Brand Voice Learner logo

Brand Voice Learner

Community
guia-matthieu
brand-voice-learner

Analyze existing brand content to extract voice patterns, create voice guidelines, and ensure consistent brand expression

Overview

Publisherguia-matthieu
Repositoryclawfu-skills
Skill namebrand-voice-learner
Stars
150
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by guia-matthieu on GitHub. Read the source before you install it.

Installation

Install the Brand Voice Learner AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/guia-matthieu/clawfu-skills.git /tmp/clawfu-skills
mkdir -p .claude/skills
cp -r /tmp/clawfu-skills/skills/branding/brand-voice-learner .claude/skills/brand-voice-learner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Voice Learner in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Brand Voice Learner on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Brand Voice Learner is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Brand Voice Learner

Analyze existing brand content to extract voice characteristics, create actionable voice guidelines, and ensure consistent brand expression across all communications.

When to Use This Skill

  • Creating brand voice guidelines
  • Onboarding new writers
  • Auditing voice consistency
  • Adapting voice for channels
  • Training AI writing tools

Methodology Foundation

Based on NN/g voice research and content strategy best practices, combining:

  • Linguistic pattern analysis
  • Voice dimension mapping
  • Guidelines development
  • Consistency measurement

What Claude Does vs What You Decide

Claude DoesYou Decide
Analyzes existing contentContent sources to analyze
Extracts voice patternsVoice evolution direction
Creates voice guidelinesApproval of guidelines
Identifies inconsistenciesException handling
Suggests voice examplesFinal voice choices

Instructions

Step 1: Gather Voice Samples

Content to Analyze:

SourcePurpose
Website copyCore brand voice
Blog postsExtended voice
Social mediaCasual variation
Email campaignsDirect communication
Product UIFunctional voice
Customer supportEmpathetic voice

Sample Requirements:

  • Minimum 10-15 pieces
  • Variety of contexts
  • Include best examples
  • Cover different tones

Step 2: Analyze Voice Dimensions

Voice Dimension Framework:

DimensionSpectrum
FormalityCasual ←→ Formal
PersonalitySerious ←→ Playful
DirectnessIndirect ←→ Direct
EnthusiasmReserved ←→ Enthusiastic
TechnicalSimple ←→ Technical
WarmthDistant ←→ Warm

Step 3: Extract Patterns

Linguistic Elements:

ElementWhat to Identify
Sentence lengthShort, medium, long
Word choiceCommon, specialized, branded
ContractionsUsed, avoided, mixed
Active/passivePreference
PronounsWe/you/they patterns
PunctuationExclamations, ellipses, etc.

Step 4: Document Guidelines

Guidelines Structure:

  1. Voice principles (3-5)
  2. Dimension scores
  3. Do/Don't examples
  4. Channel variations
  5. Word lists

Step 5: Create Consistency Tools

Tools to Create:

  • Voice checklist
  • Example library
  • Word/phrase dictionary
  • Channel guidelines

Examples

Example 1: Complete Voice Analysis

Input:

Analyze brand voice from these samples:

Website: "We build tools that actually work. No fluff, no complexity—
just software that helps you get stuff done."

Blog: "Here's the thing about productivity apps: most of them make
your life harder, not easier. We think that's backwards."

Email: "Hey there! Your trial is almost over. Before you go, we wanted
to make sure you saw everything [Product] can do."

Social: "Mondays are hard. Your software shouldn't be. ☕"

Output:

## Brand Voice Analysis

### Voice Summary

**Overall Character:** Confident, casual, anti-corporate

Your brand sounds like a smart friend who's direct and relatable—
someone who gets frustrated by the same things your customers do
and isn't afraid to call out industry BS.

---

### Voice Dimensions

Formality [===|======] Casual (3/10) Personality [======|===] Playful (7/10) Directness [========|=] Very Direct (9/10) Enthusiasm [=====|====] Moderate (6/10) Technical [====|=====] Accessible (4/10) Warmth [======|===] Warm (7/10)


---

### Voice Principles

#### 1. Say it Straight
No corporate speak, no jargon inflation. If you can say it
in fewer words, do it.

**Examples:**
- ✅ "We build tools that actually work"
- ❌ "We leverage cutting-edge solutions to optimize..."

#### 2. Take Their Side
Position as ally against frustration. You share their pain
with the status quo.

**Examples:**
- ✅ "Most productivity apps make your life harder"
- ❌ "Our competitors offer suboptimal experiences"

#### 3. Stay Human
Contractions, casual language, occasional humor. Sound like
a person, not a press release.

**Examples:**
- ✅ "Here's the thing about..."
- ❌ "It is important to note that..."

#### 4. Confident, Not Arrogant
State opinions clearly without hedging, but don't put
others down.

**Examples:**
- ✅ "No fluff, no complexity"
- ❌ "Unlike those other terrible apps..."

---

### Linguistic Patterns

| Element | Pattern | Examples |
|---------|---------|----------|
| Sentence length | Short to medium (8-15 words average) | "We think that's backwards." |
| Contractions | Always used | "That's", "shouldn't", "we're" |
| Pronouns | Heavy "we/you" | Creates conversational feel |
| Active voice | Strong preference | "We build" not "Tools are built" |
| Punctuation | Occasional em-dashes, rare exclamations | "No fluff—just software" |
| Emoji | Occasional, relevant | Coffee emoji for Monday post |

---

### Voice Do's and Don'ts

#### DO ✅

| Pattern | Example |
|---------|---------|
| Use contractions | "We're building" not "We are building" |
| Start with "Here's the thing" | Conversational opener |
| Use "actually" for emphasis | "Tools that actually work" |
| Reference shared frustrations | "Mondays are hard" |
| Keep paragraphs short | 2-3 sentences max |
| Use second person | "Your trial" "helps you" |

#### DON'T ❌

| Pattern | Why Not |
|---------|---------|
| "Leverage" "optimize" "synergy" | Corporate jargon |
| "We are pleased to announce" | Stiff, formal |
| Passive voice | "Was built by our team" |
| Hedging language | "We think maybe possibly..." |
| Long, complex sentences | Loses casual feel |
| Excessive exclamation points | Feels fake enthusiastic |

---

### Word Choice Guide

#### Preferred Terms

| Instead of | Use |
|------------|-----|
| Utilize | Use |
| Leverage | Use |
| Solutions | Tools, software |
| Empower | Help |
| Seamless | Easy, simple |
| Robust | Strong, reliable |
| Best-in-class | (just show, don't tell) |
| Cutting-edge | New, latest |

#### Signature Phrases

| Phrase | When to Use |
|--------|-------------|
| "Here's the thing" | Starting opinion pieces |
| "Actually" | Emphasizing real value |
| "No [negative], no [negative]" | Simple value props |
| "That's backwards" | Calling out industry norms |

---

### Channel Variations

#### Website (Core Voice)
- Most polished version
- Still casual but refined
- Slightly higher stakes language

#### Blog (Extended Voice)
- More conversational
- Can be longer, more exploratory
- Personal opinions encouraged

#### Social Media (Compressed Voice)
- Shortest, punchiest
- More humor allowed
- Emoji occasionally OK
- Can reference current events/culture

#### Email (Direct Voice)
- Friendly but action-oriented
- "Hey there" openings OK
- Clear CTAs
- Personal where possible

#### Support (Empathetic Voice)
- Warmer, more patient
- Solution-focused
- Less attitude, more help
- Still casual but careful

---

### Voice Checklist

Before publishing, check:

- [ ] Would you say this to a friend?
- [ ] Are there any "corporate speak" words?
- [ ] Is it shorter than it could be?
- [ ] Is the main point clear?
- [ ] Does it sound like us, not a competitor?
- [ ] Would it make sense without context?

Example 2: Quick Voice Audit

Input:

Does this match our voice?
"We are delighted to inform you that your request has been
processed and the desired outcome has been achieved."

Output:

## Voice Audit

### Verdict: ❌ Does Not Match

---

### Issues Found

| Problem | Example | Should Be |
|---------|---------|-----------|
| Too formal | "We are delighted" | "Great news!" |
| Passive voice | "has been processed" | "We processed" |
| Corporate speak | "desired outcome" | "what you wanted" |
| Stiff structure | Full sentence | Shorter, direct |

---

### Rewritten

**Original:**
> "We are delighted to inform you that your request has been
> processed and the desired outcome has been achieved."

**On-brand version:**
> "Good news! We've taken care of your request—you're all set."

**Even more casual:**
> "Done! Your request went through. You're good to go."

---

### What Went Wrong

This sounds like a corporate auto-reply, not your brand.
It has:
- No contractions
- Passive voice
- Formal phrasing
- No personality

Your brand would sound like a helpful friend delivering good news,
not a legal notice.

Skill Boundaries

What This Skill Does Well

  • Analyzing existing content
  • Extracting voice patterns
  • Creating guidelines
  • Auditing consistency

What This Skill Cannot Do

  • Create voice from scratch
  • Know your brand strategy
  • Access all your content
  • Replace brand judgment

Iteration Guide

Follow-up Prompts:

  • "Rewrite this in our brand voice"
  • "Create voice variations for [channel]"
  • "Audit these samples for consistency"
  • "Add to our word/phrase dictionary"

References

  • NN/g Voice and Tone Guidelines
  • Content Strategy Alliance
  • Mailchimp Voice and Tone
  • Buffer Brand Voice Guide

Related Skills

  • brand-strategy - Overall brand development
  • copywriting-ogilvy - Writing craft
  • storytelling-storybrand - Narrative voice

Skill Metadata

  • Domain: Branding / Content
  • Complexity: Intermediate
  • Mode: cyborg
  • Time to Value: 2-4 hours for full guidelines
  • Prerequisites: Content samples, brand context

Frequently asked questions

What does the Brand Voice Learner AI skill do?

Analyze existing brand content to extract voice patterns, create voice guidelines, and ensure consistent brand expression

Why use Brand Voice Learner on TypingMind?

Because you install it once and use it with any model. Brand Voice Learner is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Brand Voice Learner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/guia-matthieu/clawfu-skills/tree/main/skills/branding/brand-voice-learner. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Brand Voice Learner?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Brand Voice Learner?

As many as you like. As long as a model supports skills, you can use Brand Voice Learner with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Brand Voice Learner AI skill free?

Yes. It is published on GitHub by guia-matthieu under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇