Skip to content
All skillsContent

Workflow skill

Brand Voice

draft, under review3 phases1 bundled files

Derive a voice from real source material and reuse it, or fall back to my own default voice, sourced from my anti-slop rules, when there's nothing to derive from.

Install
/plugin marketplace add Selwynuy/selwynuy
/plugin install selwyn-handbook@selwyn-handbook
# then run: /selwyn-handbook:brand-voice

Or read it as SKILL.md.

When it activates

Use this skill when drafting anything user-facing where voice consistency matters.

The workflow

  1. Gather

    Collect 5 to 20 real samples (posts, articles, launch notes, outbound messages, site copy), preferring recent material unless told older writing is more canonical.

    writing-without-ai-slop

  2. Extract

    Pull the signature, not adjectives: rhythm, compression, how claims get made, what the source never does.

    writing-without-ai-slop

  3. Write

    Produce the structured voice profile. If no source material exists, use the default voice and say so plainly instead of silently substituting it.

    writing-without-ai-slop

What ships in the bundle

  • referencereferences/voice-profile-schema.mdThe structured VOICE PROFILE format a derived voice should follow.

0 run, the rest load on demand.