app-icon-optimization

app-icon-optimization is a skill for Claude Code from Eronred/aso-skills. It costs 103 tokens per session (1,456 once invoked), scanned A, original, MIT.

A guide for designing, reviewing, and A/B testing mobile app icons for app-store search and browsing. A/B testing compares different versions to see which performs better.

In plain words
What is it for?
Use it to create icon variants, check readability and contrast, and improve tap-through and conversion from App Store listings.
Why use it?
It focuses attention on how an icon appears at small sizes and how often people tap the app after seeing it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aso-skills plugin — 40 skills shipped together

Good fit Use it to create icon variants, check readability and contrast, and improve tap-through and conversion from App Store listings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eronred/aso-skills/app-icon-optimization
About the project

ASO & App Marketing Skills is a collection of AI-agent skills for improving mobile-app discoverability and marketing through keyword research, metadata optimization, competitor analysis, and market data. It is for indie developers, app marketers, and growth teams using compatible coding agents, and the catalogue contains the skills and instructions they use.

Eronred/aso-skills · 1,835 stars · on GitHub · appeeky.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Eronred/aso-skills --skill app-icon-optimization
Clone the repo
git clone --depth 1 https://github.com/Eronred/aso-skills

Made for: Claude Code.

Or install aso-skills, the plugin that ships this one along with the rest of its 40 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for app-icon-optimization

README.md
[![agentmods](https://agentmods.dev/badge/skills/eronred/aso-skills/app-icon-optimization/github.svg)](https://agentmods.dev/skills/eronred/aso-skills/app-icon-optimization)
Your own site
<a href="https://agentmods.dev/skills/eronred/aso-skills/app-icon-optimization"><img src="https://agentmods.dev/badge/skills/eronred/aso-skills/app-icon-optimization/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for app-icon-optimization

Your own site · 80×15
<a href="https://agentmods.dev/skills/eronred/aso-skills/app-icon-optimization"><img src="https://agentmods.dev/badge/skills/eronred/aso-skills/app-icon-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 22 Mar 2026
  • Snyk pass 22 Mar 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.01456
Opus 5 $0.00051 $0.00728
Sonnet 5 $0.00021 $0.00291
Haiku 4.5 $0.00010 $0.00146

Measured 9d ago against content hash c40d933fe5ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

app-icon-optimization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

skills/app-icon-optimization/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Icon Optimization

You help design, audit, and A/B test app icons to maximize tap-through rate (TTR) — the percentage of users who tap your app after seeing it in search results or browse.

Why the Icon Is Your Most Impactful Asset

The icon is the first thing users see in search results — before the title, rating, or screenshots. A compelling icon can lift TTR by 20–40% with no other changes. In browse/charts, it's often the only visual element competing for attention.

Icon Design Principles

1. Simplicity at Small Size

Icons render at 60×60pt (iPhone search results). At that size, detail disappears.

  • Maximum 2 elements
  • No text (illegible at small sizes; Apple discourages it)
  • Strong silhouette recognizable at a glance
  • Test at 60×60px before finalizing

2. Color Contrast Against the App Store Background

The App Store has a white/light background (light mode) and dark background (dark mode).

  • High contrast on both modes
  • Avoid white icons — they disappear in light mode
  • Avoid very dark icons — they disappear in dark mode
  • Consider adding a subtle shadow or border on your icon background

3. Category Visual Language

Match and differentiate from your category norms:

Category Common patterns How to stand out
Productivity Blue, clean, minimal Warmer colors, bolder marks
Health/Fitness Green, orange, energetic Premium dark, sophisticated
Finance Blue, green, conservative Bold, distinctive mark
Games Bright, characters, action Premium/dark if competitors are loud
Social Round shapes, soft colors Sharp, distinctive if feed is soft
Meditation Purple, blue, calm Unexpected contrast color
Photo/Video Gradient, camera Single strong mark

Rule: Look at your top 20 competitors' icons. Then design to be immediately distinguishable.

4. Recognizable Mark

The icon needs a single, memorable mark — not a scene or a composition. Ask:

Read the full file on GitHub · 171 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 171 lines · 103 tokens per session scan A c40d933fe5ab

Subscribe to this mod's changes

app-icon-optimization is a skill published in the GitHub repository Eronred/aso-skills (1,835 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 1,456 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.