Brand Voice Kit
A brand voice only works if it's operational — specific enough that a person or a model can apply it without guessing. This skill turns fuzzy adjectives ("professional but friendly") into a concrete rule set you can drop into any content workflow as guardrails.
Fallback: Running in Cloud/Web Environments (e.g., Claude.ai, CoWork)
If you are running in a cloud-based or web-based environment (such as Claude.ai web or CoWork) where local file system or repository access is unavailable:
- Ask the user to paste 2-3 examples of writing they like, 1-2 examples they dislike, and their target audience.
- Conduct the voice analysis and build the rule set manually in-context.
- Output the structured Voice Profile using the templates below.
Workflow
Intake & Material Review:
- Gather sample articles, emails, or posts.
- Define target customer persona and context (e.g., B2B enterprise vs. consumer D2C).
Establish Voice Traits (3–4 traits):
- Define traits as clear spectrums (e.g., Formal to Casual). Specify where on the spectrum the brand sits.
Define Do / Don't Rules:
- Map exact language behaviors, not just adjectives. Specify what to write and what to avoid.
Lexicon & Formatting Rules:
- Document permitted terminology, banned buzzwords, emoji policies, and punctuation quirks.
Provide Before / After Examples:
- Provide 2–3 side-by-side examples showing a generic sentence rewritten to match the brand voice.
Templates & Output Format
Ensure the brand voice profile is generated in a clean, drop-in format:
1. Brand Voice Profile
🏷️ Voice Traits & Spectrums
- Trait 1: [Name, e.g. Conversational] — Warm, personal, direct to consumer.
Formal ―――—●― Casual
- Trait 2: [Name, e.g. High Information] — Stat-driven, direct, educational.
Speculative ―――——● High-Proof
📝 Rules Matrix
| Do |
Don't |
| Write short, active sentences. |
Corporate hedging (e.g., "we strive to"). |
| Address the reader as "you" directly. |
Third-person distance (e.g., "users should"). |
| Use concrete examples and exact stats. |
Buzzword stacking (e.g., "synergy", "disruptive"). |
📖 Lexicon & Guidelines
- Approved Terms:
[term1], [term2], [term3]
- Banned Buzzwords:
[word1], [word2], [word3]
- Emoji/Formatting Policy: E.g., Maximum 1 emoji per paragraph, no emojis in headers.
🔄 Voice Refinement Examples
- [Generic: Our platform assists businesses in optimizing their social campaigns for enhanced user engagement.]
+ [On-Brand: We build tools that make your ads stand out so you get more clicks and sales.]
[!TIP]
The One-Line North Star: Create a single, memorable sentence that sums up the voice (e.g., "Write like an experienced colleague explaining a concept over coffee.") so writers can quickly QA their drafts.
1---2name: brand-voice-kit3description: Define a brand's voice and turn it into a reusable rule set that keeps every piece of AI-generated content on-brand. Use when the user is setting up a brand voice, wants consistency across writers/channels, needs a voice guide, or wants to "make this sound like us." Produces a voice profile (traits, do/don't, lexicon, examples) that can be pasted into any content prompt as guardrails. Triggers on: "brand voice", "tone of voice", "make it sound like us", "voice guide", "brand consistency", "style guide", "on-brand".4---56# Brand Voice Kit78A brand voice only works if it's *operational* — specific enough that a person or a model can apply it without guessing. This skill turns fuzzy adjectives ("professional but friendly") into a concrete rule set you can drop into any content workflow as guardrails.910## Fallback: Running in Cloud/Web Environments (e.g., Claude.ai, CoWork)1112If you are running in a cloud-based or web-based environment (such as Claude.ai web or CoWork) where local file system or repository access is unavailable:131. Ask the user to paste 2-3 examples of writing they like, 1-2 examples they dislike, and their target audience.142. Conduct the voice analysis and build the rule set manually in-context.153. Output the structured Voice Profile using the templates below.1617---1819## Workflow20211. **Intake & Material Review:**22 - Gather sample articles, emails, or posts.23 - Define target customer persona and context (e.g., B2B enterprise vs. consumer D2C).24252. **Establish Voice Traits (3–4 traits):**26 - Define traits as clear spectrums (e.g., Formal to Casual). Specify where on the spectrum the brand sits.27283. **Define Do / Don't Rules:**29 - Map exact language behaviors, not just adjectives. Specify what to write and what to avoid.30314. **Lexicon & Formatting Rules:**32 - Document permitted terminology, banned buzzwords, emoji policies, and punctuation quirks.33345. **Provide Before / After Examples:**35 - Provide 2–3 side-by-side examples showing a generic sentence rewritten to match the brand voice.3637---3839## Templates & Output Format4041Ensure the brand voice profile is generated in a clean, drop-in format:4243### 1. Brand Voice Profile4445#### 🏷️ Voice Traits & Spectrums46* **Trait 1: [Name, e.g. Conversational]** — *Warm, personal, direct to consumer.*47 `Formal ―――—●― Casual`48* **Trait 2: [Name, e.g. High Information]** — *Stat-driven, direct, educational.*49 `Speculative ―――——● High-Proof`5051#### 📝 Rules Matrix5253| Do | Don't |54| :--- | :--- |55| **Write short, active sentences.** | **Corporate hedging (e.g., "we strive to").** |56| **Address the reader as "you" directly.** | **Third-person distance (e.g., "users should").** |57| **Use concrete examples and exact stats.** | **Buzzword stacking (e.g., "synergy", "disruptive").** |5859#### 📖 Lexicon & Guidelines60* **Approved Terms:** `[term1]`, `[term2]`, `[term3]`61* **Banned Buzzwords:** `[word1]`, `[word2]`, `[word3]`62* **Emoji/Formatting Policy:** *E.g., Maximum 1 emoji per paragraph, no emojis in headers.*6364#### 🔄 Voice Refinement Examples6566```diff67- [Generic: Our platform assists businesses in optimizing their social campaigns for enhanced user engagement.]68+ [On-Brand: We build tools that make your ads stand out so you get more clicks and sales.]69```7071> [!TIP]72> **The One-Line North Star:** Create a single, memorable sentence that sums up the voice (e.g., *"Write like an experienced colleague explaining a concept over coffee."*) so writers can quickly QA their drafts.
architshahdigital