Este prompt gera o subtítulo, as palavras-chave, o texto promocional, a descrição e as notas de versão para um projeto Xcode atual. A estrutura segue o que o fastlane.org espera e pode ser usada imediatamente
You are a senior App Store Optimization (ASO) copywriter and localizer. Generate complete,
ready-to-upload App Store Connect metadata text files for THIS project's app, then deliver
them to me as a single ZIP file.
## 1. Learn the app from the project (do this first, do not guess)
Read and synthesize, in this priority order:
1. `fastlane/config/apps.yml` — take the app `name`, `platform`, `primary_locale`, and the
full `locales` list. If more than one app entry exists, use the one I name; if I named
none, use the first `ios` app and tell me which you picked.
2. `fastlane/config/aso.yml` — honor `app_positioning.default_tone` and any field limits.
3. `README.md`, any markdown file that contains "description" in it's name, anything under `docs/`, and `user_notes/aso_brief.md` if present.
4. Existing `fastlane/metadata/<primary_locale>/*.txt` (especially `description.txt`,
`name.txt`, `subtitle.txt`, `keywords.txt`) as ground truth for what the app actually does.
From these, form a short internal understanding: what the app does, its core features, who
it is for, and its key benefit. Do NOT invent features, prices, awards, or claims that the
source material does not support.
## 2. Files to produce, per locale
For EVERY locale listed for the app, produce exactly these five files:
- `description.txt`
- `subtitle.txt`
- `keywords.txt`
- `promotional_text.txt`
- `release_notes.txt`
## 3. Hard character limits (never exceed — count Unicode characters)
- subtitle.txt ≤ 30
- keywords.txt ≤ 100
- promotional_text.txt ≤ 170
- description.txt ≤ 4000
- release_notes.txt ≤ 4000
If `fastlane/config/aso.yml` specifies different `metadata_fields.<field>.max_length`
values, those override the numbers above. Use the space well but always stay under the cap.
## 4. Field-by-field rules
- description: Benefit-led and scannable. Front-load the single most important sentence —
the first ~2 lines are what users see before "more". Follow with concrete features from
the source material, short paragraphs or a tight bulleted list. Tone = the app's
configured tone (default: clear, useful, non-hype). No hype, no fake urgency, no emoji
spam, no unverifiable claims.
- subtitle: One punchy benefit or category line, ≤ 30 chars. Do NOT repeat the app name.
- keywords: Comma-separated list, ≤ 100 chars. CRITICAL FORMAT: NO space after the commas
(e.g. `grid,bot,crypto,trading` — never `grid, bot`). All lowercase. Do NOT include words
already present in the app name or subtitle (App Store indexes those separately, so
repeating them wastes space). No duplicate words, no plurals of a word already listed, no
competitor brand names or trademarks. Maximize distinct, relevant, high-intent terms; if
it won't fit, drop the least relevant term rather than truncating mid-word.
- promotional_text: One or two sentences of current, changeable messaging, ≤ 170 chars.
- release_notes: Concise, user-facing "what's new" (improvements, fixes, refinements),
≤ 4000. Keep it honest and generic unless the source material states specific changes.
## 5. Localization
- The primary locale is the source of truth; write it first.
- For every other locale, write NATIVE, idiomatic copy — genuinely translate and adapt for
that market. Do NOT output English text with a "localized" label, and do NOT machine-gloss.
- Re-check every limit AFTER translating (translations change length). Keyword lists must be
localized to real search terms in that language and still follow the no-space-after-comma
rule and the character cap.
## 6. Output / delivery
- Encode every file as UTF-8 plain text, content only (no markdown, no surrounding quotes),
ending with a single trailing newline.
- Lay them out mirroring Fastlane's structure, one folder per locale:
metadata_drafts/<locale>/description.txt
metadata_drafts/<locale>/subtitle.txt
metadata_drafts/<locale>/keywords.txt
metadata_drafts/<locale>/promotional_text.txt
metadata_drafts/<locale>/release_notes.txt
- Package the whole tree into ONE zip file named `aso_metadata_<app-target>_<date>.zip` and
give it to me as a downloadable file.
- After the zip, print a short verification table: locale, field, character count, and limit,
so I can confirm nothing is over. Flag any row that is within 5 characters of its limit.
Treat everything you produce as a DRAFT for my manual review before upload. Do not upload,
submit, or release anything.
Guia do prompt
Ideal para
Começar a partir de um prompt estruturado e reutilizável em vez de um chat em branco.
Adaptar o prompt aos seus próprios dados, mantendo intacta a intenção original.
Fluxos de trabalho relacionados com Software Development, Agents & Vibe Coding, Marketing & Social.
Como usar
Copie o modelo de prompt completo.
Substitua cada variável pelo seu próprio contexto ou escolha uma das opções sugeridas.
Cole o prompt concluído no ChatGPT, Claude, Gemini ou outro assistente de IA.
Exemplo de ponto de partida
You are a senior App Store Optimization (ASO) copywriter and localizer. Generate complete,
ready-to-upload App Store Connect metadata text files for THIS project's app, then deliver
them to me as a single ZIP file.
## 1. Learn the app from the project (do this first, do not guess)
Read and synthesize, in this priority order:
1. `fastlane/config/apps.yml` — take the app `name`, `platform`, `primary_locale`, and the
full `locales` list. If more than one app entry exists, use the one I name; if I named
none, use the first `ios` app and tell me which you picked.
2. `fastlane/config/aso.yml` — honor `app_positioning.default_tone` and any field limits.
3. `README.md`, any markdown file that contains "description" in it's name, anything under `docs/`, and `user_notes/aso_brief.md` if present.
4. Existing `fastlane/metadata/<primary_locale>/*.txt` (especially `description.txt`,
...
Como funcionam as variáveis
Sintaxe das variáveis
As variáveis ficam entre {{ e }} e seguem este padrão:
{{variable name: option1, option2, option3}}
Variáveis predefinidas
Uma seleção pode fazer referência a uma lista de variáveis predefinida usando colchetes. Aparecem em [laranja] e fornecem valores comuns, como cores, tons ou idiomas.
{{Tone: [tones]}}
Listas de seleção personalizadas
Também pode fornecer uma lista de opções em linha, separadas por vírgulas.
Dica: não precisa da app PUCO para usar estes prompts! Basta copiar o modelo e substituir cada secção {{…}} pelo seu próprio texto diretamente no ChatGPT, Claude, Gemini ou qualquer outro assistente de IA.
Prompts relacionados
Anticipate Critical Teacher Questions About My Work
Generates tough examiner-style questions with model answers that a critical teacher or reviewer might ask about a project thesis or topic in any subject including software projects.
Runs an agentic coding loop where the task, the verification method, and the completion criterion are selected independently, iterating until the external check passes.