Token导航 LogoToken导航

Agent Skill · 研究检索

brand-voice-generator(品牌语音发生器)

用于辅助音频、音乐、语音转写、语音合成或声音素材处理。它适合让 Agent 生成配乐说明、整理音频流程、调用语音工具或处理播客和视频配音素材。使用时需要确认输入音频来源、输出格式、时长和模型限制;涉及人声克隆、版权音乐或公开发布时,应先核对授权和合规边界。

brand-voice-generator 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,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 44,371。

总安装 917周安装 39GitHub Stars 733下载 321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-voice-generator(品牌语音发生器)
来源仓库:https://github.com/coleam00/second-brain-skills
仓库路径:skills/brand-voice-generator
安装命令:
npx skills add https://github.com/coleam00/second-brain-skills --skill brand-voice-generator
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/coleam00/second-brain-skills --skill brand-voice-generator

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-voice-generator 用于生成品牌配置文件,包括色彩、字体、输出设置及写作风格指南,支持 PPTX 生成器和其他品牌感知技能。适用于需要统一多平台内容输出风格(如 LinkedIn、X、PPT)的品牌建设场景。

通过交互式流程定义品牌身份和写作语气,生成 brand.json、config.json 和 tone-of-voice.md 等文件。涉及人声克隆或版权音乐时,应先核对授权边界,确保合规使用。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-voice-generator

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/coleam00/second-brain-skills --skill brand-voi…;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

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

brand-voice-generator 怎么安装?

在终端执行 npx skills add https://github.com/coleam00/second-brain-skills --skill brand-voice-generat…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brand-voice-generator 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-voice-generator 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/coleam00/second-brain-skills --skill brand-voice-generator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

brand-voice-generator 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-voice-generator 用的人多吗?

公开数据是累计安装 917 次,近一周安装 39 次,下载 321 次,GitHub 733 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-voice-generator 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 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。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 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-voice-generator

品牌语音发生器 · 本页

917733执行命令未明确通过

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 & Voice Generator

Generate complete brand configuration files for use with the PPTX Generator and other brand-aware skills. This skill guides users through an interactive process to define their brand identity and writing voice.

What This Creates

FilePurposeUsed By
brand.jsonColors, fonts, assetsPPTX Generator, Excalidraw
config.jsonOutput settingsPPTX Generator
brand-system.mdDesign philosophy & guidelinesAll content skills
tone-of-voice.mdWriting voice & personalityLinkedIn, X, PPTX content

Output Location

Files are created in:

.claude/skills/pptx-generator/brands/{brand-name}/

Process Overview

  1. Gather Brand Basics - Name, description, primary use case
  2. Define Colors - 10 color values for the complete system
  3. Define Typography - Heading, body, and code fonts
  4. Define Assets - Logo and icon paths
  5. Discover Voice - Personality, vocabulary, sentence patterns
  6. Create Design Philosophy - Core principles and signature elements
  7. Generate Files - Create all four files with gathered information
  8. Verify Setup - Confirm files are correctly placed

Step 1: Gather Brand Basics

Ask the user for:

FieldDescriptionExample
Brand nameFolder name (lowercase, no spaces, hyphens OK)my-brand, acme-corp
Display nameHuman-readable name"My Brand", "ACME Corporation"
DescriptionOne-line brand description"AI education content and community"
Primary useMain content typepresentations, social media, documentation

Suggested question:

"Let's set up your brand. What's your brand name? (This will be the folder name - use lowercase with hyphens, like 'my-brand')"

Step 2: Define Colors

Gather 10 color values. Colors should be hex codes WITHOUT the # prefix.

Required Colors

ColorPurposeGuidance
backgroundMain slide/page backgroundDark themes: near-black. Light themes: white/off-white
background_altAlternate background for varietySlightly different shade of background
textPrimary text colorHigh contrast against background
text_secondaryMuted/secondary textSlightly lower contrast than primary
accentPrimary accent (CTAs, highlights)Your signature brand color
accent_secondarySecondary accentComplement to primary accent
accent_tertiaryThird accent (optional variety)Another complement, or same as secondary
code_bgCode block backgroundDarker than main background
card_bgCard/surface backgroundBetween background and text
card_bg_altAlternate card backgroundSlight variation of card_bg

Color Discovery Questions

If user doesn't have a full color system, guide them:

  1. "What's your signature brand color? (This becomes your primary accent)"
  2. "Do you prefer a dark theme (dark background, light text) or light theme?"
  3. "Do you have secondary colors, or should I suggest complements?"

Color Suggestions by Theme

For dark themes, suggest:

background: 0a0a0a to 1a1a2e range
text: f5f5f5 to ffffff range
card_bg: 1a1a1a to 2d2d44 range

For light themes, suggest:

background: ffffff to f8f9fa range
text: 1a1a1a to 333333 range
card_bg: f0f0f0 to e8e8e8 range

Step 3: Define Typography

Gather 3 font names:

FontPurposeCommon Choices
headingHeadlines, titles, buttonsInter, Montserrat, Poppins, Roboto
bodyBody text, descriptionsInter, Open Sans, Lato, Source Sans Pro
codeCode blocks, terminalJetBrains Mono, Fira Code, Monaco, Consolas

Question:

"What fonts should we use? I need a heading font, body font, and code/monospace font. Common choices are Inter for both heading and body, and JetBrains Mono for code."

Default if unsure:

  • Heading: Inter
  • Body: Inter
  • Code: JetBrains Mono

Step 4: Define Assets

Gather asset paths (relative to brand folder):

AssetDescriptionCommon
logoPrimary logo fileassets/logo.png
logo_darkLogo variant for dark backgrounds (optional)null or assets/logo-dark.png
iconSquare icon (optional)null or assets/icon.png

Question:

"Do you have a logo file? If so, you'll need to copy it to the brand folder. What's the filename? (e.g., 'logo.png')"

If they have a logo, set path to assets/logo.png (they'll copy it there). If no logo, set to null.


Step 5: Discover Voice

This is the most important step for content quality. Guide the user through voice discovery.

Voice Discovery Questions

Ask these questions to understand their voice:

  1. Personality in 3 words: "Describe your brand's personality in exactly 3 words. Examples: 'Bold, Technical, Approachable' or 'Calm, Authoritative, Helpful'"
  2. Voice influences: "Who are 2-3 creators, brands, or people whose communication style you admire? This helps me understand the vibe."
  3. Vocabulary patterns: "What words or phrases do you use often? Any pet phrases, intensifiers you like ('super', 'incredibly'), or words you naturally reach for?"
  4. What to avoid: "What kind of tone or phrases do you want to AVOID? (e.g., corporate speak, hype language, overly casual)"
  5. Sentence style: "Do you prefer: Short punchy sentences, longer flowing explanations, or a mix? Do you use contractions ('don't', 'can't') casually?"
  6. Teaching style (if applicable): "When explaining something complex, how do you approach it? Show process/iterations? Use analogies? Lead with practical then theory?"

Voice Templates Reference

Read references/voice-templates.md for example voice configurations to show the user.


Step 6: Create Design Philosophy

Based on gathered information, help define:

Core Principles (3-4)

Ask:

"What are 3-4 design principles that guide your visual choices? For example: 'Clean over flashy', 'Technical but approachable', 'Dark mode by default'"

Signature Elements

Ask:

"Do you have any signature visual elements? Examples: Glass card effects, specific shadow styles, gradient patterns, geometric shapes, glow effects"

If unsure, suggest based on their colors and theme.


Step 7: Generate Files

Create all four files using the gathered information.

brand.json

{
  "name": "{display_name}",
  "description": "{description}",

  "colors": {
    "background": "{background}",
    "background_alt": "{background_alt}",
    "text": "{text}",
    "text_secondary": "{text_secondary}",
    "accent": "{accent}",
    "accent_secondary": "{accent_secondary}",
    "accent_tertiary": "{accent_tertiary}",
    "code_bg": "{code_bg}",
    "card_bg": "{card_bg}",
    "card_bg_alt": "{card_bg_alt}"
  },

  "fonts": {
    "heading": "{heading_font}",
    "body": "{body_font}",
    "code": "{code_font}"
  },

  "assets": {
    "logo": "{logo_path}",
    "logo_dark": {logo_dark_path},
    "icon": {icon_path}
  }
}

config.json

{
  "output": {
    "directory": "output/{brand_name}",
    "naming": "{name}-{date}",
    "keep_parts": false
  },
  "generation": {
    "slides_per_batch": 5,
    "auto_combine": true,
    "open_after_generate": false
  },
  "defaults": {
    "slide_width_inches": 13.333,
    "slide_height_inches": 7.5
  }
}

tone-of-voice.md

Use the template in references/tone-template.md and fill with gathered voice information.

brand-system.md

Use the template in references/brand-template.md and fill with gathered design information.


Step 8: Verify Setup

After generating files:

  1. List created files: Glob:.claude/skills/pptx-generator/brands/{brand-name}/*
  2. Remind about assets: "Don't forget to copy your logo file to .claude/skills/pptx-generator/brands/{brand-name}/assets/"
  3. Suggest test: "Try generating a simple presentation with: 'Create a 3-slide presentation for {brand-name} about [topic]'"

Quick Mode

If user just wants to get started quickly:

  1. Ask only for: brand name, signature color, and light/dark preference
  2. Generate sensible defaults for everything else
  3. Create minimal but functional files
  4. Tell them they can refine later

Quick mode trigger phrases:

  • "quick setup"
  • "just the basics"
  • "minimal brand"
  • "get started fast"

Updating Existing Brand

If a brand already exists:

  1. Read existing files first
  2. Ask what to update:

- Colors only? - Voice only? - Everything?

  1. Preserve unchanged sections
  2. Show diff of changes before writing

Checklist

  • Gather brand name and description
  • Collect all 10 color values (or suggest defaults)
  • Collect 3 font names (or use defaults)
  • Determine asset paths
  • Discover voice through questions
  • Define design principles
  • Generate brand.json
  • Generate config.json
  • Generate tone-of-voice.md
  • Generate brand-system.md
  • Create assets folder
  • Verify all files created
  • Remind user about logo copying
  • Suggest test generation

平台分布

Codex

33.63%
按下载量换算108

Claude

29.29%
按下载量换算94

Cursor

17.77%
按下载量换算57

Gemini CLI

10.02%
按下载量换算32

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/coleam00/second-brain-skills --skill brand-voice-generator 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。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