enforce-voice — Claude Code command: brand voice
The enforce-voice Claude Code command applies brand guidelines to a content request. It checks the draft’s voice, tone and terminology against those rules.
MIT ★ 36,654 updated 2026-10-24
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install brand-voice@knowledge-work-pluginsWhat enforce-voice does
The command first checks for a selected working folder, then looks for guidelines in the session or in .claude/brand-voice-guidelines.md inside that folder. Without a selected folder, it stops and asks for confirmation before continuing; guidelines created in that conversation will not carry over to later sessions.
Once it has the guidelines, the command identifies the content type, audience and requirements, then drafts and checks the text against the brand’s voice and terminology rules. It gives a short account of its brand choices, flags open questions that affect the content and offers to revise the result. If no guidelines are available, run /brand-voice:discover-brand or /brand-voice:generate-guidelines, or paste the rules into the chat.
What it helps with
- apply brand guidelines to a content request
- match a draft’s tone and terminology to brand rules
- check generated copy against brand do’s and don’ts
Example prompts for the agent
- Write homepage copy using our brand guidelines.
- Draft a product announcement in our brand voice and explain the tone choices.
- Check this text against our brand rules and revise it.
How to install enforce-voice
1Plugin marketplace
/plugin marketplace add anthropics/knowledge-work-plugins/plugin install brand-voice@knowledge-work-plugins2Manually: put the files in place
.claude/commands/enforce-voice.mdCall it with /enforce-voice. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/enforce-voice.mdCall it with /prompts:enforce-voice. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/enforce-voice.prompt.mdManually: put the files in place
.gemini/commands/enforce-voice.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about enforce-voice
How do I install enforce-voice in Claude Code?
Run these commands in order: /plugin marketplace add anthropics/knowledge-work-plugins, then /plugin install brand-voice@knowledge-work-plugins.
What does enforce-voice do?
It drafts content from brand guidelines and checks the voice, tone and terminology. It also points out open questions in the guidelines that affect the text.
What does enforce-voice need to work?
A working folder must be selected, and brand guidelines must be available in the session or in .claude/brand-voice-guidelines.md. If none are found, run /brand-voice:discover-brand or /brand-voice:generate-guidelines, or paste the rules into the chat.
Source text
enforce-voice.md · MIT
---
description: Apply brand guidelines to content creation
argument-hint: "<content request>"
---
**MANDATORY FIRST STEP — do this before anything else, including loading guidelines or processing the content request.** Check whether the user has a working folder selected for this session. You must verify this before starting any enforcement work. If there is no working folder, stop and warn the user: "You don't have a working folder selected. Without one, I can't load saved guidelines from a previous session, and any guidelines generated in this conversation won't be saved for future sessions either. Please select a working folder and re-run this command. If you'd like to proceed anyway (guidelines will only be usable in this session), let me know." Wait for the user to confirm before continuing.
Load the user's brand guidelines and apply them to the content request provided in $ARGUMENTS.
Find brand guidelines using this sequence (stop as soon as found):
1. Session context — check if guidelines were generated earlier in this conversation
2. Local guidelines file — check for `.claude/brand-voice-guidelines.md` inside the user's working folder. Do NOT use a relative path from the agent's current working directory (in Cowork, the agent runs from a plugin cache directory). If no working folder is set, skip this step.
3. If not found, ask the user to run `/brand-voice:discover-brand`, `/brand-voice:generate-guidelines`, or paste guidelines directly
Once guidelines are loaded, follow the brand-voice-enforcement skill instructions to:
1. Analyze the content request (type, audience, key messages, requirements)
2. Apply voice constants ("We Are / We Are Not") and flex tone for context (formality, energy, technical depth)
3. Generate content applying voice, tone, messaging, and terminology guidelines
4. Validate output against brand do's and don'ts
5. Present the content with a brief explanation of brand choices made
6. Note any open questions from guidelines that affect this content
7. Offer to refine based on feedback
© Tribe AI · MIT · anthropics/knowledge-work-plugins