Agent skill
gtmos-content-brand-voice
Codify the brand voice -- tone, preferred and avoided words, example phrases, voice samples and forbidden claims -- as a signed GTM OS definition, then check any copy against it.
Filed under Content and SEO.
From ay-automate/gtmos-skills · 107 skill entries · 0 · pushed 2026-11-02
What it does when it runs
Codify the brand voice -- tone, preferred and avoided words, example phrases, voice samples and forbidden claims -- as a signed GTM OS definition, then check any copy against it. With GTM OS connected it reads the current voice (brand.get), drafts a definition.brand_voice from real samples, proposes it for a human to sign, and gates every draft with brand.check_text. Use for \"brand voice\", \"tone of voice\", \"brand guidelines\", \"style guide\", \"words to avoid\", \"forbidden claims\", \"does this sound like us\", \"check this copy against our brand\".
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Ask about gtmos-content-brand-voice
Opens your assistant with this page's recorded context. Check the linked sources before relying on it.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/ay-automate/gtmos-skills.git /tmp/gtmos-skills git -C /tmp/gtmos-skills sparse-checkout set "skills/gtmos-content-brand-voice" mkdir -p ~/.claude/skills/gtmos-content-brand-voice cp -R "/tmp/gtmos-skills/skills/gtmos-content-brand-voice/." ~/.claude/skills/gtmos-content-brand-voice/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
Or take the whole library
This repo ships a .claude-plugin manifest, so Claude Code can install all 107 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.
/plugin marketplace add ay-automate/gtmos-skills /plugin
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from ay-automate/gtmos-skills/blob/86780d2f545cdc0a1de971917aa04b41bb0b3ccd/skills/gtmos-content-brand-voice/SKILL.md, which is licensed MIT (skill frontmatter). 380 words, 6 headings.
Brand voice
Part of GTM OS Skills. Adapted from
brand-guidelines-builderin zapier/gtm-cheat-codes (MIT, Copyright (c) Zapier, Inc.). Changed for GTM OS: the operating section below, rewritten cross-references and tool pointers. Notices: THIRD-PARTY-NOTICES.md (installed beside the skills asTHIRD-PARTY-NOTICES.md).
With GTM OS connected
Rules (GTMOS-RULES.md). Read
policy.get_dry_modefirst; in dry mode every effect stops at a draft. E-class operations are proposed and a different person approves them; never approve your own proposal. Numbers come only from operation results, named with the operation. Claims about results, customers or metrics must be backed by active proof fromproof.list.
1. Current state. brand.get Q returns the signed voice, its version, forbidden claims, avoided words and voice samples. voice: null means none is signed yet.
2. Draft from evidence. Collect real samples (the site, sent emails that got replies from sequence.messages, approved posts) and customer phrases (voice.customer_language.list). Build the spec: label, tone[], vocabulary.preferred[], vocabulary.avoid[], examplePhrases[], voiceSamples[{title, text}] (up to 20), forbiddenClaims[{phrase, reason, match}] (up to 200).
3. Propose, never sign. config.propose_changeset M with the definition.brand_voice (key default); a person reviews and signs it. Until it is signed, drafts are not checked against it.
4. Check copy. brand.check_text Q returns violations (forbidden_claim, avoid_word) with the phrase and excerpt. Every Outreach and SEO draft is checked the same way before send or publish.
Without GTM OS
Write the guidelines as a document with the same fields (tone, preferred and avoided words, examples, forbidden claims), using the method below, and check copy against them by hand.
Use this skill to review creative assets, campaign ideas, or page concepts against a brand system.
Workflow
- Ask for the asset, brief, audience, and channel when missing.
- Review color, typography, logo usage, imagery, layout, and tone.
- Score alignment and explain issues in plain language.
- Provide prioritized fixes and escalation guidance.
Zapier MCP And SDK Role
- Use Zapier MCP to read approved brand docs, asset libraries, and design references.
- Use Zapier SDK only if the team wants a repeatable review intake queue or feedback log.
- Keep official guideline changes and final external use human-approved.
Guardrails
- Do not invent brand rules.
- Link only to approved public or team-approved brand resources.
- Keep feedback practical and kind.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- brand-voice-guidelines by thatrebeccarae · 189
- brand-voice by Salesably · 54
- brand-voice by taizen-ai · 8
- brand-voice by ekatasingh1107 · 2
- brand-voice-extractor by edupegoretti · 0
- brand-voice-guide by esmefong · 0
- content-strategy by coreyhaines31 · 57,918
- brand-answer-monitoring by irinabuht12-oss · 6,620
Need help setting it up?
This page tells you what gtmos-content-brand-voice does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.