Token导航 LogoToken导航

Agent Skill · 研究检索

brand-identity-wizard(品牌识别向导)

brand-identity-wizard 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

brand-identity-wizard 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 65,896。

总安装 272周安装 11GitHub Stars 9下载 85核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:brand-identity-wizard(品牌识别向导)
来源仓库:https://github.com/cdeistopened/skill-stack
仓库路径:skills/brand-identity-wizard
安装命令:
npx skills add https://github.com/cdeistopened/skill-stack --skill brand-identity-wizard
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/cdeistopened/skill-stack --skill brand-identity-wizard

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

brand-identity-wizard 创建统一的品牌身份文档,供后续内容技能调用以确保跨平台表达一致性。它聚焦品牌定位、受众画像与价值主张提炼,解决多技能协作时的语境割裂问题。首次使用需回答系列引导问题,后续可直接引用生成的 brand-identity.md 文件。

适用于技能生态建设初期,帮助建立共享知识库而非一次性输出。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/brand-identity-wizard

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/cdeistopened/skill-stack --skill brand-identit…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

brand-identity-wizard 怎么安装?

在终端执行 npx skills add https://github.com/cdeistopened/skill-stack --skill brand-identity-wizard。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brand-identity-wizard 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

brand-identity-wizard 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

brand-identity-wizard 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

brand-identity-wizard 用的人多吗?

公开数据是累计安装 272 次,近一周安装 11 次,下载 85 次,GitHub 9 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

brand-identity-wizard 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
brand-identity-wizard

品牌识别向导 · 本页

2729只读未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Brand Identity Wizard

Create a comprehensive brand identity document that content skills can reference for consistent voice, messaging, and audience targeting.

Purpose

Many content skills (newsletters, podcasts, social posts, SEO articles) need brand context to produce on-brand content. This wizard creates a single brand-identity.md file that all skills can reference.

Core Philosophy: Define once, use everywhere. A well-defined brand identity enables consistent content creation across all channels.

When to Use This Wizard

Use this wizard when:

  • Setting up a new skills vault for a brand/company
  • Starting content production for a new client
  • Your brand identity has evolved and needs updating
  • Content feels inconsistent across different skills

You'll need:

  • 30-60 minutes for the initial interview
  • Access to existing brand materials (website, past content, style guides)
  • Decision-making authority on brand voice

The 5-Section Framework

Section 1: Brand Persona

Goal: Define who the brand is as if it were a person

Questions to Answer:
  1. If your brand were a person, who would they be?

- Name, background, expertise - What makes them uniquely qualified? - What's their origin story?

  1. What's their personality?

- Warm vs. reserved - Expert vs. peer - Serious vs. playful - Formal vs. casual

  1. What do they believe deeply?

- Core convictions (not just values) - What hills will they die on? - What conventional wisdom do they reject?

  1. What's their superpower?

- What do they do better than anyone else? - What unique perspective do they bring?

Output Format:
## Brand Persona

**Name:** [Name or brand name]
**Role:** [Their role/title in relation to audience]
**Background:** [2-3 sentences on origin story and qualifications]

**Personality Traits:**
- [Trait 1 with brief explanation]
- [Trait 2 with brief explanation]
- [Trait 3 with brief explanation]

**Core Beliefs:**
- [Belief 1]
- [Belief 2]
- [Belief 3]

**Superpower:** [One sentence on unique value proposition]

Section 2: Target Audience

Goal: Define who this brand serves and what they need

Questions to Answer:
  1. Primary Audience Profile:

- Demographics (age, location, profession) - Psychographics (values, goals, fears) - Current situation and pain points

  1. What transformation do they want?

- Where are they now? (Before state) - Where do they want to be? (After state) - What's blocking them?

  1. How do they describe their problem?

- Use their words, not industry jargon - What do they Google? - What do they complain about?

  1. Secondary Audiences:

- Who else might consume this content? - How do their needs differ?

Output Format:
## Target Audience

### Primary Audience
**Demographics:** [Age, location, profession, life stage]
**Psychographics:** [Values, lifestyle, interests]

**Current State:**
- [Pain point 1]
- [Pain point 2]
- [Pain point 3]

**Desired State:**
- [Goal 1]
- [Goal 2]
- [Goal 3]

**How They Describe It:**
- "[Quote-style description they'd use]"
- "[Another way they'd say it]"

### Secondary Audiences
**[Audience 2]:** [Brief description and how needs differ]
**[Audience 3]:** [Brief description and how needs differ]

Section 3: Voice & Tone

Goal: Define how the brand speaks and writes

Questions to Answer:
  1. Voice Spectrum Ratings (1-5 scale):

- Formal ← → Casual - Expert ← → Peer - Serious ← → Playful - Reserved ← → Opinionated - Abstract ← → Concrete

  1. Sentence Patterns:

- Average length (short, medium, long) - Variation style (punchy fragments? flowing paragraphs?) - Signature structures (recurring patterns)

  1. Word Choice:

- Vocabulary level (simple, moderate, sophisticated) - Contractions (always, sometimes, never) - Industry jargon (embrace, explain, avoid) - Profanity/informality (none, mild, frequent)

  1. What to NEVER do:

- Phrases to avoid - Tones that are off-brand - Common mistakes

Output Format:
## Voice & Tone

### Voice Spectrum
- Formal/Casual: [X]/5 - [Brief explanation]
- Expert/Peer: [X]/5 - [Brief explanation]
- Serious/Playful: [X]/5 - [Brief explanation]
- Reserved/Opinionated: [X]/5 - [Brief explanation]
- Abstract/Concrete: [X]/5 - [Brief explanation]

### Sentence Patterns
- **Average length:** [Short/Medium/Long]
- **Variation:** [Description of rhythm]
- **Signature structures:**
  - "[Example pattern 1]"
  - "[Example pattern 2]"

### Word Choice
- **Vocabulary:** [Simple/Moderate/Sophisticated]
- **Contractions:** [Always/Sometimes/Never]
- **Jargon:** [Policy]
- **Informality:** [Level]

### Anti-Patterns (NEVER do)
- ❌ [Thing to avoid 1]
- ❌ [Thing to avoid 2]
- ❌ [Thing to avoid 3]

### Signature Phrases
- "[Phrase this brand uses often]"
- "[Another recurring expression]"

Section 4: Values & Mission

Goal: Define the brand's purpose and principles

Questions to Answer:
  1. Mission Statement:

- What problem does this brand exist to solve? - In one sentence, what's the mission?

  1. Core Values (3-5):

- Not aspirational, but actually practiced - How does each value show up in content?

  1. What This Brand Stands For:

- Positions it takes publicly - Causes or movements it supports - Industry practices it challenges

  1. What This Brand Opposes:

- What does it stand against? - What conventional wisdom does it reject? - What practices does it criticize?

Output Format:
## Values & Mission

### Mission
[One clear sentence on why this brand exists]

### Core Values
1. **[Value 1]:** [How it shows up in content]
2. **[Value 2]:** [How it shows up in content]
3. **[Value 3]:** [How it shows up in content]

### What We Stand For
- [Position 1]
- [Position 2]
- [Position 3]

### What We Oppose
- [Opposition 1]
- [Opposition 2]

Section 5: Messaging Framework

Goal: Create reusable messaging elements

Questions to Answer:
  1. Tagline/Positioning Statement:

- How do you describe the brand in 10 words or less?

  1. Elevator Pitch (30 seconds):

- Full explanation of what, for whom, and why

  1. Key Messages (3-5):

- Core themes that appear across all content - What should every piece of content reinforce?

  1. Proof Points:

- Credentials, stats, testimonials - Stories that demonstrate credibility - Results that build trust

  1. Content Themes:

- Categories of content this brand creates - Topics that are always relevant - Topics that are off-limits

Output Format:
## Messaging Framework

### Positioning
**Tagline:** [10 words or less]
**Elevator Pitch:** [30-second version]

### Key Messages
1. [Message 1]
2. [Message 2]
3. [Message 3]

### Proof Points
- **Credentials:** [Expertise, qualifications]
- **Stats:** [Numbers that demonstrate value]
- **Testimonials:** [Quotes from satisfied customers/readers]
- **Stories:** [Signature stories to reference]

### Content Themes
**Always Relevant:**
- [Theme 1]
- [Theme 2]
- [Theme 3]

**Off-Limits:**
- [Topic 1 - why]
- [Topic 2 - why]

Wizard Workflow

Step 1: Discovery Interview

Walk through each section's questions. Document answers as you go.

Step 2: Synthesize Answers

Convert raw answers into the output format for each section.

Step 3: Review & Refine

Present draft to user. Iterate until it feels right.

Step 4: Save Document

Create file: brand-identity.md in the vault root or designated location.

Step 5: Reference in Other Skills

Point content skills to this file:

  • In CLAUDE.md: "For brand voice, see brand-identity.md"
  • In individual skills: "Load voice/messaging from brand-identity.md"

Output File Template

# Brand Identity: [Brand Name]

*Last updated: [Date]*

---

## Brand Persona
[Section 1 content]

---

## Target Audience
[Section 2 content]

---

## Voice & Tone
[Section 3 content]

---

## Values & Mission
[Section 4 content]

---

## Messaging Framework
[Section 5 content]

---

## Quick Reference

**For Newsletter Writers:**
- Voice: [Summary]
- Audience: [Summary]
- Key themes: [Summary]

**For Podcast Production:**
- Interview style: [Summary]
- Guest selection: [Summary]
- Episode framing: [Summary]

**For Social Media:**
- Platform personalities: [Any variations]
- Hashtag strategy: [Overview]
- Content pillars: [Summary]

Success Criteria

A complete brand identity document:

✅ Persona feels like a real person - You can imagine them speaking ✅ Audience is specific - Not "everyone interested in X" ✅ Voice is distinctive - Couldn't be swapped with a competitor ✅ Values are actionable - Show up in actual content decisions ✅ Messaging is reusable - Other skills can reference it


Related Skills

  • voice-analyzer - Create custom voice style from writing samples
  • voice-[style] - Individual voice implementations
  • anti-ai-writing - Ensure content matches brand voice authentically

*A well-defined brand identity is the foundation for all consistent content. Define once, reference everywhere.*

平台分布

Codex

37.48%
按下载量换算32

Claude

26.4%
按下载量换算22

Cursor

16.98%
按下载量换算14

Gemini CLI

9.48%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills