Brand Guidelines logo

Brand Guidelines

Organization
vm0-ai
brand-guidelines

Define or enforce brand voice, messaging, terminology, tone, and style standards.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill namebrand-guidelines
Stars
76
Forks
18
Bundled files
Instructions only
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 vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Brand Guidelines 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/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/brand-guidelines .claude/skills/brand-guidelines
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Guidelines 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 Guidelines 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 Guidelines 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.

Building a Brand Voice Document

A thorough voice reference covers the following areas. Use this structure to help teams articulate their voice from scratch or to interpret an existing voice configuration.

Brand Personality Profile

Describe the brand as though it were a human being. What character traits define it?

Example: "Our brand is the sharp-but-generous mentor — someone who breaks down hard ideas in plain language, takes genuine pride in your progress, and never condescends."

Communication Attributes (3-5)

Each attribute needs four elements to prevent ambiguity:

  • A plain-language definition of what it means in practice
  • A boundary statement explaining what it does NOT mean
  • A sample sentence that embodies the attribute
  • A sample sentence that violates the attribute

Target Audience Profile

  • Primary and secondary audiences the brand addresses
  • Core concerns and motivations of each audience
  • Level of domain expertise to assume
  • Communication expectations and preferences

Messaging Pillars (3-5)

  • The recurring strategic themes the brand reinforces
  • Relative priority among pillars (which leads in any given context)
  • How each pillar maps to an audience need or pain point

Contextual Tone Range

How the voice flexes across situations while remaining unmistakably the same brand. See the Tone Modulation section below.

Editorial Style Rules

Concrete grammar, punctuation, and formatting standards. See Editorial Standards below.

Vocabulary Controls

Approved and prohibited terms. See Vocabulary Governance below.

Defining Communication Attributes

Attribute Spectrum Reference

Positioning attributes on a continuum helps teams calibrate. Common spectrums include:

DimensionEnd AEnd B
RegisterFormal, institutionalRelaxed, conversational
ExpertiseAuthoritative, expertCollaborative, peer-level
WarmthEmpathetic, personalDirect, no-nonsense
TechnicalityPrecise, specializedPlain, universally accessible
IntensityBold, high-energyCalm, understated
LevityPlayful, wittySerious, measured
OrientationForward-looking, innovativeEstablished, reliability-focused

Attribute Documentation Template

For every selected attribute, record:

[Attribute Name]

  • In practice: [concrete behavioral description]
  • Not to be confused with: [the common misinterpretation]
  • Sounds like: [example sentence demonstrating it well]
  • Does not sound like: [example sentence that crosses the line]

Example:

Welcoming

  • In practice: inclusive, clear, free of jargon, equally respectful to newcomers and veterans
  • Not to be confused with: oversimplified, excessively informal, or lacking depth
  • Sounds like: "Getting set up takes about five minutes — here is how."
  • Does not sound like: "Yo! Even a total beginner can figure this out lol."

Tone Modulation

The brand voice is the constant; tone is the variable that adjusts based on context. Tone represents the emotional calibration applied to the voice.

Tone by Communication Channel

ChannelTone ShiftIllustration
BlogEducational, conversational, exploratory"Here is a walkthrough of how this works and why your team should care."
LinkedInProfessional, thought-provoking, compact"Three takeaways from running 50 campaigns last quarter."
Twitter/XSharp, concise, occasionally playful"Your landing page gets 3 seconds. Spend them wisely."
Email marketingPersonal, supportive, action-oriented"We built something we think will save you real time."
Sales materialsAssured, benefit-focused, evidence-backed"Teams on our platform cut reporting overhead by 40%."
Help documentationPatient, sequential, unambiguous"If this error appears, follow these steps to resolve it."
Press releasesFormal, factual, newsworthy"The company announced today the general availability of..."
Error statesUnderstanding, constructive, non-blaming"We hit a snag on our side. Our team is already investigating."

Tone by Scenario

ScenarioTone Adjustment
Product launchConfident, enthusiastic, forward-looking
Service disruptionTransparent, accountable, empathetic
Customer winCelebratory, specific, customer-centered
Industry thought leadershipNuanced, evidence-driven, authoritative
New user onboardingEncouraging, clear, welcoming
Unwelcome news (price changes, deprecations)Honest, respectful, solution-focused
Competitive positioningSelf-assured, factual, never disparaging

The Dial Principle

Voice attributes remain constant. Tone turns their intensity up or down depending on the moment. For a brand that is "confident and warm":

  • At a product launch, confidence takes the lead
  • During an outage, warmth takes the lead
  • Neither quality vanishes; the emphasis shifts

Editorial Standards

Grammar and Mechanical Choices

Consistency matters more than any single choice. Document and enforce these decisions:

DecisionAlternativesSample
Serial commaInclude / Omit"fast, reliable, and secure" vs. "fast, reliable and secure"
Heading capitalizationSentence case / Title case"How to get started" vs. "How to Get Started"
ContractionsPermit / Avoid"we're" vs. "we are"
Em dash styleNo surrounding spaces / Spaces"this—and more" vs. "this — and more"
Numeral rulesSpell out one through nine / Always use digits"five features" vs. "5 features"
Percentage notationSymbol / Word"50%" vs. "50 percent"
Date stylingMonth DD, YYYY / DD/MM/YYYY / other"January 15, 2025"
Time styling12-hour / 24-hour"3:00 PM" vs. "15:00"
List punctuationTerminal periods / No periods on fragments"Set up your account." vs. "Set up your account"

Formatting Conventions

  • Heading hierarchy rules (when H1, H2, H3 are appropriate)
  • Bold vs. italic purpose (bold for emphasis, italic for titles or introducing terms)
  • Hyperlink text standards (always descriptive; never "click here")
  • Image alt text requirements
  • Code formatting norms (for technical brands)
  • Use of callout or highlight boxes

Punctuation and Emphasis Policies

  • Exclamation marks: use sparingly, never consecutively
  • Ellipses: avoid in professional content
  • All-caps: prohibited for emphasis; use bold instead
  • Emoji: prohibited in professional channels; acceptable in social where context warrants

Vocabulary Governance

Standardized Terms

Maintain an authoritative list of correct forms alongside common mistakes:

Approved FormIncorrect FormRationale
sign up (verb)signup (verb)"signup" is the noun/adjective form
log in (verb)login (verb)"login" is the noun/adjective form
set up (verb)setup (verb)"setup" is the noun/adjective form
emaile-mailNo hyphen; industry standard
websiteweb siteSingle word; modern convention
data is (singular)data areUnless publication style mandates plural

Product and Feature Naming

  • Canonical capitalization for every product name
  • Rules for when to use the full name vs. an abbreviated form
  • Whether "the" precedes product names
  • How version numbers appear in copy
  • Trademark and registration symbol usage (where required and where to omit)

Language Inclusivity

  • Default to gender-neutral pronouns (they/them for individuals of unknown gender)
  • Eliminate ableist expressions ("crazy", "blind spot", "lame")
  • Favor person-first phrasing where relevant
  • Steer clear of culturally-bound idioms that resist translation
  • Prefer "straightforward" or "simple" over "easy" — difficulty is subjective

Technical and Industry Terminology

  • Catalogue which specialized terms the audience grasps without explanation
  • Identify jargon that must always be defined or replaced with plain language
  • Specify which acronyms require full expansion on first use
  • Build an audience-segmented glossary for terms with different meanings across reader groups

Competitive and Market Language

  • Define your preferred framing for your product category
  • Establish how competitors are referenced (by name or generically)
  • Identify competitor-coined terms to avoid, so you do not reinforce rival positioning
  • Codify your preferred differentiation phrasing

Frequently asked questions

What does the Brand Guidelines AI skill do?

Define or enforce brand voice, messaging, terminology, tone, and style standards.

Why use Brand Guidelines on TypingMind?

Because you install it once and use it with any model. Brand Guidelines 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 Guidelines in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/brand-guidelines. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Brand Guidelines?

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 Guidelines?

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

Is the Brand Guidelines AI skill free?

It is published on GitHub by vm0-ai. Check the repository for licensing terms. 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 👇