Brand voice
Documenting, calibrating, and enforcing brand voice across all content touchpoints. Voice as a design system component.From its SKILL.md
npx -y skills add Dragoon0x/everything-design-taste --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
- 9 stars9 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
2.7 KB, 617 tokens by cl100k_base, as published. Nobody here has run it
Brand Voice
Voice vs Tone
Voice is who you are. It doesn't change. A brand that's direct and honest is always direct and honest.
Tone shifts by context. The same direct brand sounds different in a celebration (enthusiastic, warm) vs an error message (clear, reassuring) vs a legal disclaimer (precise, transparent).
Defining Voice
The Attribute Framework
Pick 3-4 attributes. For each, define what it is, what it isn't, and give examples.
## Voice Attribute: [Name]
**What it is:** [Clear definition]
**What it isn't:** [The extreme to avoid]
**Sounds like:** "[Example sentence]"
**Doesn't sound like:** "[Anti-example sentence]"
Example:
## Voice Attribute: Confident
**What it is:** We know our stuff and we say it simply.
**What it isn't:** Arrogant, dismissive, or condescending.
**Sounds like:** "Your data is safe. Here's exactly how we protect it."
**Doesn't sound like:** "We are the industry-leading solution for data protection."
Tone Calibration by Context
| Context | More... | Less... | Example |
|---|---|---|---|
| Onboarding | Warm, encouraging | Technical, formal | "Nice, you're set up. Let's build something." |
| Error states | Clear, helpful | Apologetic, vague | "That file is too large. Max size is 10MB." |
| Marketing | Bold, specific | Hype-y, generic | "Cut review time by 40%." |
| Documentation | Clear, scannable | Dense, academic | "To add a user, click Settings then Team." |
| Pricing | Transparent, direct | Cagey, qualified | "Free up to 5 users. $12/user/month after." |
| Changelog | Specific, honest | Vague, corporate | "Fixed: images now load on slow connections." |
Word Lists
Build Three Lists
Preferred words — Words that represent our voice Acceptable alternatives — Words that work but aren't ideal Banned words — Words we never use
Example:
| Preferred | Acceptable | Banned |
|-----------|-----------|--------|
| Use | Employ | Utilize, leverage |
| Help | Assist | Empower, enable |
| Simple | Easy | Seamless, frictionless |
| Fast | Quick | Blazing, lightning |
| New | Updated | Revolutionary, groundbreaking |
| Fix | Resolve | Remediate |
Testing Voice
Read copy aloud. If it sounds like a press release, rewrite it. If it sounds like a person explaining something to a friend, it's probably close.
The ultimate test: if you covered the logo, could someone identify the brand from the writing alone? If not, the voice isn't distinctive enough.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in 617 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
- define what each attribute is and is not
- provide example and anti-example sentences for each attribute
- calibrate tone based on specific contexts
- build preferred, acceptable, and banned word lists
- read the copy aloud
- rewrite copy if it sounds like a press release
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.