Brand voice
Apply and enforce brand voice across all content creation. Manages voice attributes, tone adaptation by channel, style rules, and terminology. Use when writing content, reviewing drafts, or defining brand voice for a new project. Loads voice config from CREATOR.md or creator-memory/voice.md.From its SKILL.md
npx -y skills add frankxai/creator-skills --skill brand-voiceAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.0 KB, 878 tokens by cl100k_base, as published. Nobody here has run it
Brand Voice
Write in a consistent voice — not just tone, but the specific fingerprint of how a creator communicates.
Voice vs. Tone
Voice is fixed. It's the personality — what the brand always sounds like. Tone is variable. It's the emotional inflection applied to the voice based on context.
A creator's voice stays consistent across channels. Tone adapts: more formal on LinkedIn, punchier on X, warmer in email.
Voice Loading
Before writing, check for voice config in this order:
CREATOR.md— voice section (quick ref, covers 90% of cases)creator-memory/voice.md— full documentation with examples- If neither exists: ask user to describe their voice, or offer to initialize
The 5 Voice Components
A complete voice profile covers:
1. Voice Attributes (3-5 maximum)
Each attribute defined as:
- We are: what it means in practice
- We are not: the misinterpretation to avoid
- Sounds like: example sentence
- Never sounds like: anti-example
Example for "Cool Authority":
- We are: confident, precise, lets the work speak
- We are not: arrogant, dismissive, or name-dropping
- Sounds like: "[Specific result]. Here's what that teaches you about [topic]."
- Never sounds like: "As a top AI architect, I know better than most that..."
2. Audience Definition
- Who the primary audience is
- What they already know (don't over-explain)
- What they want from this creator
- How they expect to be addressed (peer, student, collaborator)
3. Content Pillars
3-5 core themes the creator consistently covers. Every piece of content should belong to one. Defined with topic focus, audience, and core argument.
4. Tone Adaptation Rules
How the voice shifts by context while staying recognizably consistent.
| Channel | Tone shift | Example |
|---|---|---|
| Long-form blog | Educational, complete, evidence-based | Full arguments, examples, conclusions |
| Professional, thought-provoking, personal | First-person insight, business framing | |
| X/Twitter | Direct, punchy, opinionated | Short sentences, bold claims |
| Personal, warm, action-oriented | "You" framing, clear next step | |
| Video | Conversational, energetic | Shorter sentences, visual language |
5. Terminology Rules
Preferred and avoided terms. Examples:
- "creators" not "influencers"
- "ships" not "launches" (for product releases)
- "AI music" not "generated music"
- Never: spiritual language, guru tone, lazy CTAs ("drop a comment below")
Applying Voice to Content
When writing, run this checklist:
- Read the voice attributes from CREATOR.md
- Draft the opener — rewrite until it sounds like the creator
- Check for anti-patterns (things this creator never says)
- Verify tone matches the channel rules
- Check terminology — any flagged words used?
Red flags requiring revision:
- Opener starts with "I" (usually weak, unless intentional personal story)
- More than one "!" in a piece
- "Amazing", "awesome", "incredible" (generic, not precise)
- "In today's fast-paced world..." (stock opener, never use)
- Passive voice where active works better
- Hedging: "I think", "maybe", "possibly" (unless intentional)
Loading Voice Config
Check for voice documentation in this priority order:
CREATOR.mdin the current project (hot cache — covers 90% of requests)creator-memory/voice.mdin the current project (full documentation)- Project
CLAUDE.md— look for a "Brand Positioning" or "Voice" section - If none found: ask the user to describe their voice, or run
/creator-sprint
See references/voice-frameworks.md for the full voice documentation template and attribute definition system.
What ships with it: 1 file
6.1 KB alongside SKILL.md
references/
- voice-frameworks.md6.1 KB
Gives 0 of the 12 instructions most marketing audience skills give in 878 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- check for voice config before writing
- read voice attributes from config
- draft the opener until it matches the creator
- check for specified anti-patterns
- check content for prohibited terminology
- ask the user if no voice config exists
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.