agentleFS
asospyasospy/asospy-agent-skills/skills/aso-audit/SKILL.md

aso-audit

Skill1 starsChanged 46 days agoMITView on GitHub

Audit an App Store or Google Play listing — title, subtitle or short description, description, keyword coverage, category, ratings, reviews and chart ranks — and return a checklist with prioritised fixes. Use when the user asks for an ASO audit, a listing review or how to rank better. Needs the ASOSpy MCP server.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Before rewriting a title, subtitle or description.

    line 11

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

ASO audit

When to use

  • "Audit my app's store listing", "how can X rank higher", "review my ASO".
  • Before rewriting a title, subtitle or description.

Inputs

InputDefaultNotes
ApprequiredAny identifier. A name that exists on both stores needs store.
CountryusThe storefront to audit (listing text and chart ranks).

Tools

get_app_detail, search_keywords, live_keyword_metrics, get_store_ranking_history, get_app_reviews, search_apps, search_ads (mode: "app_keywords", iOS only).

Workflow

  1. get_app_detail with country: title, subtitle / short description, description, category, ratingScore, ratingsCount, last update, size (Google Play only), price.
  2. Take 3–5 core terms from the title and subtitle. search_keywords for each: are they terms with real demand (applePopularity, volume)? For an iOS app audited outside the US, applePopularity is the US figure, so also check these terms with live_keyword_metrics (source: "apple", storefront: <country>). Use it the same way when a figure is missing or stale (old updatedAt / appleUpdatedAt). Each live lookup costs 3 quota units (1 when cached: true), and the tool allows 10 lookups per minute per workspace.
  3. search_keywords for the app's core use case (2–3 seeds) to find strong keywords the listing does not use.
  4. search_apps for the top 3 apps in the same category (sort: "installs") and compare their titles and subtitles with get_app_detail.
  5. get_store_ranking_history with country: where the app charts and how stable it is.
  6. get_app_reviews with sort: "lowest_rated", limit: 50: problems that pull the rating down.
  7. iOS: search_ads with mode: "app_keywords": keywords the app already appears on in Apple Search Ads.

Output

A checklist. For each area give a status (good / improve / missing), the finding, and the evidence:

  • Title (length, main keyword, brand)
  • Subtitle (iOS) or short description (Android)
  • Description (first lines, keyword use, readability)
  • Keyword coverage (strong keywords used vs. missing)
  • Category fit
  • Ratings and reviews (score, volume, recurring complaints)
  • Chart ranks (where, how stable)
  • Update frequency

Then the 5 most important fixes in order, each with the expected benefit.

Limitations

  • The audit cannot see screenshots, the icon, the preview video or the iOS hidden keyword field. Say so rather than guessing.
  • Keyword metrics: applePopularity from search_keywords is US App Store only; live_keyword_metrics measures other storefronts one keyword at a time, and those non-US values are not saved in ASOSpy. Google figures are not store search counts. measured: false from live_keyword_metrics means unknown, not 0.
  • Conversion rate, impressions and page views are not in the data.

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.