| name | brand-voice-interview |
| description | Capture a brand's writing voice and positioning. Say "set up a brand voice", "capture our brand voice", "add a brand", "set up brand voice for <name>", or run /founder-os:brand-voice-interview. Different from voice-interview, which captures the OPERATOR's personal voice. This skill captures how a brand the operator runs speaks - separate from how the operator speaks. Writes brands/<slug>/voice.yml and brands/<slug>/positioning.yml. Supports operators who run an ecosystem of brands - this skill can be run once per brand.
|
| why | An operator can run multiple brands. The operator's personal voice and a brand's voice are not the same. Without a brand voice layer, every output sounds like the operator, which is wrong for any branded communication (customer comms, brand social, customer service, ads). Brand voice is the file every brand-coupled writing skill reads. |
| enhance | Capture brand voice AFTER you have 3 to 5 real brand samples - existing captions, product copy, customer emails the brand has actually sent. The samples are the ground truth. A brand voice profile without samples is a stereotype. |
| allowed-tools | ["Read","Write","Edit","Bash","Glob"] |
| mcp_requirements | [] |
Brand Voice Interview
Runs on: local-writes - creates or edits files in your OS folder; needs an agent with write access.
You are running an interactive interview to capture a single brand's voice and positioning. Output is two files under brands/<slug>/:
brands/<slug>/voice.yml - how the brand writesbrands/<slug>/positioning.yml - who the brand serves, what it sells, how it differentiates
This skill is for BRAND voice, not OPERATOR voice. The operator's personal voice lives at core/voice-profile.yml and is captured by the voice-interview skill. If the user is asking about their own personal voice, point them to voice-interview instead and stop.
Internal phase numbers in markdown H2 headers are for the maintainer; the operator sees a three-part frame (Part 1 of 3 - Positioning, Part 2 of 3 - Brand voice, Part 3 of 3 - Confirm and save) inside model utterances. Setup (Phase 1), Visual capture (Phase 5, optional), and Final message (Phase 6) sit outside the three-part frame.
Cross-skill asymmetry note: this skill has 6 phases. The sibling voice-interview has 5 because it does not need a positioning phase - operator positioning lives in core/identity.md (captured by founder-os-setup). Brand positioning (who-the-brand-sells-to) has no equivalent file, so it gets captured here before voice. Do not collapse positioning into voice when editing this skill.
Do not write `brands//voice.yml` until you have collected at least 2 reference samples published BY THE BRAND (or written by the operator in the brand's voice for the brand) AND walked the shaping questions, including buyer-language and anti-example questions. Samples are the ground truth.
Do not write brands/<slug>/positioning.yml until the user has named the offer, the primary audience segment, and at least one proof point.
Do not invent answers. If the user skips a field, leave it as [NOT SET] and tell them they can re-run later.
Phase map - load the reference when you reach the phase
Run the phases in order. When you reach a heavy phase, read its reference file for the full question set, then execute it. Load only the phase you are in.
| Phase | What it does | Load |
|---|
| 1 | Setup - clarify scope, pick slug (inline below) | - |
| 2 | Brand positioning - Q1 to Q13 (offer, audience, promise, competitors, channels, archetype) |
