Skip to content

thatrebeccarae/claude-marketing / skills/brand-voice-guidelines

brand-voice-guidelines

Verified

Develop brand voice, tone matrices, messaging frameworks, and brand book documentation. Use when the user asks about brand voice, tone of voice, brand guidelines, messaging framework, or brand consistency.

Brand Voice & Guidelines

Develop, document, and maintain consistent brand voice across all channels.

Install

git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/brand-voice-guidelines ~/.claude/skills/

Voice vs Tone

Voice = who you are (consistent). Tone = how you adapt to context (variable).

  • Voice is your brand personality — it does not change
  • Tone shifts based on situation: celebration vs crisis, social vs support, blog vs legal

Voice Development Process

Step 1: Audit Existing Content

Analyze 10-20 pieces of existing content across channels:

  • What adjectives describe the writing?
  • What is consistent? What is inconsistent?
  • How does your audience describe you?

Step 2: Define Voice Attributes

Choose 3-5 attributes that define your brand voice. Each attribute sits on a spectrum:

AttributeWe AreWe Are NOT
ConfidentBold, direct, opinionatedArrogant, dismissive, preachy
ApproachableWarm, conversational, humanUnprofessional, sloppy, too casual
ExpertKnowledgeable, precise, credibleJargon-heavy, condescending, academic
PlayfulWitty, creative, surprisingSilly, forced, distracting

Step 3: Brand Personality Archetypes

ArchetypeVoiceBrands
The SageKnowledgeable, thoughtful, guidingGoogle, TED, McKinsey
The CreatorInnovative, expressive, visionaryApple, Adobe, Figma
The HeroBold, confident, empoweringNike, Patagonia, Slack
The JesterPlayful, irreverent, entertainingOld Spice, Mailchimp, Duolingo
The CaregiverWarm, supportive, trustworthyDove, TOMS, Headspace
The RebelProvocative, disruptive, directHarley-Davidson, Basecamp, Cards Against Humanity
The ExplorerAdventurous, curious, independentAirbnb, North Face, REI
The RulerAuthoritative, premium, exclusiveRolex, Mercedes, Bloomberg
The EverypersonRelatable, honest, groundedIKEA, Target, Slack

Step 4: Create Tone Matrix

Define how voice adapts across contexts:

ContextConfidence LevelFormalityHumorEmpathy
Marketing websiteHighLow-mediumLightMedium
Blog postHighLowMediumMedium
Social mediaMedium-highLowHighMedium
Customer supportMediumMediumNoneVery high
Error messagesLow (humble)LowLight if appropriateHigh
Legal/complianceMediumHighNoneLow
Crisis commsHighHighNoneVery high
Sales emailsHighMediumLightHigh

Step 5: Messaging Framework

## Brand Promise
[One sentence: what you promise your customers]

## Value Propositions (3-5)
1. [VP 1]: [Proof point]
2. [VP 2]: [Proof point]
3. [VP 3]: [Proof point]

## Tagline Options
- [Tagline 1]
- [Tagline 2]
- [Tagline 3]

## Elevator Pitch (30 seconds)
[2-3 sentences that explain what you do, who you serve, and why it matters]

## Boilerplate (for press/about)
[Standard paragraph used in press releases, about pages, speaker bios]

Writing Style Guide

Grammar & Mechanics

DecisionOur StandardWhy
Oxford commaYesClarity
ContractionsYes (we are → we're)Conversational
Exclamation marksMax 1 per pageNot shouty
Emoji[Platform-specific rules]Context-dependent
CapitalizationSentence case for headingsModern, approachable
NumbersSpell out 1-9, numerals 10+Standard convention
PronounsWe (company), you (customer)Direct and personal

Vocabulary

Instead OfUseWhy
UtilizeUseSimpler
LeverageUse, applyLess jargon
SynergyCollaboration, combinedReal words
Best-in-classLeading, top-performingLess cliche
Disruptive[describe what actually changed]Show, do not label
Solution[name the actual thing]Be specific

Voice Consistency Audit

Audit Checklist

  • Sample 3 pages per channel (website, email, social, support)
  • Score each on voice attributes (1-5 per attribute)
  • Identify outliers (pages that do not sound like the brand)
  • Check for forbidden vocabulary
  • Verify tone matches context (support should not sound like marketing)
  • Test with the "read it aloud" check — does it sound like one person?

Deliverable: Brand Voice Document

Document Structure

# [Brand] Voice Guide

## Who We Are (1 paragraph)
## Our Voice Attributes (3-5 with Do/Don't examples)
## Tone Matrix (context-specific adjustments)
## Messaging Framework (promise, VPs, tagline, elevator pitch)
## Writing Style Guide (grammar, vocabulary, formatting)
## Channel-Specific Guidelines (website, email, social, support)
## Examples (before/after rewrites for each voice attribute)

Integration with Other Skills

  • content-creator — Brand voice analyzer script validates consistency
  • seo-content-writer — Apply voice guidelines while optimizing for SEO
  • copywriting-frameworks — Use frameworks within your established voice
  • social-media-strategy — Platform-specific tone adaptations
  • email-composer — Maintain voice in professional communications
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall