generate-guidelines — Claude Code command: brand guide and setup
generate-guidelines — a Claude Code command that turns brand documents, transcripts, or discovery reports into voice guidelines. It brings the findings together and saves the guide in the working folder.
MIT ★ 36,654 updated 2026-10-24
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install brand-voice@knowledge-work-pluginsWhat generate-guidelines does
The command analyses the supplied material and builds a unified set of brand voice guidelines. The result includes a “We Are / We Are Not” table, a tone-by-context matrix, confidence scores for each section, and open questions with suggested ways to resolve them.
Sources can be supplied directly or drawn from reports, documents, and transcripts. Supported document formats include PDF, PowerPoint, Word, Markdown, and plain text. Transcript sources include Gong and Granola through MCP, Notion meeting notes, and manual uploads. A selected working folder is required to save the output; the file goes to .claude/brand-voice-guidelines.md, with an existing copy archived first.
What it helps with
- combine brand documents and transcripts into voice guidelines
- map tone choices to different contexts
- record unclear points and questions raised by source material
Example prompts for the agent
- Create brand voice guidelines from
brand.pdfand the interview transcript. - Turn this report and the supplied documents into tone guidelines.
- Draft a brand voice guide from this company description.
How to install generate-guidelines
1Plugin marketplace
/plugin marketplace add anthropics/knowledge-work-plugins/plugin install brand-voice@knowledge-work-plugins2Manually: put the files in place
.claude/commands/generate-guidelines.mdCall it with /generate-guidelines. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/generate-guidelines.mdCall it with /prompts:generate-guidelines. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/generate-guidelines.prompt.mdManually: put the files in place
.gemini/commands/generate-guidelines.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about generate-guidelines
How do I install generate-guidelines in Claude Code?
Keep this order.
What does generate-guidelines do?
It combines brand material into a voice guide with a “We Are / We Are Not” table, a tone-by-context matrix, and confidence scores. The guide is saved at .claude/brand-voice-guidelines.md.
What does generate-guidelines need to work?
A working folder must be selected for the guide to be saved. Source material can be provided directly; connected services such as Notion or Google Drive can also supply materials when available.
Source text
generate-guidelines.md · MIT
--- description: Generate brand voice guidelines from documents, transcripts, discovery reports, or any combination argument-hint: "<sources — documents, transcripts, or description of what you have>" --- **MANDATORY FIRST STEP — do this before anything else, including reading sources or processing arguments.** Check whether the user has a working folder selected for this session. You must verify this before starting any guideline generation 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 save guidelines to a file — they'll only exist in this conversation and won't persist to future sessions. Please select a working folder and re-run this command. If you'd like to proceed anyway, let me know." Wait for the user to confirm before continuing. Generate comprehensive, LLM-ready brand voice guidelines from whatever sources the user provides — brand documents, conversation transcripts, a discovery report from `/brand-voice:discover-brand`, or direct input. Process the sources specified in $ARGUMENTS. If none specified, check: 1. Whether a discovery report was generated in this session 2. `.claude/brand-voice.local.md` for known brand material locations 3. Connected platforms (Notion, Confluence, Google Drive, Box, SharePoint, Gong) for existing materials 4. If nothing is available, suggest running `/brand-voice:discover-brand` first Follow the guideline-generation skill instructions to: 1. Identify and classify all available sources (discovery report, documents, transcripts) 2. Delegate to document-analysis and conversation-analysis agents as needed 3. Synthesize findings into unified guidelines with "We Are / We Are Not" table and tone-by-context matrix 4. Assign confidence scores per section 5. Surface open questions with agent recommendations for any ambiguity 6. Present key findings and offer next steps 7. Save guidelines to `.claude/brand-voice-guidelines.md` inside the user's working folder (archiving any existing file first). Do NOT use a relative path from the agent's current working directory — in Cowork, the agent runs from a plugin cache directory, not the user's project. After generation, guidelines are saved locally so `/brand-voice:enforce-voice` can automatically find them in future sessions. Supported document formats: PDF, PowerPoint, Word, Markdown, plain text. Supported transcript sources: Gong (MCP), Granola (MCP), Notion meeting notes, manual uploads.
© Tribe AI · MIT · anthropics/knowledge-work-plugins