---
name: brand-voice
description: "Captures a person's or brand's writing voice from samples into a reusable profile the other skills write in. Use when the user shares writing samples or says 'make it sound like me', 'match my voice', 'capture my writing style', or 'it doesn't sound like us'. For removing AI tells with no captured voice, see humanize. For niche and audience setup, see blog-context."
metadata:
  version: 0.3.0
---

# Brand voice

You capture a real person's or brand's writing voice from samples and turn it into a
reusable profile the other skills write in. A captured voice is the most valuable
context this collection holds. It overrides the generic "sound human" rules, because
the goal stops being "avoid AI tells" and becomes "sound like this specific writer."

You're done when the profile holds only traits the samples show, each with a do and a
tiny example, plus the verbatim anchor lines, and it's saved where the other skills
read it.

## Initial assessment

- Read `.agents/blog-context.md` if it exists. The Voice section is where the profile
  belongs; update it rather than starting a parallel file. For more than one author,
  use `.agents/voice-<name>.md` and note which posts use which.
- Get samples. Ask for three to five pieces the author actually wrote: posts, emails,
  threads, or a URL to their writing. More and longer is better, and varied beats
  similar: pieces on different topics and in different formats leave the voice as the
  only thing they share. Models copy whatever samples have in common, so five posts
  on one topic teach the topic, and a phrase that appears in two samples gets
  mistaken for a signature. Without samples you
  can't capture a voice, so don't invent one. If the user has none, capture stated
  preferences by interview and label the profile aspirational until real samples exist.
- Check you have enough. Count the words you actually have. Under about 400, capture only
  the traits the samples clearly support, label the profile "low-confidence (thin
  samples)" in the Voice section, and tell the user which dimensions you couldn't observe
  (usually transitions and how they sustain a long middle). Never fabricate a trait to
  reach a count.

## Method

1. Read for what repeats, not what it's about. Ignore the topics; study the moves.
   Read at least a few hundred words before you generalize, so you catch habits rather
   than one-off choices. Separate voice from belief: a trait must be a portable mechanic
   (sentence shape, person, punctuation, an opening move), not a claim only this author
   can make ("I've done this at four companies") or a topic-bound opinion. Capture the
   shape ("earns authority by citing specific reps"), never the specific claim, so the
   skills that write later never fabricate experience. Real stories, results, and
   stances you find in the samples are still valuable: record them in the
   "Experience and proof" section of `.agents/blog-context.md`, where writing skills
   may cite them as facts.
2. Profile the voice across concrete, imitable dimensions:
   - Rhythm: typical sentence length and how much it varies (short and punchy, long
     and winding, or a deliberate mix).
   - Formality and person: first or second person, contractions, slang, how close the
     writer stands to the reader.
   - Signature moves: rhetorical questions, fragments, asides, humor, analogies, direct
     address, strong openings. This is the fingerprint.
   - Vocabulary: plain or technical, the words they reach for, the words they avoid.
   - Stance: how much opinion, hedging, or certainty they show.
   - Structure: how they open, how they transition, how they land an ending.
   - Punctuation habits: dashes, parentheses, lists, emphasis. Note what they actually
     do, even when it breaks a generic rule.
3. Pull two or three short verbatim lines that are unmistakably theirs, each from a
   different sample, to anchor the profile in real examples. Pick lines whose move
   would work on any topic. A line that only lands because of a fact about the
   author ("Not the dishwasher" only works if they washed dishes somewhere) shows
   the move but invites imitation of the fact; put that fact in "Experience and
   proof" and choose a different anchor. A sample beats any
   adjective: writing skills imitate these lines far more reliably than they follow
   "conversational" or "witty."
4. If the author writes in clearly different modes (long posts versus short social
   posts, say), note per trait which mode it belongs to rather than averaging them.

## Output

If `.agents/blog-context.md` exists, replace its Voice section. If it doesn't, create it
from blog-context's [template](../blog-context/references/template.md) and fill in only
the Voice section, leaving the other sections as bracketed prompts for blog-context to
complete later. For more than one author, write `.agents/voice-<name>.md`. The Voice
section holds:

- As many copyable traits as the samples support (up to ten; fewer is fine for
  thin samples), each with a one-line do and a tiny example. For instance: "Opens with a
  blunt claim, not a windup. Do: 'Most cold brew advice is wrong.' Not: 'Cold brew has
  become increasingly popular.'"
- A short "keep these, they're intentional" list: quirks a generic pass would flag as
  tells but that belong to this voice (a habit of fragments, a signature dash, a
  rule-of-three). Name each one with the heading ai-tells.md uses for it ("Fragments
  posing as paragraphs," "Question, then a clipped answer," "Stacked threes," or "em
  dashes" for hard rule 1), and add the line "These win over ai-tells.md wherever they
  conflict." Matching names are what make humanize and article skip them instead of
  sanding them off. A voice can keep a habit, never a fabrication: the no-fabrication
  and chatbot-residue rules still apply.
- The two or three verbatim anchor lines, with the note "Imitate the move, never
  reuse the line," so writing skills don't paste them into every post.

Confirm the path, then tell the user that article, humanize, and the rest now write in
this voice and that it overrides the generic anti-AI rules wherever they conflict.

## Related skills

blog-context · humanize · house-style · article
