: Extract pre-triaged sources, conflicts, and gaps. Use the ranked sources directly.

对于文档： 委托给文档分析Agent进行深度解析。提取语音属性、信息主题、术语、语调指导及示例。

对于通话记录： 委托给对话分析Agent进行模式识别。提取隐含的语音属性、成功的语言模式、不同场景下的语调及反模式。

对于调研报告： 提取已预先分类的来源、冲突点和信息缺口。直接使用已排序的来源内容。

3. Synthesize Into Guidelines

3. 合成为指南

Merge all findings into a unified guideline document following the template in

references/guideline-template.md

. Key sections:

"We Are / We Are Not" Table — The core brand identity anchor:

We Are	We Are Not
[Attribute — e.g., "Confident"]	[Counter — e.g., "Arrogant"]
[Attribute — e.g., "Approachable"]	[Counter — e.g., "Casual or sloppy"]

Derive attributes from the most consistent patterns across sources. Each row should have supporting evidence.

Voice Constants vs. Tone Flexes — Clarify what stays fixed and what adapts:

Voice = personality, values, "We Are / We Are Not" — constant across all content
Tone = formality, energy, technical depth — flexes by context

Tone-by-Context Matrix:

Context	Formality	Energy	Technical Depth	Example
Cold outreach	Medium	High	Low	"[example phrase]"
Enterprise proposal	High	Medium	High	"[example phrase]"
Social media	Low	High	Low	"[example phrase]"

将所有发现整合为统一的指南文档，遵循

references/guideline-template.md

中的模板。核心章节如下：

“我们的特质 / 我们避免的特质”表 — 品牌核心身份锚点：

我们的特质	我们避免的特质
[属性示例："自信"]	[反例："傲慢"]
[属性示例："平易近人"]	[反例："随意或散漫"]

从各来源中最一致的模式推导属性。每一行都应附带支撑证据。

固定语音 vs 灵活语调 — 明确固定内容与可调整内容：

语音 = 品牌个性、价值观、“我们的特质 / 我们避免的特质” — 在所有内容中保持一致
语调 = 正式程度、活力、技术深度 — 可根据场景调整

场景-语调矩阵：

场景	正式程度	活力	技术深度	示例
陌生客户开发	中等	高	低	"[示例语句]"
企业提案	高	中等	高	"[示例语句]"
社交媒体	低	高	低	"[示例语句]"

4. Assign Confidence Scores

4. 分配置信度评分

Score each section using the methodology in

references/confidence-scoring.md

High confidence: 3+ corroborating sources, explicit guidance found
Medium confidence: 1-2 sources, or inferred from patterns
Low confidence: Single source, inferred, or conflicting data

使用

references/confidence-scoring.md

中的方法为每个章节评分：

高置信度：3个及以上佐证来源，找到明确指导内容
中等置信度：1-2个来源，或从模式中推导得出
低置信度：单一来源、推导得出或存在冲突数据

5. Surface Open Questions

5. 提出待解决问题

Generate open questions for any ambiguity that cannot be resolved:

markdown

undefined

针对所有无法解决的歧义生成待解决问题：

markdown

undefined

Open Questions for Team Discussion

团队讨论待解决问题

High Priority (blocks guideline completion)

高优先级（阻碍指南完成）

[Question Title]
- What was found: [conflicting or incomplete info]
- Agent recommendation: [suggested resolution with reasoning]
- Need from you: [specific decision or confirmation needed]


Every open question MUST include an agent recommendation. Turn ambiguity into "confirm or override" — never a dead end.

[问题标题]
- 已发现内容：[冲突或不完整信息]
- Agent建议：[带推理的解决方案建议]
- 需要您提供：[具体决策或确认信息]


每个待解决问题必须包含Agent的建议。将歧义转化为“确认或否决”的明确选项，而非死胡同。

6. Quality Check

6. 质量检查

Before presenting, verify via the quality-assurance agent (defined in

agents/quality-assurance.md

All major sections populated (including Brand Personality and Content Examples if sources support them)
At least 3 voice attributes with evidence
"We Are / We Are Not" table has 4+ rows
Tone matrix covers at least 3 contexts
Confidence scores assigned per section
Source attribution for all extracted elements
No PII exposed
Open questions include recommendations

在呈现结果前，通过质量保障Agent（定义于

agents/quality-assurance.md

）进行验证：

所有主要章节已填充（若来源支持，需包含品牌个性和内容示例）
至少有3个带证据的语音属性
“我们的特质 / 我们避免的特质”表包含4行及以上内容
语调矩阵覆盖至少3种场景
每个章节已分配置信度评分
所有提取元素均标注来源
未暴露任何PII（个人可识别信息）
待解决问题包含建议内容

7. Present and Offer Next Steps

7. 呈现结果并提供后续步骤

Summarize key findings:

Total sections generated with confidence breakdown
Strongest voice attribute and most effective message
Number of open questions (if any)

总结关键发现：

生成的章节总数及置信度分布
最突出的语音属性和最有效的信息
待解决问题的数量（若有）

8. Save for Future Sessions

8. 保存以供后续会话使用

The default save location is

.claude/brand-voice-guidelines.md

inside the user's working folder.

Important: The agent's working directory may not be the user's project root (especially in Cowork, where plugins run from a plugin cache directory). Always resolve the path relative to the user's working folder, not the current working directory. If no working folder is set, skip the file save and tell the user guidelines will only be available in this conversation.

Resolve the save path. The file MUST be saved to
```
.claude/brand-voice-guidelines.md
```
inside the user's working folder. Confirm the working folder path before writing.
Check if guidelines already exist at that path
If they exist, archive the previous version: Rename the existing file to
```
brand-voice-guidelines-YYYY-MM-DD.md
```
in the same directory (using today's date)
Save new guidelines to
```
.claude/brand-voice-guidelines.md
```
inside the working folder
Confirm to the user with the full absolute path: "Guidelines saved to
```
<full-path>
```
.
```
/brand-voice:enforce-voice
```
will find them automatically in future sessions."

The guidelines are also present in this conversation, so

/brand-voice:enforce-voice

can use them immediately without loading from file.

After saving, offer:

Walk through the guidelines section by section
Start creating content with
```
/brand-voice:enforce-voice
```
Resolve open questions

默认保存位置为用户工作文件夹内的

.claude/brand-voice-guidelines.md

。

重要提示： Agent的工作目录可能并非用户的项目根目录（尤其是在Cowork环境中，插件从插件缓存目录运行）。务必相对于用户的工作文件夹而非当前工作目录解析路径。若未设置工作文件夹，则跳过文件保存步骤，并告知用户指南仅在本次会话中可用。

解析保存路径。文件必须保存至用户工作文件夹内的
```
.claude/brand-voice-guidelines.md
```
。写入前请确认工作文件夹路径。
检查指南是否已存在于该路径
若已存在，归档旧版本：将现有文件重命名为同目录下的
```
brand-voice-guidelines-YYYY-MM-DD.md
```
（使用当前日期）
保存新指南至工作文件夹内的
```
.claude/brand-voice-guidelines.md
```
向用户确认保存结果，提供完整绝对路径：“指南已保存至
```
<完整路径>
```
。后续会话中
```
/brand-voice:enforce-voice
```
可自动调用该指南。”

指南也会同步至本次会话中，因此

/brand-voice:enforce-voice

可立即使用该指南，无需从文件加载。

保存完成后，提供以下后续选项：

逐章节浏览指南内容
使用
```
/brand-voice:enforce-voice
```
开始创建内容
解决待解决问题

Privacy and Security

隐私与安全

Enforce these privacy constraints throughout the entire generation workflow, not only at output time:

Redact customer names and contact information from all examples
Anonymize company names in transcript excerpts if requested
Flag any sensitive information detected during processing

在整个生成工作流中严格执行以下隐私约束，而非仅在输出阶段：

从所有示例中隐去客户姓名和联系方式
若用户要求，在通话记录摘录中匿名化公司名称
标记处理过程中检测到的任何敏感信息

Reference Files

参考文件

references/guideline-template.md
— Complete output template with all sections, field definitions, and formatting guidance
references/confidence-scoring.md
— Confidence scoring methodology, thresholds, and examples

references/guideline-template.md
— 完整输出模板，包含所有章节、字段定义和格式指导
references/confidence-scoring.md
— 置信度评分方法、阈值及示例