Brand Voice Profile

Define and store your brand voice profile for consistent content generation. Captures writing style, vocabulary patterns, tone preferences, and content rules...

Security Scan

This instruction-only skill is internally consistent with its stated purpose: it guides the agent to interview the user, create and reuse a local brand voice profile (brand-voice/profile.json), and optionally integrate with content sources — it requests no installs or credentials, but it will read and write user content so you should control what the agent can access.

Purpose & Capability

The name/description (brand voice profile) matches the instructions: creating, reading, using JSON profile files and guiding interviews. There are no unrelated environment variables, binaries, or installs requested.

Instruction Scope

Instructions tell the agent to read/write profile files (brand-voice/profile.json) and to 'analyze existing content' by reading the user's last ~10 posts/articles. That behavior is coherent with the purpose but means the agent may access user content (local files or remote posts). The SKILL.md does not specify how to fetch remote content or what permissions to use, so you should confirm which connectors or access methods the agent will use before allowing it to analyze external data.

Install Mechanism

No install spec, no code files, and no downloads — lowest-risk form (instruction-only).

Credentials

The skill declares no environment variables, credentials, or config paths. Nothing disproportionate is requested for the described functionality.

Persistence & Privilege

The skill expects to write persistent profile files (brand-voice/profile.json and optional profiles/). This is reasonable, but persistent data will exist on whatever agent storage is used — if that storage is synced to cloud or backed up, the profiles could be exposed. The skill does not request always:true or modify other skills.

Assessment

This skill appears to do what it says: interview you and keep a JSON brand profile to reuse when generating content. Before installing or invoking it, consider: 1) Where profile files will be stored (local vs cloud-backed agent storage) and whether that's acceptable for your data; 2) What the agent will use to "read their last 10 posts" — prefer explicit RSS or connected-account integrations rather than open web scraping; 3) Do not provide credentials or private keys directly; instead connect through vetted integrations and grant the minimum required permissions for scheduling/posting; 4) Review generated profile.json and any analyzed content for sensitive PII before sharing it with other services; 5) If you plan to integrate with scheduling or social posting skills, limit those skills' scopes and verify that posting actions require your explicit confirmation. If you want extra assurance, test with non-sensitive sample content first.

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