guideline-generation by anthropics/knowledge-work-plugins
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill guideline-generation从任意组合的来源中生成全面、LLM就绪的品牌声音准则——品牌文档、销售通话记录、发现报告或直接用户输入。将原始材料转化为结构化的、可执行的准则,并附带置信度评分和待解决问题。
接受以下任意组合:
当提供发现报告时,将其作为主要输入——来源已经过分类和排序。根据需要补充额外的分析。
确定用户提供了什么。如果没有可用来源:
/brand-voice:discover-brand 生成的发现报告.claude/brand-voice.local.md 以获取已知品牌材料位置/brand-voice:discover-brand对于文档: 委托给文档分析代理进行深度解析。提取声音属性、消息主题、术语、语气指导和示例。
对于记录: 委托给对话分析代理进行模式识别。提取隐含的声音属性、成功的语言模式、上下文相关的语气以及反模式。
提取预先分类的来源、冲突和空白。直接使用已排序的来源。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
将所有发现合并成一个统一的准则文档,遵循 references/guideline-template.md 中的模板。关键部分:
"我们是 / 我们不是" 表格 —— 核心品牌身份锚点:
| 我们是 | 我们不是 |
|---|---|
| [属性 — 例如:"自信"] | [对立面 — 例如:"傲慢"] |
| [属性 — 例如:"平易近人"] | [对立面 — 例如:"随意或马虎"] |
从所有来源中最一致的模式中推导出属性。每一行都应有支持证据。
声音常量 vs. 语气灵活性 —— 阐明哪些是固定的,哪些是适应的:
按上下文划分的语气矩阵:
| 上下文 | 正式程度 | 活力 | 技术深度 | 示例 |
|---|---|---|---|---|
| 陌生拜访 | 中等 | 高 | 低 | "[示例短语]" |
| 企业提案 | 高 | 中等 | 高 | "[示例短语]" |
| 社交媒体 | 低 | 高 | 低 | "[示例短语]" |
使用 references/confidence-scoring.md 中的方法为每个部分评分:
为任何无法解决的模糊之处生成待解决问题:
## 供团队讨论的待解决问题
### 高优先级(阻碍准则完成)
1. **[问题标题]**
- 发现内容:[冲突或不完整的信息]
- 代理建议:[建议的解决方案及理由]
- 需要您:[具体的决定或确认]
每个待解决问题必须包含代理建议。将模糊性转化为"确认或覆盖"——永远不要陷入死胡同。
在呈现之前,通过质量保证代理(定义在 agents/quality-assurance.md 中)进行验证:
总结关键发现:
默认保存位置是用户工作文件夹内的 .claude/brand-voice-guidelines.md。
重要提示: 代理的工作目录可能不是用户的项目根目录(尤其是在 Cowork 中,插件从插件缓存目录运行)。始终相对于用户的工作文件夹解析路径,而不是当前工作目录。如果未设置工作文件夹,则跳过文件保存,并告知用户准则仅在此次对话中可用。
.claude/brand-voice-guidelines.md。在写入前确认工作文件夹路径。brand-voice-guidelines-YYYY-MM-DD.md(使用今天的日期).claude/brand-voice-guidelines.md<完整路径>。未来的会话中 /brand-voice:enforce-voice 将自动找到它们。"准则也存在于本次对话中,因此 /brand-voice:enforce-voice 可以立即使用它们,而无需从文件加载。
保存后,提供:
/brand-voice:enforce-voice 创建内容在整个生成工作流中强制执行这些隐私约束,而不仅仅是在输出时:
references/guideline-template.md —— 包含所有部分、字段定义和格式指导的完整输出模板references/confidence-scoring.md —— 置信度评分方法、阈值和示例每周安装次数
79
代码仓库
GitHub 星标数
8.8K
首次出现
14 天前
安全审计
安装于
codex76
opencode74
github-copilot74
amp74
kimi-cli74
gemini-cli74
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.
Accept any combination of:
When a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.
Determine what the user has provided. If no sources are available:
/brand-voice:discover-brand run.claude/brand-voice.local.md for known brand material locations/brand-voice:discover-brandFor 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.
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:
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]" |
Score each section using the methodology in references/confidence-scoring.md:
Generate open questions for any ambiguity that cannot be resolved:
## Open Questions for Team Discussion
### High Priority (blocks guideline completion)
1. **[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.
Before presenting, verify via the quality-assurance agent (defined in agents/quality-assurance.md):
Summarize key findings:
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.
.claude/brand-voice-guidelines.md inside the user's working folder. Confirm the working folder path before writing.brand-voice-guidelines-YYYY-MM-DD.md in the same directory (using today's date).claude/brand-voice-guidelines.md inside the working folder<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:
/brand-voice:enforce-voiceEnforce these privacy constraints throughout the entire generation workflow, not only at output time:
references/guideline-template.md — Complete output template with all sections, field definitions, and formatting guidancereferences/confidence-scoring.md — Confidence scoring methodology, thresholds, and examplesWeekly Installs
79
Repository
GitHub Stars
8.8K
First Seen
14 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex76
opencode74
github-copilot74
amp74
kimi-cli74
gemini-cli74
超能力技能使用指南:AI助手技能调用优先级与工作流程详解
40,300 周安装
社交媒体内容策略指南:LinkedIn、Twitter、Instagram、TikTok、Facebook平台优化与内容创作模板
303 周安装
data-extractor 数据提取技能:从PDF、Word、Excel等文档自动提取结构化数据
304 周安装
架构决策框架:需求驱动架构设计,ADR记录决策,权衡分析指南
304 周安装
使用reveal.js创建HTML幻灯片 | 交互式演示文稿制作工具 | 代码高亮与动画效果
304 周安装
移动应用发布策略指南:从ASO优化到推广渠道的完整发布计划
304 周安装
计分卡营销系统:四步法生成高转化率潜在客户,互动评估提升线索质量
304 周安装