AGENT SKILL

brand-voice

Define and store your brand voice profile for consistent content generation. Captures writing style, vocabulary patterns, tone preferences, and content rules. Use when generating content that matches your voice, onboarding a new content workflow, or ensuring consistency across platforms.

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
brand-voice
description
Define and store your brand voice profile for consistent content generation. Captures writing style, vocabulary patterns, tone preferences, and content rules. Use when generating content that matches your voice, onboarding a new content workflow, or ensuring consistency across platforms.

03 SKILL.md 正文

Brand Voice

Store your writing style so AI-generated content sounds like you, not a robot.

Quick Start

Create Your Voice Profile

Talk to your agent naturally:

"Let's set up my brand voice. I write casually, use short sentences, and like to make technical topics accessible. I never use corporate jargon. My audience is indie developers and solopreneurs."

The agent should then:

  1. Ask follow-up questions to understand your style
  2. Create a profile at brand-voice/profile.json
  3. Use it when generating content for you

Profile Structure

{
  "name": "Your Brand",
  "created": "2026-02-22",
  "updated": "2026-02-22",
  
  "voice": {
    "tone": "casual, direct, slightly irreverent",
    "personality": ["helpful", "opinionated", "no-BS"],
    "formality": "informal",
    "humor": "dry wit, occasional sarcasm"
  },
  
  "writing": {
    "sentenceLength": "short to medium, punchy",
    "paragraphLength": "2-3 sentences max",
    "structure": "lead with the point, then explain",
    "formatting": ["use headers", "bullet points over paragraphs", "bold key phrases"]
  },
  
  "vocabulary": {
    "use": ["ship", "build", "hack", "vibe", "solid"],
    "avoid": ["utilize", "leverage", "synergy", "best practices", "learnings"],
    "jargon": "minimal, explain when used",
    "contractions": true
  },
  
  "audience": {
    "who": "indie developers, solopreneurs, tech-curious founders",
    "assumes": "basic technical literacy",
    "explains": "complex concepts simply"
  },
  
  "content": {
    "topics": ["AI", "automation", "building in public", "productivity"],
    "avoid": ["politics", "controversial takes without data"],
    "cta_style": "soft, value-first",
    "hashtags": "minimal, 1-3 max"
  },
  
  "platforms": {
    "twitter": {
      "maxLength": 280,
      "style": "punchy, hook-first",
      "threads": "use for longer ideas, 3-7 tweets"
    },
    "linkedin": {
      "style": "slightly more professional but still human",
      "formatting": "line breaks for readability"
    },
    "blog": {
      "style": "conversational, like talking to a friend",
      "length": "800-1500 words typical"
    }
  },
  
  "examples": {
    "good": [
      "Shipped a thing. It's rough but it works. Feedback welcome.",
      "Hot take: most 'AI strategies' are just ChatGPT with extra steps.",
      "Here's what I learned building X for 6 months..."
    ],
    "bad": [
      "We are pleased to announce the launch of our innovative solution.",
      "Leveraging cutting-edge AI to drive synergies across the value chain.",
      "🚀🔥💯 HUGE NEWS!!! 🔥🚀💯"
    ]
  }
}

Usage

When Generating Content

Reference the voice profile before writing:

Before generating:
1. Read brand-voice/profile.json
2. Match tone, vocabulary, and style
3. Check examples for calibration
4. Adapt for specific platform if specified

Voice Check Prompt

After generating content, self-check:

  • Does this sound like the examples in "good"?
  • Does this avoid the patterns in "bad"?
  • Does this match the tone and vocabulary rules?
  • Would this fit on the specified platform?

Multi-Brand Support

For agencies or multiple projects:

brand-voice/
  profiles/
    personal.json
    company.json
    client-a.json

Reference by name: "Use the client-a voice profile for this post."

Building Your Profile

The Interview

Ask the user these questions (conversationally, not as a checklist):

  1. Tone: How would you describe your writing style in 3 words?
  2. Audience: Who are you writing for? What do they already know?
  3. Formality: LinkedIn-formal or Twitter-casual? Somewhere in between?
  4. Humor: Serious? Playful? Sarcastic? None?
  5. Words you love: Any phrases or words that feel very "you"?
  6. Words you hate: Corporate speak? Emoji overload? What to avoid?
  7. Examples: Share 2-3 things you've written that feel authentic.
  8. Anti-examples: Share something that feels "off" or too corporate.

Analyze Existing Content

If they have existing content, analyze it:

Read their last 10 posts/articles. Look for:
- Sentence length patterns
- Opening hook style
- Common phrases
- Vocabulary choices
- Formatting preferences
- CTA patterns

Iterate

The profile isn't static. Update it when:

  • User says "that doesn't sound like me"
  • New topics or platforms are added
  • Writing style evolves

Integration with Other Skills

With RSS Reader

1. Check RSS for trending topics
2. Pick an angle
3. Generate post using brand voice
4. Review and schedule

With Content Schedulers (Metricool, etc.)

1. Load voice profile
2. Generate week of content
3. Apply platform-specific formatting
4. Queue for posting

With Image Generation

Voice profile can include visual style:
{
  "visual": {
    "aesthetic": "clean, minimal, lots of whitespace",
    "colors": ["#1a1a1a", "#f5f5f5", "#0066cc"],
    "avoid": ["stock photo vibes", "corporate clip art"]
  }
}

Tips

  1. Start simple — you can always add detail later
  2. Use real examples — they calibrate better than descriptions
  3. Platform-specific rules — what works on Twitter fails on LinkedIn
  4. Update regularly — voices evolve
  5. Test with the user — generate, show, iterate

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0