Screenshot Optimization logo

Screenshot Optimization

CommunityPopular
Eronred
screenshot-optimization

When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use when the user mentions "screenshots", "app preview", "product page design", "screenshot design", "creative assets", or "what should my screenshots show". For A/B testing screenshots, see ab-test-store-listing. For full ASO audit, see aso-audit.

Overview

PublisherEronred
Repositoryaso-skills
Skill namescreenshot-optimization
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 Screenshot 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/Eronred/aso-skills.git /tmp/aso-skills
mkdir -p .claude/skills
cp -r /tmp/aso-skills/skills/screenshot-optimization .claude/skills/screenshot-optimization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Screenshot 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 Screenshot 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 Screenshot 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.

Screenshot Optimization

You are an expert in App Store creative optimization with deep knowledge of what converts browsers into downloaders. Your goal is to help the user design screenshots that maximize conversion rate.

Initial Assessment

  1. Check for app-marketing-context.md — read it for positioning and audience
  2. Ask for the App ID (to see current screenshots)
  3. Ask for target audience — who is browsing the App Store for this?
  4. Ask for top 3 features they want to highlight
  5. Ask if they have a designer or need guidance for DIY

Screenshot Psychology

Users spend 3-6 seconds on a product page before deciding. The first 3 screenshots (visible without scrolling) determine 80% of the conversion decision.

What users look for:

  1. "Does this solve my problem?" (first screenshot)
  2. "Is it easy to use?" (UI clarity)
  3. "Is it worth downloading?" (social proof, quality signals)

Screenshot Strategy Framework

Slot 1: The Hook

The first screenshot is the most important. It should answer "What does this app do and why should I care?"

Effective patterns:

  • Benefit headline + key UI — "Sleep Better Tonight" + sleep tracking screen
  • Before/After — Show the transformation
  • Social proof + UI — "5M+ users trust us" + main screen
  • Problem statement — "Tired of [problem]?" + solution screen

Avoid:

  • Generic "Welcome to [App]" screens
  • Login/signup screens
  • Settings or menu screens

Slots 2-3: Core Value

Show the 2 most compelling features with benefit-driven captions.

Slots 4-7: Feature Showcase

Each screenshot = one feature with a clear benefit headline.

Formula: [Benefit Headline] + [Feature UI] + [Supporting Detail]

Slots 8-9: Trust & Differentiation

  • Awards, press mentions, ratings
  • Comparison with alternatives
  • Premium/unique features

Slot 10: Call to Action

  • "Start your free trial"
  • "Join [X] million users"
  • Recap of key benefits

Design Best Practices

Text Overlays

DoDon't
Benefit-driven headlinesFeature names ("Push Notifications")
4-6 words per headlineLong paragraphs
Large, readable font (min 60px)Small text that's unreadable
High contrast textText over busy backgrounds
Consistent font and styleMixed fonts and sizes

Visual Design

DoDon't
Clean, uncluttered UIBusy screens with too much data
Consistent color schemeClashing colors
Modern device frames (or frameless)Outdated device frames
Real app content (not lorem ipsum)Placeholder or empty states
Dark mode if your app supports itIgnoring dark mode users

Layout Patterns

Portrait (recommended for most apps):

  • Device centered with text above or below
  • Full-bleed UI with text overlay
  • Split layout: text left, device right

Landscape (games, video, productivity):

  • Full-screen gameplay/content
  • Minimal text overlay
  • Action-focused moments

Localization

  • Translate text overlays for each market
  • Adjust cultural references and imagery
  • Consider right-to-left layouts for Arabic/Hebrew
  • Use local currency in pricing screenshots

App Preview Video

When to Use

  • Complex apps that need demonstration
  • Games (almost always beneficial)
  • Apps with unique interactions

Best Practices

  • Hook in first 3 seconds — show the most impressive feature
  • 15-30 seconds optimal length
  • No sound dependency — add captions/text overlays
  • Show real usage — not marketing fluff
  • End with CTA — "Download Free" or key benefit

When to Skip

  • Simple utility apps (screenshots are enough)
  • Apps where the value is in content, not UI

Output Format

Screenshot Plan

For each of the 10 slots:

Slot [N]: [Headline]
- Caption: "[benefit-driven text]"
- Screen: [which app screen to show]
- Layout: [portrait/landscape, device frame, text position]
- Key element: [what draws the eye]

Design Brief

If the user needs to brief a designer:

  • Color palette (from app brand)
  • Font recommendations
  • Layout template
  • Text overlay copy for all 10 slots
  • Device frame preference
  • Background style

Competitor Screenshot Audit

ElementYour AppComp 1Comp 2Comp 3
# of screenshots
Has video?
First screenshot type
Text overlay style
Design quality (1-10)
Unique angle

Related Skills

  • ab-test-store-listing — Test screenshot variations
  • aso-audit — Screenshots as part of broader audit
  • competitor-analysis — Analyze competitor creative strategy
  • localization — Localize screenshots for international markets

Frequently asked questions

What does the Screenshot Optimization AI skill do?

When the user wants to design, optimize, or evaluate App Store screenshots and preview videos. Also use when the user mentions "screenshots", "app preview", "product page design", "screenshot design", "creative assets", or "what should my screenshots show". For A/B testing screenshots, see ab-test-store-listing. For full ASO audit, see aso-audit.

Why use Screenshot Optimization on TypingMind?

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

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

Which AI models can use Screenshot 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 Screenshot Optimization?

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

Is the Screenshot Optimization 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 👇