Brand Voice Keeper

---
name: brand-voice-keeper
description: Defines and enforces a consistent brand voice and visual identity across every post and platform. It distills voice into tone attributes, a do/don't lexicon, and rhythm rules, extracts that voice from sample posts, then runs any draft through a pass/fail consistency checklist. Use when the user asks about brand voice, tone, staying "on-brand," "does this sound like me," a style guide, or visual consistency. Pairs with onboarding-brand-brief. Works with any capable model.
---

# Brand Voice Keeper

A brand is recognized before it is read — the same voice and look across dozens of posts is what turns scattered content into a memorable presence. Voice is not vibes; it is a small set of enforceable rules: how you sound (tone), the words you use and refuse (lexicon), and how the text moves (rhythm and formatting). Define it once from real examples, then gate every draft against it. Consistency compounds; each on-brand post makes the next one recognizable.

## 1. Distill the voice
1. Pick 3-5 tone attributes as tension pairs, e.g. "warm but not saccharine," "expert but not academic," "playful but never flippant." Vague single words (friendly, professional) fail — force the "not."
2. Build a do/don't lexicon: 8-12 signature words/phrases to USE, 8-12 to BAN (jargon, clichés, filler like "in today's world," "game-changer").
3. Set rhythm rules: sentence length (short punchy vs. flowing), contractions yes/no, emoji policy (count + which), opener and CTA patterns, formatting (line breaks, lists, capitalization).

## 2. Extract voice from samples
1. Paste 3-5 of the user's best-performing or favorite posts.
2. Tag recurring moves: how they open, how they land a point, humor type, sentence cadence, punctuation quirks.
3. Draft the attributes + lexicon FROM those patterns, then confirm with the user before enforcing — never invent a voice they did not demonstrate.

## 3. Enforce with the checklist
1. Run every draft line-by-line against the Voice Guide below.
2. Mark each check PASS or FAIL with the offending snippet quoted.
3. Any FAIL = rewrite that element only, preserving meaning; do not rewrite passing lines.

## Output template
```
VOICE GUIDE
Tone attributes: <A but not X> | <B but not Y> | <C but not Z>
Use words: <8-12 words/phrases>
Ban words: <8-12 words/phrases>
Rhythm: sentences <short/mixed> | contractions <yes/no> | emoji <n + which> | opener <pattern> | CTA <pattern>
Visual: colors <hex primary/secondary/accent> | fonts <heading/body> | framing <thumbnail/cover style> | logo <placement>

CONSISTENCY CHECK — <draft title>
[ ] Tone matches all attributes ......... PASS / FAIL: "<snippet>"
[ ] No banned words .................... PASS / FAIL: "<snippet>"
[ ] Rhythm + formatting on-brand ....... PASS / FAIL: "<snippet>"
[ ] Opener + CTA follow pattern ........ PASS / FAIL: "<snippet>"
[ ] Emoji/punctuation within policy .... PASS / FAIL: "<snippet>"
[ ] Visual assets on-brand ............. PASS / FAIL: "<snippet>"
VERDICT: ON-BRAND / NEEDS FIX
Fixes: <only the failing elements, rewritten>
```

## Platform variants
Voice stays constant; register flexes. LinkedIn: fuller sentences, same lexicon. X/Threads: compressed, same banned words still banned. TikTok/Reels captions: most casual, but tone attributes still hold. Visuals travel across all: same color palette, font pairing, thumbnail template, and logo placement so the grid and feed read as one brand.

## Rules
- No voice without samples — extract from real posts, never guess.
- Attributes must include the "not" half; a word with no boundary is unenforceable.
- The ban list is stronger than the use list; one banned cliché fails the draft.
- Keep visual identity fixed: same 2-3 fonts, same palette, same thumbnail frame — change only with intent.
- On FAIL, rewrite the element, not the whole post; preserve the user's meaning.
- One voice per brand across all platforms; adjust register, never the identity.