brand-guidelines

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Brand Guidelines Generator

品牌规范生成器

Create a self-contained brand guidelines skill through guided discovery. The generated skill lives at the user level and enforces brand identity across all future Claude Code sessions.

通过引导式调研创建独立的品牌规范 skill，生成的 skill 属于用户级别，会在未来所有 Claude Code 会话中统一生效，确保品牌标识一致性。

Workflow Overview

工作流概览

Execute these phases in strict order. Phase 0 is optional (skip if the user has no existing assets to share). Never skip Phases 1-4. Each phase builds on the previous.

Phase	Name	Action	Output
0	Context Ingestion	Collect + analyze existing business assets	Extracted brand signals + smart defaults for discovery
1	Brand Discovery	Interactive questionnaire across 6 dimensions	User preferences for brand identity
2	Synthesis & Preview	Format and present brand summary	User-confirmed brand identity spec
3	Skill Generation	Generate user-level SKILL.md from template	`~/.claude/skills/{brand-slug}/SKILL.md`
4	Optional DS Creation	Create design systems for unmapped asset types	Updated mapping table in brand skill

请严格按照顺序执行以下阶段，阶段0为可选（若用户没有可分享的现有资产可跳过），阶段1-4不可跳过，每个阶段都基于前一阶段的输出构建。

阶段	名称	操作	输出
0	上下文摄入	收集+分析现有业务资产	提取的品牌信号+调研智能默认值
1	品牌调研	覆盖6个维度的交互式问卷	用户确认的品牌标识偏好
2	整合与预览	格式化并展示品牌摘要	用户确认的品牌标识规范
3	Skill生成	基于模板生成用户级 SKILL.md	`~/.claude/skills/{brand-slug}/SKILL.md`
4	可选设计系统创建	为未映射的资产类型创建设计系统	品牌skill中更新后的映射表

Phase 0: Context Ingestion (Optional)

阶段0：上下文摄入（可选）

Before starting discovery, ask the user if they have existing business assets to share. Existing context dramatically reduces the number of questions needed — the skill extracts what it can and only asks about what's missing or ambiguous.

Opening prompt: "Before we start defining your brand, do you have any existing assets I can learn from? These could be your website, newsletter archives, social media profiles, pitch decks, brand documents, images, or anything that represents your brand today. This is optional — we can build entirely from scratch too."

Supported input types:

Input Type	How to Provide	What to Extract
Website URL	User provides a URL like `https://mybrand.com`	Use WebFetch to capture the page. Extract: brand name, tagline (from hero/header), mission/about copy, value proposition, tone signals from copywriting style, target audience signals, content categories (→ asset types). Follow internal links to About, Mission, and similar pages if present.
Newsletter / blog posts	User provides URLs, files, or pastes content	Analyze writing style for voice and tone signals. Extract: recurring topics (→ value prop), how the author addresses readers (→ audience), vocabulary level (→ tone modifiers), sentence structure patterns.
Documents	User provides file paths (PDF, MD, TXT, DOCX)	Read and analyze. Could be pitch decks, brand guides, one-pagers, course outlines, etc. Extract any brand identity data present.
Images / logos	User provides file paths or pastes images	Read images visually. Extract: brand name from wordmarks, color palette signals, visual style/mood, existing design system hints.
Social media profiles	User provides profile URLs	Use WebFetch to capture. Extract: bio (→ tagline/mission), content themes, posting style (→ voice), follower description (→ audience), platform mix (→ asset types).
Existing brand skill	User points to a previous SKILL.md	Read it as a starting point for updates. Pre-fill all dimensions from existing data.
Skip	User has no assets to share	Proceed directly to Phase 1 with no smart defaults.

Analysis protocol:

For each provided asset, extract and categorize signals into the 6 discovery dimensions:

Dimension	What to Look For
1. Brand name & tagline	Literal brand name, slogans, header text, social bios
2. Mission & value prop	About pages, mission statements, "what we do" sections, pitch deck opening slides
3. Voice & tone traits	Copywriting style — formal vs. casual, assertive vs. supportive, humorous vs. serious
4. Tone modifiers	Sentence length patterns, vocabulary level, use of jargon, narrative vs. direct style
5. Target audiences	Who the content addresses ("you" references), testimonials, case studies, subscriber descriptions
6. Asset types	What visual content exists (thumbnails, social posts, headers, slides, etc.)

After analysis, present a summary:

"Here's what I extracted from your assets:

Brand name: {name} | Tagline: {tagline or "none found"}

Mission signals: {1-2 sentence summary of what the brand appears to be about}

Voice signals: {detected traits, e.g., "Reads as friendly and expert — conversational but backs up claims"}

Tone signals: {detected modifiers, e.g., "Short punchy sentences, casual vocabulary, avoids jargon"}

Audience signals: {who the content seems to target}

Asset types spotted: {list of visual content types found}

I'll use these as starting points during discovery. You'll have full control to confirm, adjust, or override everything."

Store the complete analysis as

context_analysis

with per-dimension confidence levels:

High confidence — clear, unambiguous signal (e.g., brand name from a logo, explicit mission statement)
Medium confidence — strong signal but inferred (e.g., voice traits from writing style analysis)
Low confidence — weak or mixed signals (e.g., audience guessed from content topics)

开始调研前，先询问用户是否有可分享的现有业务资产，现有上下文能大幅减少需要提问的问题数量——skill会尽可能提取已有信息，仅对缺失或模糊的内容发起询问。

开场提示语： "在我们开始定义你的品牌前，你有没有可以供我学习的现有资产？可以是你的官网、通讯存档、社交媒体主页、 pitch deck、品牌文档、图片，或者任何能代表你当前品牌的内容。这一步是可选的，我们也完全可以从零开始搭建品牌规范。"

支持的输入类型：

输入类型	提供方式	提取内容
网站URL	用户提供类似 `https://mybrand.com` 的链接	使用 WebFetch 抓取页面，提取：品牌名称、标语（来自首屏/页头）、使命/关于文案、价值主张、文案风格传递的语气信号、目标受众信号、内容分类（→资产类型），如果存在关于、使命等内部链接也跟进抓取。
通讯/博客文章	用户提供URL、文件或粘贴内容	分析写作风格提取语气信号，提取： recurring 话题（→价值主张）、作者对读者的称呼方式（→受众）、词汇难度（→语气修饰项）、句式结构模式。
文档	用户提供文件路径（PDF、MD、TXT、DOCX）	读取并分析，可能是 pitch deck、品牌指南、单页介绍、课程大纲等，提取所有存在的品牌标识数据。
图片/Logo	用户提供文件路径或粘贴图片	视觉识别图片内容，提取：字标中的品牌名称、调色板信号、视觉风格/调性、现有设计系统线索。
社交媒体主页	用户提供主页URL	使用 WebFetch 抓取，提取：简介（→标语/使命）、内容主题、发帖风格（→语气）、粉丝描述（→受众）、使用的平台组合（→资产类型）。
现有品牌skill	用户指向之前的 SKILL.md	读取作为更新的起点，用现有数据预填充所有维度。
跳过	用户无资产可分享	无智能默认值，直接进入阶段1。

分析规则：

对每一份提供的资产，提取信号并归类到6个调研维度中：

维度	提取方向
1. 品牌名称与标语	字面品牌名、 slogan、页头文本、社交简介
2. 使命与价值主张	关于页面、使命声明、"我们的业务"板块、 pitch deck 开场页
3. 语气与风格特质	文案风格——正式vs随意、坚定vs支持、幽默vs严肃
4. 语气修饰项	句子长度模式、词汇难度、行话使用情况、叙事式vs直接式风格
5. 目标受众	内容面向的对象（"你"的指代对象）、推荐语、案例研究、订阅者描述
6. 资产类型	存在的视觉内容类型（缩略图、社交帖子、页头、幻灯片等）

分析完成后展示摘要：

"以下是我从你提供的资产中提取的信息：

品牌名称： {name} | 标语： {tagline 或 "未找到"}

使命信号： {1-2句话总结品牌的核心业务方向}

语气信号： {检测到的特质，例如"读起来友好且专业——对话感强但所有说法都有依据"}

风格信号： {检测到的修饰项，例如"短句有力、词汇口语化、避免使用行话"}

受众信号： 内容看起来面向的人群

识别到的资产类型： {找到的视觉内容类型列表}

我会在后续调研中将这些信息作为起点，你完全可以确认、调整或者覆盖所有内容。"

将完整分析结果存储为

context_analysis

，附带每个维度的置信度：

高置信度——清晰、无歧义的信号（例如Logo中的品牌名、明确的使命声明）
中置信度——信号强烈但属于推断结果（例如从写作风格分析得到的语气特质）
低置信度——信号弱或混杂（例如从内容主题推测的受众）

Phase 1: Brand Discovery

阶段1：品牌调研

Guide the user through structured questions to define their brand identity. Use the AskUserQuestion tool to present options. Ask questions one dimension at a time to keep the conversation focused.

Load the full question bank from references/discovery-framework.md.

Rules:

Ask dimensions in order (they build on each other)
One dimension per AskUserQuestion call — do not batch across dimensions
If Phase 0 produced smart defaults, adapt each dimension based on confidence level (see Smart Default Behavior below)
For open-ended dimensions, use AskUserQuestion with broad options that prompt elaboration
For multi-choice dimensions, present all options with descriptions and enable
```
multiSelect
```
After each answer, give a brief 1-sentence acknowledgment contextualizing the choice, then move to the next dimension
Complete ALL 6 dimensions before moving to Phase 2
If the user wants to go back and change a previous answer, allow it

Smart Default Behavior (when Phase 0 data exists):

Confidence	Behavior
High	Present the extracted value and ask for confirmation: "From your website, I found your brand name is {name}* with tagline {tagline}. Sound right, or want to change it?"* Use AskUserQuestion with the extracted value as the first option and "I want to change this" as the second.
Medium	Present the extracted value as a suggested default: "Based on your writing style, I'd suggest Friendly & approachable* + Expert & authoritative — your content is conversational but backs up claims with evidence. Does this match your intent?"* Still present all options with the suggestion pre-noted.
Low	Present all options normally but note what was observed: "Your content seems to target developers, but I wasn't sure — who is your primary audience?"
No signal	Ask the full question as defined in the discovery framework with no pre-selection.

Dimensions (in order):

Brand name & tagline
Mission & value proposition
Voice & tone traits
Tone modifiers
Target audiences
Asset types & design system mapping

Dimension 6 — Special handling:

Before presenting asset type options, scan

~/.claude/.context/design-systems/

to discover available design systems. For each directory found, read the design system markdown file to extract the style name.

After the user selects their asset types, ask a follow-up for each selected asset type: which design system should be used? Present three options per asset type:

Each discovered design system (by style name)
"Create new design system" — flags this type for Phase 4
"Decide later" — leaves the mapping empty for now

Store the complete mapping as

asset_ds_mapping

通过结构化问题引导用户定义品牌标识，使用 AskUserQuestion 工具展示选项，每次仅提问一个维度，保持对话聚焦。

从 references/discovery-framework.md 加载完整问题库。

规则：

按顺序提问维度（维度之间相互关联）
每次 AskUserQuestion 调用仅覆盖一个维度——不要跨维度批量提问
如果阶段0生成了智能默认值，根据置信度调整每个维度的提问方式（见下方智能默认行为）
开放式维度使用 AskUserQuestion 提供宽泛选项引导用户详细说明
多选维度展示所有带描述的选项并开启
```
multiSelect
```
收到每个回答后，给出1句话的简短确认说明用户的选择，然后进入下一个维度
完成全部6个维度的提问后再进入阶段2
如果用户想返回修改之前的回答，允许修改

智能默认行为（存在阶段0数据时）：

置信度	行为
高	展示提取到的值并请求确认："从你的官网我提取到你的品牌名称是 {name}，标语是 {tagline}，对吗？还是你想要修改？" 使用 AskUserQuestion ，将提取到的值作为第一个选项，"我想要修改"作为第二个选项。
中	将提取到的值作为建议默认值展示："基于你的写作风格，我建议选择友好易接近* + 专业权威——你的内容对话感强但所有说法都有证据支撑，这符合你的预期吗？"* 仍然展示所有选项，提前标注建议项。
低	正常展示所有选项但标注观察到的内容："你的内容看起来面向开发者，但我不太确定，你的核心受众是谁？"
无信号	按照调研框架的定义完整提问，不做预选。

维度（按顺序）：

品牌名称与标语
使命与价值主张
语气与风格特质
语气修饰项
目标受众
资产类型与设计系统映射

维度6——特殊处理：

展示资产类型选项前，扫描

~/.claude/.context/design-systems/

路径查找可用的设计系统，对每个找到的目录，读取设计系统 markdown 文件提取风格名称。

用户选择完资产类型后，为每个选中的资产类型追加提问：应该使用哪个设计系统？每个资产类型提供三个选项：

每个已发现的设计系统（按风格名称展示）
"创建新的设计系统"——标记该类型进入阶段4处理
"稍后决定"——暂时留空映射关系

将完整映射存储为

asset_ds_mapping

。

Phase 2: Synthesis & Preview

阶段2：整合与预览

After all 6 dimensions are answered, synthesize into a formatted brand summary and present for confirmation.

Steps:

Derive the brand slug from the brand name: lowercase, spaces and special characters replaced by hyphens (e.g., "AI Launchpad Newsletter" →
```
ai-launchpad-newsletter
```
)
Synthesize voice traits + tone modifiers into 3-4 voice application rules — concrete, actionable guidelines for how this brand should sound
Derive brand anti-patterns from the inverse of chosen voice traits (see mapping in template reference)
Build audience profiles — for each audience segment, infer goals, frustrations, what resonates, and preferred platforms based on the user's description
Format the complete brand summary:

Present to the user:

undefined

所有6个维度都收集完回答后，整合为格式化的品牌摘要并提交用户确认。

步骤：

从品牌名称生成 品牌slug：小写，空格和特殊字符替换为连字符（例如 "AI Launchpad Newsletter" →
```
ai-launchpad-newsletter
```
）
将语气特质+语气修饰项整合为3-4条 语气应用规则——具体、可执行的品牌声音指导规范
从所选语气特质的反方向推导 品牌反模式（见模板参考中的映射关系）
构建 受众画像——对每个受众分组，根据用户的描述推断其目标、痛点、感兴趣的内容和偏好的平台
格式化完整的品牌摘要：

向用户展示：

undefined

Brand Summary: {brand_name}

品牌摘要：{brand_name}

Tagline: {tagline} Mission: {mission} Value Prop: {value_prop}

Voice Traits: {trait_1}, {trait_2} Tone Modifiers: {modifier_1}, {modifier_2}

Voice Application Rules:

{rule_1}
{rule_2}
{rule_3}

Audiences:

Primary: {primary_audience}
Secondary: {secondary_audience}

Asset Type → Design System Mapping:

Asset Type	Design System
{type_1}	{ds_1 or "Create new" or "Decide later"}
...	...

Anti-Patterns (things this brand should NEVER do):

{anti_pattern_1}
{anti_pattern_2}
...


6. Ask the user: "Does this brand summary look right? Want to change anything before I generate the skill?"
7. If the user wants changes, update the relevant fields and re-present
8. Once confirmed, proceed to Phase 3

---

标语： {tagline} 使命： {mission} 价值主张： {value_prop}

语气特质： {trait_1}, {trait_2} 风格修饰项： {modifier_1}, {modifier_2}

语气应用规则：

{rule_1}
{rule_2}
{rule_3}

受众：

核心：{primary_audience}
次级：{secondary_audience}

资产类型 → 设计系统映射：

资产类型	设计系统
{type_1}	{ds_1 或 "新建" 或 "稍后决定"}
...	...

反模式（本品牌绝对不能做的事）：

{anti_pattern_1}
{anti_pattern_2}
...


6. 询问用户："这份品牌摘要是否正确？在我生成skill前你想要修改任何内容吗？"
7. 如果用户想要修改，更新对应字段后重新展示
8. 获得确认后进入阶段3

---

Phase 3: Skill Generation

阶段3：Skill生成

Generate the brand guidelines skill at

~/.claude/skills/{brand-slug}/SKILL.md

Steps:

Load the template from references/brand-skill-template.md
Fill every
```
{{placeholder}}
```
with the confirmed brand data from Phase 2
Ensure the generated skill is fully self-contained — all brand data embedded directly, no references to external config files
Create the directory
```
~/.claude/skills/{brand-slug}/
```
if it doesn't exist
Write the generated SKILL.md to
```
~/.claude/skills/{brand-slug}/SKILL.md
```
Verify the generated skill — read the file back and check:
- No unfilled
```
{{placeholder}}
```
  markers remain
- All 6 sections are present (Brand Identity, Voice & Tone, Target Audiences, Design System Resolution, How To Apply, Brand Anti-Patterns)
- The asset type mapping table has the correct number of rows
- If any issues found, fix and re-write before proceeding
Inform the user:
"Your brand guidelines skill has been created at
```
~/.claude/skills/{brand-slug}/SKILL.md
```
. Restart Claude Code to activate it — user-level skills are loaded at startup."

在路径

~/.claude/skills/{brand-slug}/SKILL.md

下生成品牌规范skill。

步骤：

从 references/brand-skill-template.md 加载模板
用阶段2确认的品牌数据填充所有
```
{{placeholder}}
```
占位符
确保生成的skill完全独立——所有品牌数据直接嵌入，不引用外部配置文件
如果目录
```
~/.claude/skills/{brand-slug}/
```
不存在则创建
将生成的 SKILL.md 写入路径
```
~/.claude/skills/{brand-slug}/SKILL.md
```
验证生成的skill——回读文件检查：
- 没有残留未填充的
```
{{placeholder}}
```
  标记
- 包含全部6个板块（品牌标识、语气与风格、目标受众、设计系统匹配、应用方式、品牌反模式）
- 资产类型映射表行数正确
- 发现任何问题修复后再重写文件
告知用户：
"你的品牌规范skill已创建在路径
```
~/.claude/skills/{brand-slug}/SKILL.md
```
，重启 Claude Code 即可激活——用户级skill会在启动时加载。"

Phase 4: Optional DS Creation

阶段4：可选设计系统创建

If any asset types in

asset_ds_mapping

were mapped to "Create new design system", offer to create them now.

Steps:

List all asset types mapped to "Create new"
Ask the user: "You flagged {N} asset type(s) for new design systems: {list}. Want to create them now, or come back later?"
If the user wants to create now: a. For each asset type, invoke the branding-kit:design-system skill (suggest "user level" as the output location so it's available system-wide) b. After each design system is created, update the brand skill's mapping table:
- Read
```
~/.claude/skills/{brand-slug}/SKILL.md
```
- Replace the "Create new" entry for that asset type with the new design system's style name and path
- Write the updated file
If the user wants to come back later, remind them they can update the mapping manually or re-invoke this skill in "update" mode

如果

asset_ds_mapping

中有资产类型被标记为"创建新的设计系统"，询问用户是否现在创建。

步骤：

列出所有被标记为"新建"的资产类型
询问用户："你标记了{N}个资产类型需要新建设计系统：{list}，想要现在创建还是稍后处理？"
如果用户选择现在创建： a. 对每个资产类型，调用 branding-kit:design-system skill（建议输出位置为"用户级别"，可全系统可用） b. 每个设计系统创建完成后，更新品牌skill的映射表：
- 读取
```
~/.claude/skills/{brand-slug}/SKILL.md
```
- 将对应资产类型的"新建"条目替换为新设计系统的风格名称和路径
- 写入更新后的文件
如果用户选择稍后处理，提醒他们可以手动更新映射，或者以"更新"模式重新调用本skill

Updating an Existing Brand Skill

更新现有品牌Skill

If the user already has a brand skill (detected by checking

~/.claude/skills/

for existing brand directories), offer an abbreviated update flow.

Update workflow:

List discovered brand skills from
```
~/.claude/skills/*/SKILL.md
```
Ask the user which brand to update
Read the existing brand skill
Ask which dimensions to update (multi-select from the 6 dimensions)
Run only the selected dimensions from Phase 1
Re-synthesize only the affected sections
Update the existing SKILL.md (preserve unchanged sections)
Inform the user to restart Claude Code

如果用户已有品牌skill（通过检查

~/.claude/skills/

路径下的现有品牌目录检测到），提供简化的更新流程。

更新工作流：

列出
```
~/.claude/skills/*/SKILL.md
```
路径下发现的所有品牌skill
询问用户想要更新哪个品牌
读取现有品牌skill
询问想要更新哪些维度（从6个维度中多选）
仅运行阶段1中选中的维度
仅重新整合受影响的板块
更新现有 SKILL.md（保留未修改的板块）
告知用户重启 Claude Code

Error Handling

错误处理

If
```
~/.claude/.context/design-systems/
```
does not exist or is empty during Dimension 6, inform the user no design systems are available yet and offer "Create new" or "Decide later" as the only options
If
```
~/.claude/skills/{brand-slug}/SKILL.md
```
already exists, ask the user whether to overwrite or choose a different slug
If the brand name produces an empty or invalid slug, ask the user to provide a custom slug
If the user's voice trait + modifier combination creates a contradictory voice (e.g., "Bold & provocative" + "Casual vocabulary" for a financial services brand), flag the tension during synthesis and ask which direction to prioritize

维度6处理阶段如果
```
~/.claude/.context/design-systems/
```
路径不存在或为空，告知用户暂无可用设计系统，仅提供"新建"或"稍后决定"两个选项
如果
```
~/.claude/skills/{brand-slug}/SKILL.md
```
已存在，询问用户是否覆盖或者选择其他slug
如果品牌名称生成的slug为空或无效，要求用户提供自定义slug
如果用户选择的语气特质+修饰项组合产生矛盾的声音（例如金融服务品牌选择"大胆激进"+"口语化词汇"），在整合阶段提示冲突，询问优先方向