agentsclimarketplace
Sign in

Brand voice kit

Skill architshahdigital/claude-marketing-skills/skills/brand-voice-kit

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".From its SKILL.md

Install
npx -y skills add architshahdigital/claude-marketing-skills --skill brand-voice-kit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.5 KB, 751 tokens by cl100k_base, as published. Nobody here has run it

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:

  1. Ask the user to paste 2-3 examples of writing they like, 1-2 examples they dislike, and their target audience.
  2. Conduct the voice analysis and build the rule set manually in-context.
  3. Output the structured Voice Profile using the templates below.

Workflow

  1. Intake & Material Review:

    • Gather sample articles, emails, or posts.
    • Define target customer persona and context (e.g., B2B enterprise vs. consumer D2C).

  2. Establish Voice Traits (3–4 traits):

    • Define traits as clear spectrums (e.g., Formal to Casual). Specify where on the spectrum the brand sits.

  3. Define Do / Don't Rules:

    • Map exact language behaviors, not just adjectives. Specify what to write and what to avoid.

  4. Lexicon & Formatting Rules:

    • Document permitted terminology, banned buzzwords, emoji policies, and punctuation quirks.

  5. 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

DoDon'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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 751 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • gather sample materials and define target audience
  • define three to four voice traits as spectrums
  • map specific language behaviors as do and don't rules
  • document permitted terminology and banned buzzwords
  • specify emoji and punctuation policies
  • provide two to three before and after examples

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.