App Store Optimization logo

App Store Optimization

Organization
TerminalSkills
app-store-optimization

Optimize mobile app listings for discovery and conversion in Apple App Store and Google Play. Use when tasks involve ASO keyword research, title and subtitle optimization, screenshot and preview video design, A/B testing store listings, review management, localization for international markets, tracking keyword rankings, or improving download conversion rates. Covers both iOS and Android store algorithms and best practices.

Overview

PublisherTerminalSkills
Repositoryskills
Skill nameapp-store-optimization
Stars
155
Forks
21
Bundled files
1
LicenseApache-2.0
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the App Store Optimization 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/TerminalSkills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/app-store-optimization .claude/skills/app-store-optimization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Store Optimization 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 Store Optimization 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 Store Optimization 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 Store Optimization (ASO)

Overview

Optimize mobile app visibility and conversion in App Store and Google Play. Cover keyword research, metadata optimization, creative assets, ratings management, and localization.

Instructions

How store algorithms work

Apple App Store indexes: App Name (30 chars, highest weight), Subtitle (30 chars), Keyword field (100 chars, hidden), In-App Purchase names, Developer name. Apple does NOT index the description for search.

Google Play indexes: App Title (30 chars, highest weight), Short Description (80 chars), Long Description (4000 chars, 2-5% keyword density), Developer name, Package name. Google also factors engagement metrics: install velocity, retention, crash rate, uninstall rate.

Keyword research

  1. Seed list: Features, use cases, competitor names, problem words
  2. Expand: Use autocomplete in both stores
  3. Validate: Check volume and difficulty (AppTweak, Sensor Tower, AppFollow)
  4. Prioritize: Score each on volume × relevance / difficulty
  5. Map: Assign keywords to metadata fields by priority

Keyword placement:

App Store (iOS):
- App Name (30 chars): Top 2-3 keywords, natural reading
- Subtitle (30 chars): Supporting keywords, value prop
- Keyword field (100 chars): Everything else, no duplicates across fields
- Comma-separated, no spaces. Singular OR plural (Apple matches both)
- Don't include "app" or category name. Don't use competitor brands.

Google Play:
- Title (30 chars): Primary keyword + brand
- Short Description (80 chars): Key features with keywords
- Long Description (4000 chars): Natural usage, 2-5% density, repeat 3-5x

Store listing creative assets

Screenshots are the single biggest conversion factor. Design principles:

  • First 3 screenshots visible without scrolling — strongest value props here
  • Each screenshot = one clear message (feature + benefit)
  • Large, readable text overlay
  • Sequence: Hero shot → Core feature → Unique differentiator → Secondary feature → Social proof

Preview video: iOS 15-30s (autoplays muted), Android 30s-2min (YouTube). Start with the wow moment, no long intros.

Icon: Recognizable at 16×16px, single focal element, avoid text, A/B test variations.

A/B testing store listings

Google Play Experiments: Test up to 5 variants (icon, screenshots, descriptions). Minimum 7 days, recommend 14 days.

Apple Product Page Optimization: Test up to 3 treatments (icon, screenshots, preview video). Cannot test title/subtitle. 90-day limit.

Priority order: Screenshots → Icon → Short description/subtitle → Preview video.

Ratings and reviews

Each 0.5-star increase improves conversion by 10-20%. Apps below 4.0 lose significant traffic.

In-app review prompts: Use native review API. Trigger after positive actions (completed goal, saved money). Pre-qualify: ask "Are you enjoying [App]?" — if yes, show review; if no, route to feedback form. Max 3 times per year (iOS enforced).

Responding: Reply to all negative reviews within 24-48 hours. Be specific about fixes. Never argue or be defensive.

Localization

Localizing metadata (not the app) is the fastest ASO win. High-impact locales: Spanish, Portuguese (Brazil), Japanese, German, French, Korean.

Localization is NOT translation — research keywords in each locale separately. Direct translations often aren't what locals search for.

Monitoring

Track weekly: keyword rankings (top 10 with position changes), category ranking, impressions, page view → install rate (benchmark: 25-35%), impression → install rate (benchmark: 3-8%), Day 1 retention, crash rate, current rating and trend.

Examples

Optimize an iOS app listing for more downloads

prompt
Our meditation app "ZenFlow" has 2,000 daily downloads but a 22% conversion rate from page views. Current title: "ZenFlow". We rank for "meditation" (#45) and "sleep sounds" (#78). Optimize our App Store metadata — title, subtitle, and keyword field — to improve keyword rankings and conversion. Research what top competitors in the meditation category use.

Plan a localization strategy for Google Play

prompt
Our fitness app has 100K downloads in the US and we want to expand internationally. Identify the top 5 markets by opportunity (considering competition, ARPU, and mobile fitness trends), then create localized metadata for each — not direct translations, but locally researched keywords and culturally adapted screenshots.

Design a screenshot A/B test

prompt
Our productivity app's screenshots haven't been updated in 8 months and conversion is declining. Design 3 screenshot variants to A/B test on Google Play. Include the messaging strategy, visual approach, and success metrics for each variant. Our current conversion rate from page view to install is 28%.

Guidelines

  • Always deduplicate keywords across title, subtitle, and keyword field on iOS — Apple deduplicates automatically
  • Use singular or plural forms but not both on iOS (Apple matches both)
  • Never include competitor brand names in the keyword field — risk of rejection
  • Update screenshots and metadata at least every 3-6 months to avoid conversion decline
  • Always pre-qualify users before showing the native review prompt
  • Respond to negative reviews with specific fix information, never defensively
  • Track keyword rankings weekly and iterate metadata based on position changes

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the App Store Optimization AI skill do?

Optimize mobile app listings for discovery and conversion in Apple App Store and Google Play. Use when tasks involve ASO keyword research, title and subtitle optimization, screenshot and preview video design, A/B testing store listings, review management, localization for international markets, tracking keyword rankings, or improving download conversion rates. Covers both iOS and Android store algorithms and best practices.

Why use App Store Optimization on TypingMind?

Because you install it once and use it with any model. App Store Optimization 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 Store Optimization in TypingMind?

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

Which AI models can use App Store Optimization?

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 Store Optimization?

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

Is the App Store Optimization AI skill free?

Yes. It is published on GitHub by TerminalSkills under the Apache-2.0 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 👇