brand-voice-guide

$npx mdskill add Significant-Gravitas/skills-catalog/brand-voice-guide

Use this whenever you write or edit anything a customer will read.

SKILL.md

.github/skills/brand-voice-guideView on GitHub ↗
---
name: "brand-voice-guide"
description: "Write in a consistent brand voice: capture the voice once, then apply it to any draft and flag where a draft drifts off it."
triggers: ["brand voice", "tone of voice", "write copy", "on-brand", "style guide", "rewrite this"]
version: "1"
---

# Brand voice guide

Use this whenever you write or edit anything a customer will read.

## First, get the voice on paper

If the user has not given you a voice guide, ask for three things and nothing
more — people abandon long intake forms:

1. Two or three pieces of writing they think sound right.
2. Who the reader is, in one sentence.
3. Three words the brand is, and one word it is not.

Infer the rest from the samples. Write the result back as five to eight rules,
each one testable — "no exclamation marks", not "be energetic". Store it so you
do not ask again.

## Applying the voice

Work in this order. Meaning first, voice second: a perfectly on-brand sentence
that says the wrong thing is a failure.

- Draft for the reader's question, not the brand's message.
- Cut every sentence that survives only because it sounds good.
- Replace abstract nouns with the concrete thing they stand for.
- Read the opening line alone. If it could open any competitor's page, rewrite it.

## Checking a draft

When asked to review rather than write, return the draft with each drift marked
and a one-line reason, then a corrected version. Do not silently rewrite —
people need to see what changed to trust the next one.

Flag these:

- A claim with no evidence behind it.
- A word from the "is not" list.
- Two adjectives where one carries the meaning.
- A sentence over about 25 words that could be two.

## What not to do

Never invent customer numbers, testimonials or results. If a draft needs a
statistic the user has not supplied, leave a marked gap and say what is missing.

More from Significant-Gravitas/skills-catalog

SkillDescription
account-health-and-qbrsUse when a support account wobbles or a quarterly business review looms: read the health signals, run the success plan, and prep the review from evidence.
accounts-receivable-follow-upReview open receivables and draft factual, staged payment follow-ups without inventing status or contacting a customer.
ad-copy-variantsWrite ad variants that each test one idea, within platform limits and supported claims.
alex-getting-startedUse on the first conversation with Alex, or whenever their memory has no product preferences yet: learn what the user is building and who for, where specs, roadmap and numbers live, who decides dates and scope, and get them to a first real product deliverable.
alliance-co-commercializationUse when a strategic alliance needs joint selling governance: operating model, joint targeting, steering prep, and milestone accountability.
anika-getting-startedUse on the first conversation with Anika, or whenever their memory has no partnership preferences yet: learn which partners and alliances the user owns, what motion they run, and get one real partner read on screen in the same session.
assure-partner-led-deliveryUse when partners deliver client work in your name: own the in-flight book, run the weekly delivery review, and rescue engagements before clients feel it.
automate-finance-reportingUse to connect a number source, map an export into the finance ledger, or QA a sheet: the column mapping, the dedupe key, the load summary, and the checks that must pass before a read ships.
billing-refunds-and-exceptionsUse when money is on the table: verify the charge, check the policy, and stage a refund or exception draft that stops at the owner's yes.
board-and-investor-metrics-briefPrepare a concise board or investor metrics brief with definitions, sources, comparisons, drivers, risks, and decisions needed.