Brand Voice & Style Guide Creator

What it does

/define-brand-voice is a Cursor slash command. Type it in chat to run a saved workflow: Brand Voice & Style Guide Creator.

Establishes brand guidelines, tone rules, prohibited cliché lists, and cross-channel messaging standards tailored to technical audiences.

Tone parameters, prohibited buzzwords, and developer-centric copy rules. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /define-brand-voice for you.

Why it exists

Founders retype the same multi-step prompt until it rots. /define-brand-voice exists so the pipeline, all 4 steps of it, is a file in .cursor/commands, versioned with the repo.

It ships in the Marketing Kit. It is wired to the Brand Identity & Tone Lead (brand-voice) and Direct Response Copywriter (copywriter) agents. Required skills: Brand Voice Guidelines & Jargon Elimination; Marketing Psychology & Direct Response Principles.

When to use it

• Use to ensure consistent messaging across landing pages, ads, documentation, and emails.
• Use /define-brand-voice when you want that pipeline, not a freeform chat. If you only need one step, use a narrower command or a single agent.
• Start a new chat. Do not run this command in a thread that just touched production SQL.

When not to use it

• Do not run /define-brand-voice as a substitute for reading the diff. The command produces files; you still gate them.
• Do not chain it into a 40-turn chat. Fresh context is part of the design.
• Do not run it if you have not filled CURSOR.md. The pipeline will invent a stack.

Example workflow

1. Define brand personality attributes (e.g. precise, direct, pragmatic)
2. Establish banned buzzword and corporate cliché filter lists
3. Create before-and-after copywriting examples for landing, email, and docs
4. Auto-save style guide to docs/marketing/brand-voice.md

Example usage

Type this in Cursor chat: /define-brand-voice Create brand voice guide with do's and don'ts for technical audience

The command file tells the session which agents to adopt and which skills to read. You should see phase headers, not a single dump of code.

If a phase fails its gate, stop. Do not add 'just continue'.

Example output

• Expected artifact: docs/marketing/brand-voice.md

Best practices

• Keep the prompt specific. /define-brand-voice Create brand voice guide with do's and don'ts for technical audience is the shape: object, constraint, and outcome.
• Let the listed agents work in order: brand-voice → copywriter.
• Save outputs in the repo. Chat-only answers evaporate.
• Marketing commands write to docs/marketing/ so the next command can read positioning before it writes a landing page.

Common mistakes

• Typing /define-brand-voice with no object ('do the thing'). The pipeline will guess.
• Re-running the command in the same chat after a failed gate instead of fixing the failing file.
• Editing the command file to skip review so it 'goes faster'.
• Skipping the Brand Voice Guidelines & Jargon Elimination skill that the command depends on.