スキル一覧に戻る

brand-voice-learner

guia-matthieu
更新日 2 days ago
4 閲覧
111
20
111
GitHubで表示
メタdesign

について

このスキルは、既存のブランドコンテンツを分析して口調パターンを抽出し、実践的なガイドラインを作成することで、一貫したブランド表現の維持を支援します。ライターのオンボーディング、コンテンツ監査、AIライティングツールのトレーニングに有用です。確立されたコンテンツ戦略手法に基づき、言語分析と口調の次元マッピングを採用しています。

クイックインストール

Claude Code

推奨
メイン
npx skills add guia-matthieu/clawfu-skills -a claude-code
プラグインコマンド代替
/plugin add https://github.com/guia-matthieu/clawfu-skills
Git クローン代替
git clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/brand-voice-learner

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

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

GitHub リポジトリ

guia-matthieu/clawfu-skills
パス: skills/branding/brand-voice-learner
0
ai-skillsanthropicclaude-codeclaude-skillsmarketingmcp-server

関連スキル

content-collections

メタ

このスキルは、Content Collections(Markdown/MDXファイルを型安全なデータコレクションに変換するTypeScriptファーストのツール)の本番環境でテストされた設定を提供します。Zodバリデーションによる型安全性を実現し、ブログ、ドキュメントサイト、コンテンツ重視のVite + Reactアプリケーション構築時にご利用ください。Viteプラグインの設定、MDXコンパイルから、デプロイ最適化、スキーマバリデーションまで、すべてを網羅しています。

スキルを見る

polymarket

メタ

このスキルは、開発者がPolymarket予測市場プラットフォームを活用したアプリケーション構築を可能にします。API統合による取引や市場データの取得に加え、WebSocketを介したリアルタイムデータストリーミングにより、ライブ取引や市場活動を監視できます。取引戦略の実装や、ライブ市場更新を処理するツールの作成にご利用ください。

スキルを見る

creating-opencode-plugins

メタ

このスキルは、開発者がコマンド、ファイル、LSP操作など25種類以上のイベントタイプにフックするOpenCodeプラグインを作成することを支援します。JavaScript/TypeScriptモジュール向けに、プラグイン構造、イベントAPI仕様、および実装パターンを提供します。カスタムイベント駆動ロジックでOpenCode AIアシスタントのライフサイクルをインターセプト、監視、または拡張する必要がある場合にご利用ください。

スキルを見る

sglang

メタ

SGLangは、高性能なLLMサービングフレームワークであり、RadixAttentionプレフィックスキャッシュを活用したJSON、正規表現、エージェントワークフロー向けの高速で構造化された生成を特長とします。特にプレフィックスが繰り返されるタスクにおいて、大幅に高速な推論を実現し、複雑な構造化出力やマルチターン対話に最適です。制約付きデコードが必要な場合や、広範なプレフィックス共有を伴うアプリケーションを構築する場合は、vLLMなどの代替案ではなくSGLangを選択してください。

スキルを見る