Skip to content
TrustedSkillsbeta
Back to all skills

Brand Voice Enforcement

Official
anthropics·vlatest·marketing·Apache-2.0

Ensures consistent brand messaging across all outputs by analyzing and applying defined tone, style, and terminology – boosting brand recognition & trust.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add anthropics/knowledge-work-plugins --skill brand-voice-enforcement -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

anthropics

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned anthropics/knowledge-work-plugins at da38ec1ee8.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
da38ec1ee8
Manifest
partner-built/brand-voice/skills/brand-voice-enforcement/SKILL.md
Scanned
3 files, 399 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill ensures consistent brand messaging across all sales and marketing content generated by an AI agent. It loads user-defined brand guidelines, applies voice constants and tone adjustments based on context (content type and target audience), validates output against those guidelines, and can explain the reasoning behind specific brand choices. The goal is to boost brand recognition and trust through consistent communication.

When to use it

  • Generating marketing emails or social media posts that need to align with established brand voice.
  • Creating sales presentations or proposals where a consistent tone and terminology are crucial.
  • When you want the AI agent to explain why certain wording choices were made based on your brand guidelines.
  • Ensuring content reflects specific messaging pillars and value propositions.

Key capabilities

  • Brand Guideline Loading: Automatically finds existing brand guidelines from previous sessions or a local file (.claude/brand-voice-guidelines.md).
  • Guidance Prompting: If no guidelines are found, prompts the user to provide them through various methods (discovery, generation, pasting, or linking).
  • Voice Constant Application: Enforces consistent brand personality ("We Are / We Are Not" attributes) and approved terminology.
  • Tone Flexing: Adjusts tone based on content type and target audience using a tone-by-context matrix.
  • Enforcement Settings: Reads settings from .claude/brand-voice.local.md to control strictness of enforcement (strict, balanced, flexible) and whether explanations are always provided.

Example prompts

  • "Write an email announcing our new product, ensuring it aligns with our brand voice."
  • “Create a social media post about [topic] following our brand guidelines.”
  • "Generate a proposal for [client], explaining the reasoning behind my brand choices."

Tips & gotchas

  • Brand Guidelines Required: The skill requires existing brand guidelines to function. If none are found, you'll be prompted to provide them.
  • Working Folder Dependency: The local guideline file search relies on a user’s working folder being set.
  • Local Enforcement Settings: Remember that .claude/brand-voice.local.md can override guidelines from other sources, controlling the level of enforcement and explanation provided.