app-store-screenshots

Создание скриншотов для App Store и Google Play с точными спецификациями платформ. Охватывает размеры для iOS/Android, порядок в галерее, макеты устройств и превью-видео. Используется для: оптимизации в магазинах приложений, ASO, скриншотов приложений, превью приложений, оформления в Play Store. Триггеры: скриншоты для магазина приложений, aso, оптимизация в магазине приложений, скриншоты для Play Store, превью приложения, оформление приложения, скриншоты для iOS, скриншоты для Android, изображения приложения, макет приложения, макет устройства, галерея приложения, оформление в магазине

npx skills add https://github.com/halt-catch-fire/skills --skill app-store-screenshots

Install the belt CLI skill: npx skills add belt-sh/cli

App Store Screenshots

Create app store screenshots and preview videos via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate a device mockup scene
belt app run falai/flux-dev-lora --input '{
  "prompt": "iPhone 15 Pro showing a clean modern app interface with analytics dashboard, floating at slight angle, soft gradient background, professional product photography, subtle shadow, marketing mockup style",
  "width": 1024,
  "height": 1536
}'

Platform Specifications

Apple App Store (iOS)

DeviceDimensions (px)Required
iPhone 6.7" (15 Pro Max)1290 x 2796Required
iPhone 6.5" (11 Pro Max)1284 x 2778Required
iPhone 5.5" (8 Plus)1242 x 2208Optional
iPad Pro 12.9" (6th gen)2048 x 2732If iPad app
iPad Pro 11"1668 x 2388If iPad app
  • Up to 10 screenshots per localization
  • First 3 screenshots are visible without scrolling (critical)
  • Formats: PNG or JPEG (no alpha/transparency for JPEG)

Google Play Store (Android)

SpecValue
Min dimensions320 px (any side)
Max dimensions3840 px (any side)
Aspect ratio16:9 or 9:16
Max screenshots8 per device type
FormatsPNG or JPEG (24-bit, no alpha)
  • Feature graphic: 1024 x 500 px (required for featuring)
  • Promo video: YouTube URL (optional but recommended)

The First 3 Rule

80% of App Store impressions show only the first 3 screenshots (before the user scrolls). These three must:

  1. Communicate the core value proposition
  2. Show the best feature/outcome
  3. Differentiate from competitors

Screenshot Gallery Order

PositionContentPurpose
1Hero — core value, best featureStop the scroll, communicate what the app does
2Key differentiatorWhat makes you unique vs competitors
3Most popular featureThe thing users love most
4Social proof or outcomeRatings, results, testimonials
5-8Additional featuresSupporting features, settings, integrations
9-10Edge casesSpecialized features for niche users

Screenshot Styles

1. Device Frame with Caption

The standard: device mockup showing the app, caption text above/below.

┌──────────────────────────┐
│   "Track Your Habits     │  ← Caption (benefit-focused)
│    Effortlessly"         │
│                          │
│   ┌──────────────────┐   │
│   │                  │   │
│   │   App Screen     │   │  ← Actual app UI in device frame
│   │   Content        │   │
│   │                  │   │
│   │                  │   │
│   └──────────────────┘   │
│                          │
└──────────────────────────┘

2. Full-Bleed UI (No Device Frame)

The app UI fills the entire screenshot. Works for immersive apps.

3. Lifestyle Context

The device shown in a real-world context (person holding phone, on desk, etc.).

4. Feature Highlight with Callouts

UI screenshot with arrows/circles pointing to specific features.

Caption Writing

Rules

  • Max 2 lines of text
  • Benefit-focused, not feature-focused
  • 30pt+ equivalent font size (must be readable in store)

Examples

❌ Feature-focused:
"Push Notification System"
"Calendar View with Filters"
"Data Export Functionality"

✅ Benefit-focused:
"Never Miss a Deadline Again"
"See Your Week at a Glance"
"Share Reports in One Tap"

Generating Screenshots

Hero Screenshot (Position 1)

# Clean device mockup with hero feature
belt app run falai/flux-dev-lora --input '{
  "prompt": "modern iPhone showing a beautiful fitness tracking app with activity rings and workout summary, device floating at slight angle against soft purple gradient background, professional product shot, clean minimal composition, subtle reflection",
  "width": 1024,
  "height": 1536
}'

Feature Highlight

# Feature callout style
belt app run bytedance/seedream-4-5 --input '{
  "prompt": "app store screenshot style, iPhone showing a messaging app with AI writing suggestions highlighted, clean white background, subtle UI callout arrows, professional marketing asset, modern design",
  "size": "2K"
}'

Lifestyle Context

# Device in real-world setting
belt app run falai/flux-dev-lora --input '{
  "prompt": "person holding iPhone showing a cooking recipe app, kitchen background with ingredients, warm natural lighting, over-the-shoulder perspective, lifestyle photography, authentic feeling",
  "width": 1024,
  "height": 1536
}'

Before/After

# Split comparison
belt app run infsh/stitch-images --input '{
  "images": ["before-screenshot.png", "after-screenshot.png"],
  "direction": "horizontal"
}'

Preview Videos

Apple App Store

SpecValue
Duration15-30 seconds
OrientationPortrait or landscape (match app)
AudioOptional (loops silently in store)
FormatH.264, .mov or .mp4

Google Play

SpecValue
SourceYouTube URL
Duration30s-2min recommended
OrientationLandscape preferred

Preview Video Structure

SegmentDurationContent
Hook0-3sShow the core outcome/wow moment
Feature 13-10sDemonstrate top feature in action
Feature 210-18sSecond key feature
Feature 318-25sThird feature or social proof
CTA25-30sEnd screen with app icon
# Generate preview video scenes
belt app run google/veo-3-1-fast --input '{
  "prompt": "smooth screen recording style, finger tapping on a modern mobile app interface, swiping between screens showing charts and data visualizations, clean UI transitions, professional app demo"
}'

Localization

Each language gets its own set of screenshots. Priorities:

MarketLocalization Level
Primary marketsFull: new screenshots + translated captions
Secondary marketsTranslated captions, same screenshots
OtherEnglish defaults

Key localization markets: English, Japanese, Korean, Chinese (Simplified), German, French, Spanish, Portuguese (Brazilian)

A/B Testing (Google Play)

Google Play Console supports store listing experiments:

  • Test different screenshot orders
  • Test with/without device frames
  • Test different captions
  • Test different color schemes
  • Run for 7+ days with 50%+ traffic for significant results

Common Mistakes

MistakeProblemFix
Settings screen as screenshotNobody cares about settingsShow core value, not infrastructure
Onboarding flow screenshotsShows friction, not valueShow the app in-use state
Too much textUnreadable in storeMax 2 lines, 30pt+ font
Wrong dimensionsRejected by storeUse exact platform specs
All screenshots look the sameNo reason to scrollVary composition and content
Feature-focused captionsDoesn't communicate benefit"Never Miss a Deadline" > "Push Notifications"
Outdated UILooks abandonedUpdate screenshots with each major release
No hero screenshotWeak first impressionPosition 1 = your best shot

Checklist

  • Correct dimensions for target platform
  • First 3 screenshots communicate core value
  • Captions are benefit-focused, max 2 lines
  • No onboarding or settings screens
  • Preview video is 15-30s with hook in first 3s
  • Localized for top markets
  • Feature graphic (1024x500) for Google Play
  • Screenshots updated for current app version
  • A/B test variant prepared

Related Skills

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: belt app list

Больше skills от halt-catch-fire

ai-image-generation
halt-catch-fire
We need to translate the given text from English to Russian. The text describes an agent skill for AI image generation. We must preserve the name "ai-image-generation" but it's not in the text, so we don't include it. We preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. Translate the entire <text> content. The text: "Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to..." Translate
creativemediaimage
ai-video-generation
halt-catch-fire
Генерируйте AI-видео с помощью Google Veo, Seedance 2.0, HappyHorse, Wan, Grok и 40+ моделей через CLI inference.sh. Модели: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Возможности: текст-в-видео, изображение-в-видео, референс-в-видео, редактирование видео, липсинк, анимация аватаров, апскейлинг видео, звук фоли. Используйте для: видео для соцсетей, маркетинговый контент, объясняющие видео, демонстрации продуктов, AI-аватары. Триггеры: генерация видео, ai video,...
creativevideomedia
twitter-automation
halt-catch-fire
Автоматизация Twitter/X с публикацией, вовлечением и управлением пользователями через CLI inference.sh. Приложения: x/post-tweet, x/post-create (с медиа), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Возможности: публикация твитов, планирование контента, лайки, ретвиты, отправка личных сообщений, подписка на пользователей, получение профилей. Используется для: автоматизации социальных сетей, планирования контента, ботов вовлечения, роста аудитории, X API. Триггеры: twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x...
marketingapicommunication
ai-avatar-video
halt-catch-fire
Создавайте AI-аватары и видео с говорящими головами через CLI inference.sh. Рекомендуется: P-Video-Avatar (самый быстрый, дешёвый, встроенный TTS). Также: OmniHuman, Fabric, PixVerse. Аудио: Inworld TTS-2 (100+ языков, управление эмоциями для персонажей), ElevenLabs, Kokoro. Возможности: аватары, управляемые аудио, текст-в-аватар, видео с синхронизацией губ, генерация говорящих голов, виртуальные ведущие, UGC-контент. Используйте для: AI-ведущие, обучающие видео, виртуальные инфлюенсеры, дубляж, маркетинговые видео, UGC-реклама, игровые аватары,...
videocreativemedia
agent-browser
halt-catch-fire
Автоматизация браузера для AI-агентов через inference.sh. Навигация по веб-страницам, взаимодействие с элементами с помощью @e refs, создание скриншотов, запись видео. Возможности: веб-скрапинг, заполнение форм, клики, ввод текста, перетаскивание, загрузка файлов, выполнение JavaScript. Используется для: веб-автоматизации, извлечения данных, тестирования, просмотра страниц агентом, исследований. Триггеры: браузер, веб-автоматизация, скрапинг, навигация, клик, заполнение формы, скриншот, просмотр веб-страниц, playwright, headless-браузер, веб-агент, серфинг в интернете, запись видео
browser-automationweb-scrapingtesting
web-search
halt-catch-fire
Веб-поиск и извлечение контента с помощью Tavily и Exa через CLI inference.sh. Приложения: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Возможности: поиск на основе ИИ, извлечение контента, прямые ответы, исследования. Используется для: исследований, RAG-пайплайнов, проверки фактов, агрегации контента, агентов. Триггеры: веб-поиск, tavily, exa, search api, извлечение контента, исследования, интернет-поиск, ИИ-поиск, поисковый ассистент, веб-скрапинг, rag, альтернатива perplexity
researchweb-scrapingapi
infsh-cli
halt-catch-fire
Запускайте 250+ AI-приложений через CLI inference.sh — генерация изображений, создание видео, LLM, поиск, 3D, автоматизация Twitter. Модели: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter и многие другие. Используйте при запуске AI-приложений, генерации изображений/видео, вызове LLM, веб-поиске или автоматизации Twitter. Триггеры: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
developmentapicreative
landing-page-design
halt-catch-fire
We need to translate the given text from English to Russian, preserving the name "landing-page-design" as it appears in the source? The instruction says: "Do not include the name unless it appears in the source text." The name "landing-page-design" is not in the <text> block. The <text> block contains the description. So we only translate the text inside <text>. Also preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. The text: "Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page..." Translate to Russian. Keep technical terms like "CTA", "above-the-fold