Brand Voice Guidelines
Writing skill, available on Zeplik
Brand Voice Guidelines is a ready-to-run writing skill on Zeplik. Produces a structured, enforceable brand voice guideline with a We Are/We Are Not table, tone matrix, confidence scores, and open questions from docs, transcripts, or user input. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Brand voice guideline doc with We Are/We Are Not table, tone matrix, confidence scores, open questions (see artifact-templates/document.md).
The Brand Voice Guidelines skill loads automatically when your request matches it, or you can invoke it directly by typing /guideline-generation in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Brand Voice Guidelines skill can do
- Build a We Are / We Are Not table with 4+ evidence-backed rows
- Generate a tone by context matrix covering formality, energy, and depth
- Assign confidence scores per section based on source corroboration
- Surface open questions with concrete recommendations for user decisions
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Brand Voice Guidelines skill works
Guideline Generation
Generate comprehensive, LLM-ready brand voice guidelines from any combination of sources — brand documents, sales call transcripts, discovery reports, or direct user input. Transform raw materials into structured, enforceable guidelines with confidence scoring and open questions.
Inputs
Accept any combination of:
- Discovery report (structured, pre-triaged sources) — use as primary input when present
- Brand documents (PDF, PPTX, DOCX, MD, TXT)
- Conversation transcripts (call recordings, meeting notes, manual uploads)
- Direct user input about brand voice and values
If no sources are available, ask the user to share brand documents or transcripts before proceeding.
Generation Workflow
1. Identify and classify sources
Determine what the user provided. Group into documents, transcripts, and direct input.
2. Process sources
- Documents: extract voice attributes, messaging themes, terminology, tone guidance, and examples.
- Transcripts: extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.
- Discovery reports: use the ranked sources, conflicts, and gaps directly.
3. Synthesize into guidelines
"We Are / We Are Not" table — the core brand identity anchor:
| We Are | We Are Not |
|---|---|
| Confident | Arrogant |
| Approachable | Casual or sloppy |
Derive attributes from the most consistent patterns across sources. Each row needs supporting evidence. Aim for 4+ rows.
Voice constants vs. tone flexes:
- Voice = personality, values, "We Are / We Are Not" — constant across all content.
- Tone = formality, energy, technical depth — flexes by context.
Tone-by-context matrix:
| Context | Formality | Energy | Technical Depth | Example |
|---|---|---|---|---|
| Cold outreach | Medium | High | Low | "[example phrase]" |
| Enterprise proposal | High | Medium | High | "[example phrase]" |
| Social media | Low | High | Low | "[example phrase]" |
Cover at least 3 contexts.
4. Assign confidence scores
Score each section:
- High: 3+ corroborating sources, explicit guidance found.
- Medium: 1-2 sources, or inferred from patterns.
- Low: single source, inferred, or conflicting data.
5. Surface open questions
For any ambiguity that cannot be resolved, list an open question with: what was found, a recommendation, and the specific decision needed from the user. Every open question MUST include a recommendation — turn ambiguity into "confirm or override," never a dead end.
6. Quality check
Before presenting, verify: all major sections populated; at least 3 voice attributes with evidence; "We Are / We Are Not" has 4+ rows; tone matrix covers 3+ contexts; confidence scores per section; source attribution for extracted elements; no PII exposed; open questions include recommendations.
7. Present
Summarize: sections generated with confidence breakdown, strongest voice attribute, most effective message, and number of open questions. Offer to walk through section by section or resolve open questions.
Privacy
Enforce throughout, not only at output: redact customer names and contact info from examples, anonymize company names in transcript excerpts if requested, flag any sensitive information detected.
Output
A saved brand voice guideline document containing the "We Are / We Are Not" table, voice-vs-tone breakdown, tone-by-context matrix, per-section confidence scores, and a prioritized list of open questions with recommendations.
How to use the Brand Voice Guidelines skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Brand Voice Guidelines skill right away.
Describe your writing task
Ask in plain language, or type /guideline-generation to invoke the skill directly. Zeplik recognizes the Brand Voice Guidelines skill and applies its method.
Review and refine the result
Zeplik returns a structured document you can edit, download, and reuse. Ask follow-ups to refine it.
Source and credit
- Author
- Anthropic
- License
- Apache-2.0
Adapted from the open-source anthropics/knowledge-work-plugins project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Brand Voice Guidelines skill?
- Brand Voice Guidelines is a ready-to-run writing skill on Zeplik. Produces a structured, enforceable brand voice guideline with a We Are/We Are Not table, tone matrix, confidence scores, and open questions from docs, transcripts, or user input. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer. It returns a structured document you can keep and reuse: Brand voice guideline doc with We Are/We Are Not table, tone matrix, confidence scores, open questions (see artifact-templates/document.md).
- How do I use Brand Voice Guidelines on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /guideline-generation in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Brand Voice Guidelines skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Brand Voice Guidelines skill runs on your preferred model for the task.
- Where does the Brand Voice Guidelines skill come from?
- The Brand Voice Guidelines skill is adapted from the open-source anthropics/knowledge-work-plugins project (Apache-2.0) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Brand Voice Guidelines skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related writing skills
- AI Text HumanizerRewrite text to strip recognizable AI-writing patterns (inflated significance, formulaic transitions, stock vocabulary, generic endings) while preserving full content and the author's voice. Use for 'humanize this', 'make it sound less like AI', 'natural voice'. Not for marketing-copy quality sweeps (use copy-editing).
- Brand Voice DiscoveryUse when the user wants to find or audit brand materials across their platforms -- 'find our style guide', 'what brand docs do we have', 'discover brand voice', 'audit brand content' -- searching Notion, Drive, Slack, Confluence, Figma, etc. Not for applying an existing voice to content (use brand-voice-enforcement).
- Brand Voice GuardianUse when content must match the company's brand voice -- 'make this sound like us', 'rewrite this in our tone', 'is this on-brand', or any email/post/deck request where brand guidelines apply. Loads existing guidelines and enforces voice constants and tone flexes. Not for finding brand docs (use discover-brand).
- Content CreatorUse for channel-specific marketing content structures and frameworks -- blog post, social media, email newsletter, landing page, press release, and case study templates, SEO checklists, headline formulas, CTA patterns: 'what's the right structure for a case study'. For a guided draft, use draft-content.
- Content DrafterUse when the user asks to draft a specific piece of marketing content -- 'write a LinkedIn post about our launch', 'draft a blog post on X', 'write a press release' -- gathering content type, topic, audience, and brand voice first. For structure reference use content-creation; for drip flows use email-sequence.
- Content Pipeline NavigatorUse to chain content production across skills -- brand voice, strategy, drafting, editing, humanizing. Not for a single draft (use draft-content) or a one-off edit pass (use copy-editing).
More on Zeplik
Try Brand Voice Guidelines on Zeplik
Every model, one chat. Bring the Brand Voice Guidelines skill into your next conversation and let the assistant do the work.