ssheleg/super-ux / plugins/super-ux/skills/brand-voice
brand-voice
VerifiedUse when defining or checking how a product speaks: tone of voice, terminology, canonical facts, register. Triggers: "tone of voice" / "тон оф войс", "brand voice" / "голос бренда", "брендбук", "наша терминология". Not for writing the text (copywriting). Refusal phrase "no brand" / «без бренда».
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.8 KB |
| references/ai-tells.md | markdown | 20.6 KB |
| references/brand-contract.md | markdown | 25.4 KB |
| references/channel-playbooks.md | markdown | 20.0 KB |
| references/hooks.md | markdown | 26.4 KB |
| references/localization.md | markdown | 5.2 KB |
| references/marketing-copy.md | markdown | 8.1 KB |
| references/research-outliers.md | markdown | 5.4 KB |
| references/seo-aeo-safety.md | markdown | 9.9 KB |
| references/store-copy.md | markdown | 7.4 KB |
| references/surface-registers.md | markdown | 9.1 KB |
| references/system-map.md | markdown | 12.4 KB |
| references/video-script.md | markdown | 14.6 KB |
| references/voice-packs.md | markdown | 15.9 KB |
| templates/brand/README.md | markdown | 2.3 KB |
| templates/brand/channels.md | markdown | 4.2 KB |
| templates/brand/copy-brief.md | markdown | 187 B |
| templates/brand/facts.md | markdown | 1.3 KB |
| templates/brand/locale.md | markdown | 2.2 KB |
| templates/brand/strings.md | markdown | 1.7 KB |
| templates/brand/terminology.md | markdown | 1.2 KB |
| templates/brand/voice.md | markdown | 2.2 KB |
references/store-copy.md
View on GitHub# Store listings: App Store, Google Play, RuStore and Meta Horizon
Field limits, indexing rules and craft for the store surfaces. Field
values live in the project's `channels.md`; the limits below are what the
platforms enforce, and `B040` checks copy against them with the locale's
length coefficient applied.
## Contents
- [Field limits](#field-limits)
- [The iOS keyword field](#the-ios-keyword-field)
- [Title and subtitle](#title-and-subtitle)
- [Description](#description)
- [Screenshot captions](#screenshot-captions)
- [What's new](#whats-new)
- [Ratings and reviews](#ratings-and-reviews)
- [Localization](#localization)
*Platform limits checked 2026-10-07 against each store's own page (sources
under the table). Stores change them; re-verify before a listing rewrite
rather than trusting this table.*
## Field limits
| Field | App Store | Google Play | RuStore | Meta Horizon |
|---|---|---|---|---|
| Title | 30 | 30 | 30 (see note) | 40 |
| Subtitle | 30 | — | — | — |
| Short description | — | 80 | 80 | 500 |
| Keyword field | 100 | — | 5 search tags | — |
| Promotional text | 170 | — | — | — |
| Full description | 4000 | 4000 | 4000 | 1500 |
| What's new | 4000 | 500 | 5000 | — |
Sources, read 2026-10-07 from the rendered pages (RuStore's help is a
JavaScript shell; a summary of the raw HTML misreads it):
- [Google Play metadata policy](https://support.google.com/googleplay/android-developer/answer/9898842):
"Your app title must be 30 characters or less" (an earlier version of this
table said 50).
- **RuStore disagrees with itself on the name.** The
[publication help page](https://www.rustore.ru/help/developers/publishing-and-verifying-apps/app-publication)
says "не более 30 символов"; the
[ASO recommendations](https://www.rustore.ru/help/developers/publishing-and-verifying-apps/aso-recommendations)
say "до 50 символов", and the
[publishing API](https://www.rustore.ru/help/en/work-with-rustore-api/api-upload-publication-app/create-draft-version)
accepts `appName` up to 50. Write the name to 30: it passes every page.
The same API gives short 80, full 4000, `whatsNew` 5000; the help page gives
up to 5 search tags.
- [RuStore app requirements §6.4](https://www.rustore.ru/help/developers/publishing-and-verifying-apps/requirement-apps):
the name, descriptions and version history must not carry clickbait —
"лучший", "единственный", "запрещённый", "секретный", "самый" and the like —
and "официальный" must be provable. A name or listing that breaks this can be
refused at moderation.
- [Meta Horizon app metadata](https://developers.meta.com/horizon/resources/publish-app-metadata/)
(updated 2025-08-20): Name 40, Short description 500, Long description 1500.
[Meta Horizon asset guidelines](https://developers.meta.com/horizon/resources/asset-guidelines/)
(updated 2026-05-11), Screenshots: "No banners, badges, titles, or marketing
text" — a screenshot caption is a store-copy decision only on the stores that
allow one.
Two structural differences that change how each is written:
- **App Store has a hidden keyword field; Google Play indexes the
description.** So the App Store description is written entirely for humans,
while the Play description carries the terms as well, naturally, at the
density prose tolerates.
- **App Store keyword changes need a submission; promotional text does not.**
Promotional text is the only field that can be changed between releases,
which makes it the place for anything time-bound.
## The iOS keyword field
100 characters, and most listings waste a third of them.
- **No space after commas.** `task,todo,planner`, because each space is a
character bought for nothing.
- **No plurals — in English.** Both English forms are matched from the
singular; `reminders` costs a character for no reach. Matching of inflected
forms in other languages (Russian cases and numbers, for one) is not
documented by the store: check a form in the store's own search before
dropping it, rather than assuming the English rule carries over.
- **Nothing already in the title or subtitle.** Those are indexed at higher
weight; repeating them here spends the field twice.
- **No competitor brand names.** Not a style preference: it is grounds for
rejection.
- **Singular concepts, comma-separated**, ordered by relevance. The field is
a bag of terms, not a phrase.
These four rules are `B041`.
```
✗ task manager, todo list, productivity app, daily planner, reminder app
✓ task,todo,checklist,reminder,organize,daily,planner,schedule,deadline,goal
```
The first spends 69 characters on eight terms, several already in the title.
The second fits eleven distinct terms in 70.
## Title and subtitle
The title carries the brand plus the single strongest term. The subtitle
carries the benefit, in the user's words, with the secondary term.
```
✗ MyTasks
✗ MyTasks - The Best Task Management App For Busy Professionals
✓ MyTasks: Todo List & Planner
```
Neither field is a place for a sentence. Read them together, because they
appear together everywhere in the store.
## Description
The first two or three lines are visible before "more". Almost nobody
expands. Write the opening as if it were the whole listing.
1. **Opening.** The user's problem, then what the app does about it, then
one piece of proof. No throat-clearing, no company history.
2. **Benefits.** Five short bullets, outcome-first. Not a feature dump.
3. **Proof.** Rating, install count, a named award or press mention. Every
figure traceable to `facts.md`.
4. **Close.** The next step and the reassurance that removes the hesitation
(`no account needed`, `free to try`, `cancel anytime`).
Keyword density above the `B051` threshold reads as stuffing to the store's
own review as well as to `brand_lint.py`.
## Screenshot captions
The caption is read before the screenshot is understood, so it carries the
value, not the label.
```
✗ Task List Feature (names the UI)
✗ Create Task Lists (names the action)
✓ Never miss a deadline (names the outcome)
```
First screenshot does the work of a headline; the rest tell a sequence. Five
to seven is the practical range.
## What's new
Play truncates at 500 characters, so the first line has to carry the release.
Write what changed for the user; the changelog rule from
[channel-playbooks.md](channel-playbooks.md) applies unchanged. "Bug fixes
and performance improvements" as the entire entry is a wasted surface that
users do read.
## Ratings and reviews
- The prompt goes after a success moment, never on launch and never during a
failure. A prompt shown at the wrong moment converts a neutral user into a
one-star.
- Respond to reviews in the product's voice, at the register of
`settings and legal`: plain, specific, no defensiveness, no humor.
- A review naming a bug that is now fixed deserves a reply saying which
version fixed it.
## Localization
Store listings are the surface where machine translation is most visible and
most damaging: the title and subtitle are short enough that a literal
translation reads as obviously foreign.
- Keyword research is redone per locale. Translated keywords are not
keywords, so see [localization.md](localization.md).
- Length coefficients bite hardest here, because these are the tightest
fields in the product. A 30-character title at a 1.3 coefficient has 23
characters of usable meaning.
- Screenshot captions are re-written, not translated.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |