rampstackco/claude-skills / skills/brand-voice
brand-voice
VerifiedDevelop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.1 KB |
| SKILL.md | skill md | 8.7 KB |
| references/voice-document-template.md | markdown | 5.5 KB |
| references/voice-frameworks.md | markdown | 7.5 KB |
references/voice-frameworks.md
View on GitHub# Voice Frameworks
Three established frameworks for thinking about brand voice. Each emphasizes a different layer. Mix and match. None is "right." Each is a tool.
---
## Framework 1: The "We are X, not Y" approach
The most pragmatic framework. Start here if you have not done voice work before.
### How it works
Pick 3 to 5 voice attributes. For each, name what the attribute is NOT. The pairing is the framework.
```
We are confident, not arrogant.
We are direct, not blunt.
We are warm, not saccharine.
We are smart, not academic.
```
### Why the "not Y" matters
Single-word attributes are aspirational. They float. Without a counterweight, writers (and AI assistants) overshoot.
- "Confident" alone = swagger, bravado, dismissiveness
- "Direct" alone = curtness, coldness, rudeness
- "Warm" alone = mushy, performative, over-friendly
- "Smart" alone = jargon-heavy, exclusionary
Each "not Y" tells the writer where the line is. It is the guardrail.
### Picking attributes
Avoid generic words every brand claims. "Friendly," "professional," "approachable," "trustworthy," "innovative" are filler. They do not distinguish.
Better attributes are specific enough to make some other brand a bad fit. If you can imagine your competitor saying the same word, the word is too generic.
A good list:
- Distinctive (no other brand in your category would put it the same way)
- Honest (you actually sound this way, or are committed to)
- Useful (writers can apply it to a real piece of copy)
- Limited (3 to 5 attributes; 8+ becomes unworkable)
### Stress test
Take a recent piece of copy. Score it 1 to 5 against each attribute. If it scores below 3 on any, the copy is off-voice. If it scores 5 across the board, the attributes might be too generous.
Apply the test to a competitor's copy. If their copy scores high on your attributes, the attributes are not distinctive enough.
---
## Framework 2: The Nielsen Norman 4 dimensions
Nielsen Norman Group introduced a model that treats voice as four sliders rather than a list of adjectives.
### The 4 sliders
**1. Funny vs serious**
Where on the spectrum from playful to earnest does the brand sit?
- Far funny: jokes are signature, even in support content
- Mid: occasional wit, mostly straightforward
- Far serious: humor is rare and only when context invites it
**2. Formal vs casual**
How structured and decorous is the writing?
- Far formal: full sentences, correct grammar, no contractions, professional register
- Mid: standard professional, occasional contractions
- Far casual: contractions, fragments, conversational rhythms, slang where appropriate
**3. Respectful vs irreverent**
Does the brand treat its audience and category with deference, or does it poke fun?
- Far respectful: customers are addressed with care, category is treated with seriousness
- Mid: respectful default, willing to be playful at edges
- Far irreverent: category cliches get punctured, the brand is willing to mock conventions (its own and competitors')
**4. Matter-of-fact vs enthusiastic**
What is the energy level?
- Far matter-of-fact: calm, even, measured
- Mid: warm but not effusive
- Far enthusiastic: animated, expressive, energetic
### How to use
Plot the brand on each of the four. The position is the brand's voice signature.
Example:
- Funny vs serious: 30 (mostly serious, occasional dryness)
- Formal vs casual: 70 (mostly casual, contractions standard)
- Respectful vs irreverent: 40 (respectful default, willing to be playful)
- Matter-of-fact vs enthusiastic: 50 (warm but measured)
This produces a recognizable signature distinct from competitors plotted on the same axes.
### Why this framework
It forces choices. Adjective lists let you claim "warm AND professional AND witty AND smart." The dimensions force you to commit to a position, which is what voice actually is.
### When to use it
Best as a complement to the "We are X, not Y" approach. Use the dimensions to plot the brand. Use the attributes to give writers actionable language.
---
## Framework 3: Brand archetypes (the Jung-derived model)
A model from depth psychology, applied to brands by Margaret Mark and Carol Pearson. Twelve archetypes, each with a recognizable voice pattern.
### The 12 archetypes
| Archetype | Voice signature | Example brands (illustrative, not endorsements) |
|---|---|---|
| Innocent | Pure, optimistic, simple | Wholesome consumer brands, family-oriented |
| Sage | Wise, considered, knowledgeable | Educational publishers, research institutions |
| Explorer | Adventurous, free, restless | Outdoor brands, travel platforms |
| Outlaw | Rebellious, defiant, anti-establishment | Disruptors, challenger brands |
| Magician | Visionary, transformative, mystical | Tech that "changes everything" |
| Hero | Brave, decisive, achievement-oriented | Athletic brands, ambitious tools |
| Lover | Sensual, intimate, devoted | Premium consumer goods, luxury |
| Jester | Playful, irreverent, lighthearted | Entertainment, fast food, fun-first |
| Everyman | Down-to-earth, relatable, fair | Mass market, "for everyone" |
| Caregiver | Compassionate, generous, protective | Healthcare, family services |
| Ruler | Authoritative, sophisticated, in-control | Premium brands, enterprise |
| Creator | Imaginative, expressive, original | Creative tools, artistic brands |
### How to use
Pick a primary archetype. Optionally a secondary. The combination is the voice signature.
A brand might be primary Sage with secondary Caregiver. That voice is wise + protective. It would write differently than a Sage + Outlaw (wise + defiant).
### Strengths
- Forces a clear voice character rather than a list of adjectives
- The archetypes are recognizable, which helps writers visualize the voice
- Distinguishes brands that might otherwise sound similar
### Weaknesses
- Some archetypes are dated or culturally specific
- "Pick one" is harder than it sounds; brands often span 2 or 3
- Easy to pick aspirational archetypes the brand does not actually live
### When to use it
When the brand has a distinctive personality you want to crystallize. Less useful for utilitarian or category-defining brands.
---
## Combining frameworks
The three frameworks are not mutually exclusive. They emphasize different layers.
A useful combination:
1. **Archetype** for the high-level character
2. **NN/g dimensions** for the calibration
3. **"We are X, not Y" attributes** for the daily writing guardrails
Example for a fictional brand:
- **Archetype:** Sage (primary) + Everyman (secondary)
- **Dimensions:** 30 funny / 60 casual / 50 respectful / 40 enthusiastic
- **Attributes:**
- Knowledgeable, not academic
- Plain-spoken, not basic
- Honest, not harsh
- Patient, not condescending
Each layer adds resolution. The archetype gives character. The dimensions give calibration. The attributes give writers the daily tool.
---
## Choosing a framework
If you have done voice work before and know what you want, the "We are X, not Y" approach alone is enough.
If the brand voice is undefined and you need to start from zero, begin with archetypes (high-level character), move to dimensions (calibration), then derive attributes (daily guardrails).
If voice work has been done but is too vague, the dimensions framework is the best clarifier.
If voice has been documented but writers do not know how to apply it, the attributes framework is the missing piece.
The frameworks are tools. The output of voice work is consistent writing across the brand. If the writing is consistent, the framework worked. If it is not, no framework is the right one yet.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |