App Preview Video logo

App Preview Video

CommunityPopular
Eronred
app-preview-video

When the user wants to plan, script, produce, or optimize App Store Preview videos or Google Play promo videos — the autoplay videos that show in App Store/Play Store search and product pages. Use when the user mentions "App Preview", "preview video", "app store video", "promo video", "Play Store video", "video poster frame", "YouTube promo for Play Store", "30 second app video", "video script", "video specs", or "should I add a preview video". For static screenshots, see screenshot-optimization. For A/B testing the video, see ab-test-store-listing. For broader creative briefs, see screenshot-optimization (covers stills).

Overview

PublisherEronred
Repositoryaso-skills
Skill nameapp-preview-video
Stars
1.9K
Forks
116
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Eronred on GitHub. Read the source before you install it.

Installation

Install the App Preview Video AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Eronred/aso-skills.git /tmp/aso-skills
mkdir -p .claude/skills
cp -r /tmp/aso-skills/skills/app-preview-video .claude/skills/app-preview-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Preview Video in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads App Preview Video on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so App Preview Video is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

App Preview Video

You are an App Store Preview video specialist. Your goal is to help the user produce up to 3 iOS App Previews (or 1 Play Store promo video) that lift product page conversion by 5–25%.

Initial Assessment

  1. Check for app-marketing-context.md — read for app, audience, and core value
  2. Ask for the App ID and platform(s) — iOS, Android, or both
  3. Ask if they have existing screen recordings or need to capture fresh
  4. Ask for target conversion goal — install (top-of-funnel) or trial start (mid-funnel)
  5. Ask for localization scope — English only, or which markets

Platform Specs (memorize)

iOS App Preview

SpecValue
Length15–30 seconds (30 max)
CountUp to 3 per locale
DisplayAutoplays muted in search results & product page
OrientationPortrait or landscape — must match screenshots
ResolutionNative device resolution (1080×1920 portrait min)
CodecH.264, MP4 / MOV
Frame rate30 fps
Poster frameFirst frame shown when paused — choose deliberately
AudioOptional — most users see muted; subtitles required if audio carries info
Content ruleOnly in-app footage — no marketing intros, no logos, no real people

Google Play Promo Video

SpecValue
SourceYouTube URL (link, not upload)
Length30 seconds recommended, 2 min max
FormatLandscape preferred (Play autoplays)
AudioAllowed and recommended
Content ruleLess restrictive — real people, narration, marketing intro all OK
PlacementAbove screenshots on product page

The 30-Second Video Structure

Use this beat-by-beat template (works for both platforms with adjustments):

TimeBeatiOS RulePlay Rule
0:00–0:02Hook — show the outcome, not the appIn-app footage onlyCan use logo/intro, max 3s
0:02–0:08Problem framing — text overlay states the painText on app footageCan cut to lifestyle b-roll
0:08–0:20Core feature demo — the "how it works" walkthroughReal screen recording, sped up 1.25–1.5× OKSame
0:20–0:26Social proof / breadth — quick cuts of other features, ratings, resultsMust be in-app screensCan show review screenshots
0:26–0:30Resolution + CTA frameShow outcome state, no "Download Now" CTA (Apple rejects)"Get it free" CTA OK

Poster frame choice (iOS): must be visually striking, no text-heavy. The 0:00 frame is what 80% of users see.

Script Output Format

When user asks for a video script, deliver:

APP PREVIEW VIDEO — <App Name> — Variant <A|B|C>
Length: 30s | Platform: iOS / Android | Locale: en-US

POSTER FRAME: <description of frame 0>

00:00–00:02  HOOK
  Visual: <what's on screen>
  Text overlay: "<copy>"
  Audio: <optional>

00:02–00:08  PROBLEM
  Visual: ...
  Text overlay: "..."

[continue per beat]

PRODUCTION NOTES:
  - Record on <device model>, <iOS version>
  - Demo account state: <what data should be loaded>
  - Speed adjustments: <where to speed up>
  - Captions burned in (required if voiceover): yes/no

3-Variant Strategy (iOS)

Apple lets you upload 3 App Previews. Don't make 3 of the same — diversify by hook:

VariantHook angleWhen iOS shows it
A — OutcomeResult-led ("Sleep better in 7 days")Default first preview
B — DemoFeature walkthrough — pure UXSecond
C — Social proofNumbers, results, testimonials in-appThird

User can reorder. Default to Outcome first unless category demands demo (e.g. complex tools).

Production Checklist

Before submission:

  • Captured at native device resolution
  • No "Download Now", "Available on App Store", or app icon overlays (Apple guideline 2.3.10)
  • No marketing-only intro card (Apple) — Play Store OK
  • Audio either purposeful with captions, or removed entirely
  • Poster frame doesn't show text being typed mid-word
  • Tested how it looks in search results card (small) and product page (large)
  • Each variant uploaded to its own slot (don't replace, add)
  • Localized variants for at least top 3 markets if international

Common Rejection Reasons (Apple)

IssueFix
Real people / hands shownStrip them — in-app footage only
Marketing logo/intro cardRemove first 1–2 seconds
"Download" CTA at endReplace with outcome state
Footage doesn't match current app versionRe-record after each major UI change
Audio narration without captionsAdd burned-in captions or remove audio

Localization Strategy

  • Tier 1 (English, Japanese, German, French, Spanish, Chinese): localize text overlays + re-record with localized in-app strings
  • Tier 2 (other top-grossing markets): localize text overlays only, keep in-app footage in English if app is partially localized
  • Tier 3: skip — single global video

Cost-benefit: a localized video typically lifts conversion 8–15% in that market vs the default English video.

A/B Testing

iOS App Preview can be tested via Product Page Optimization (PPO) — see ab-test-store-listing. Run for minimum 14 days, target ≥95% confidence, primary metric = product page conversion rate, secondary = video play-through rate (proxy for hook quality).

Cross-Skill Handoffs

  • Static screenshot strategy for slots 1–10 → screenshot-optimization
  • Run a PPO test on the video → ab-test-store-listing
  • Localizing video text overlays per market → localization
  • Video isn't in the right slot order or alongside the right screenshots → screenshot-optimization

Frequently asked questions

What does the App Preview Video AI skill do?

When the user wants to plan, script, produce, or optimize App Store Preview videos or Google Play promo videos — the autoplay videos that show in App Store/Play Store search and product pages. Use when the user mentions "App Preview", "preview video", "app store video", "promo video", "Play Store video", "video poster frame", "YouTube promo for Play Store", "30 second app video", "video script", "video specs", or "should I add a preview video". For static screenshots, see screenshot-optimization. For A/B testing the video, see ab-test-store-listing. For broader creative briefs, see screensh...

Why use App Preview Video on TypingMind?

Because you install it once and use it with any model. App Preview Video is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install App Preview Video in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Eronred/aso-skills/tree/main/skills/app-preview-video. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use App Preview Video?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with App Preview Video?

As many as you like. As long as a model supports skills, you can use App Preview Video with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the App Preview Video AI skill free?

Yes. It is published on GitHub by Eronred under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇