Token导航 LogoToken导航

Agent Skill · 研究检索

brand-setup(品牌设置)

brand-setup 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-setup 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 50,882。

总安装 605周安装 26GitHub Stars 67下载 212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-setup(品牌设置)
来源仓库:https://github.com/indranilbanerjee/digital-marketing-pro
仓库路径:skills/brand-setup
安装命令:
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill brand-setup
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/indranilbanerjee/digital-marketing-pro --skill brand-setup

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-setup 交互式构建品牌档案,支持快速启动与深度定制两种模式。适用于新品牌创建、客户项目切换或品牌声音/受众/目标更新场景。通过引导式提问收集品牌名称、业务范围与核心价值,生成结构化档案。建议首次使用选择快速模式,后续可通过 /brand-init 命令完善细节。

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-setup

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/indranilbanerjee/digital-marketing-pro --skill…;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-setup 怎么安装?

在终端执行 npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill brand-set…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brand-setup 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-setup 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-setup 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-setup 用的人多吗?

公开数据是累计安装 605 次,近一周安装 26 次,下载 212 次,GitHub 67 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-setup 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-setup

品牌设置 · 本页

60567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 Setup — Interactive Brand Profiling

When to Use This Skill

  • User says "set up a new brand" or "create a brand profile"
  • User mentions a new client or project for marketing
  • User wants to switch between brands (agency use case)
  • User wants to update brand voice, audiences, or goals
  • First time using any marketing skill without an active brand

Setup Modes

Quick Setup (5 questions — recommended for getting started fast)

If the user wants to get started quickly, or says "quick setup", ask only these 5 essential questions:

  1. Brand name — "What's your brand or business name?"
  2. What you do — "In one sentence, what does [brand] do?" (extract industry, business model, USP)
  3. Target audience — "Who is your primary customer?" (extract B2B/B2C, demographics)
  4. Brand voice — "Pick 3 words that describe how your brand communicates" (map to formality/energy/humor/authority scales)
  5. Primary channel — "Where do you primarily market? (social media, email, SEO, paid ads, etc.)"

From these 5 answers, intelligently populate the full profile:

  • Infer industry, business model type, and compliance requirements
  • Map voice descriptors to the 1-10 scales (e.g., "professional" → formality: 8, "fun" → humor: 7)
  • Set sensible defaults for everything else
  • Tell the user: "Quick profile created! You can refine it anytime with /dm:brand-setup --full"

Full Setup (17 questions — comprehensive profiling)

Use the full setup when:

  • User explicitly asks for detailed/full/comprehensive setup
  • User says "/dm:brand-setup --full"
  • User wants to update specific sections of an existing profile

Process (Full Setup)

Step 1: Brand Identity

Ask the user one question at a time (don't overwhelm):

  1. Brand name: "What's the brand/company name?"
  2. Elevator pitch: "In one sentence, what does [brand] do?"
  3. USP: "What makes [brand] different from competitors?"
  4. Mission/Values: "What's the brand's mission? What values drive it?"

Step 2: Business Model

  1. Business type: Present options:

- B2B SaaS / Software - B2C eCommerce / DTC - B2B Services / Consulting - Local Business - Agency (managing multiple clients) - Creator / Personal Brand - Enterprise - Non-Profit - Marketplace

  1. Revenue model: subscription, transactional, freemium, marketplace commission, donation, retainer, advertising
  2. Price range and sales cycle: "What's your typical deal size and how long does it take to close?"

Step 3: Industry & Compliance

  1. Industry: "What industry are you in?" (match to industry-profiles.md)
  2. Regulated?: "Are you in a regulated industry? (healthcare, finance, legal, alcohol, cannabis, etc.)"
  3. Target markets: "What countries/regions do you sell to?" (triggers compliance rules)

Step 4: Brand Voice

  1. Voice dimensions — Ask user to rate 1-10 or describe:

- Formality (1=very casual like a friend, 10=very formal like a law firm) - Energy (1=calm and measured, 10=enthusiastic and bold) - Humor (1=never use humor, 10=humor is core to the brand) - Authority (1=peer-level, friendly guide, 10=expert thought leader)

  1. Personality traits: "Pick 3-5 words that describe the brand's personality" (e.g., witty, empathetic, direct, bold, thoughtful, playful, authoritative, warm)
  2. This-Not-That: "Give me examples of how you'd say something vs. how you wouldn't" (e.g., "We say 'Let's figure this out together' not 'Contact our support team'")
  3. Sample content: "Share 2-3 URLs or text snippets of content you think nails your brand voice"

Step 5: Channels & Goals

  1. Active channels: "Which marketing channels are you currently using?" (website, Instagram, LinkedIn, Twitter, TikTok, YouTube, Facebook, Pinterest, Email, Google Ads, Meta Ads, etc.)
  2. Goals: "What's your #1 marketing goal right now?" + target KPIs + budget range + team size

Step 6: Competitors

  1. Competitors: "Name 3-5 competitors (direct or aspirational)"

- For each: name, URL, relationship (direct/indirect/aspirational), known strengths/weaknesses

Step 7: Save & Confirm

After collecting all information:

  1. Run: python3 scripts/setup.py --create-brand "[brand name]"
  2. Update the created profile.json with all collected data
  3. Confirm to user: "Brand profile created for [brand_name]. All marketing modules will now use this context. You can update it anytime by saying 'update my brand profile.'"

Switching Brands

When user says "switch to [brand name]":

  1. Run: python3 scripts/setup.py --list-brands
  2. Find matching brand
  3. Update ~/.claude-marketing/brands/_active-brand.json
  4. Confirm: "Switched to [brand_name]."

Updating a Brand

When user wants to update specific fields:

  1. Load current profile from ~/.claude-marketing/brands/{slug}/profile.json
  2. Ask about the specific field(s) to update
  3. Write updated profile back
  4. Confirm changes

Important Notes

  • NEVER skip the brand voice section — it's what makes all content outputs on-brand
  • For agencies: each client should be a separate brand profile
  • Store voice samples as markdown files in the brand's voice-samples/ directory
  • Auto-detect industry compliance rules based on the industry and market selections

平台分布

Codex

38.1%
按下载量换算81

Claude

29.23%
按下载量换算62

Cursor

20.65%
按下载量换算44

Gemini CLI

9.16%
按下载量换算19

安全审计

Gen Agent Trust Hub

可疑

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