agentleFS
Sign inStart free
milad-ahmdmilad-ahmd/agent-skills/skills/app-store-optimizer/SKILL.md

app-store-optimizer

Skill5 starsChanged 15 days agoMITView on GitHub

App Store Optimization (ASO) for the Apple App Store and Google Play, covering keyword research, title, subtitle, short description and keyword field within character limits, long description, screenshot captions and order, preview video script, localization, ratings prompts, review replies, and A/B tests. Use when the user asks to improve an app store listing, ASO, app keywords, screenshots, app descriptions, or app review responses.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look at competitors' titles and subtitles, App Store and Play search suggestions (the user pastes them or a tool fetches them), and review …

    line 16
  2. Distinctive:

    Write 3 options for the title, subtitle and short description.

    line 30
  3. Distinctive:

    Ask for a rating at a happy moment (after a success), using the native prompt APIs (SKStoreReviewController, Play In-App Review).

    line 40
  4. Distinctive:

    No fake reviews, incentivised ratings or misleading claims.

    line 48
  5. Distinctive:

    Update listings only through the user's own access (App Store Connect, Play Console, fastlane) and after their confirmation.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

App Store Optimizer 📱

Rank for the right searches, and turn page visitors into installs.

1. Inputs

The app, its category, target users, core features, competitors (3–5 apps), current listing text (or a store-listing*.md / fastlane/metadata in the repo), current ratings and reviews, and the target countries and languages.

2. Keyword research

Look at competitors' titles and subtitles, App Store and Play search suggestions (the user pastes them or a tool fetches them), and review language (the words real users use). Score each keyword on relevance (1–5), estimated competition and intent. Pick a primary keyword and 10–20 secondary ones.

3. Metadata (count the characters and show the counts)

FieldApple App StoreGoogle Play
Title / App name≤ 30 chars≤ 30 chars
Subtitle≤ 30 chars—
Short description—≤ 80 chars
Keyword field≤ 100 chars, comma-separated, no spaces, no repeats of title words—
Description≤ 4000 (not indexed for search, written for conversion)≤ 4000 (indexed: use keywords naturally)
Promotional text≤ 170 (updatable without release)—

Write 3 options for the title, subtitle and short description. Never stuff competitor brand names (it breaks store guidelines).

4. Screenshots and video

  • The first 2–3 screenshots decide most installs. Each one gets one benefit-led caption of 5 words or fewer, in large text.
  • Order: core value → top feature → social proof or result → differentiators. Provide captions and layout notes for each.
  • Preview video script (15–30 seconds): the app in use within the first 3 seconds, no long logo intro.

5. Ratings and reviews

Ask for a rating at a happy moment (after a success), using the native prompt APIs (SKStoreReviewController, Play In-App Review). Write reply templates for reviews: thank specifically, fix or explain, and invite them back. Mine the reviews for keywords and bugs.

6. Localize and test

Localize the metadata for the top markets (not just translate it; do keyword research per locale). A/B test with Apple Product Page Optimization and Google Play store listing experiments, changing one element at a time.

Rules

  • No fake reviews, incentivised ratings or misleading claims. Follow the App Store Review Guidelines and Google Play policies.
  • Update listings only through the user's own access (App Store Connect, Play Console, fastlane) and after their confirmation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free