Guide · Agent skill
How to use the App Store Listing Audit agent skill (aso)
Updated · written with AI from the project's own documentation and checked against our catalogue data
The aso skill is an agent skill that tells an AI agent how to audit an app's public App Store or Google Play listing. It is written for developers and marketers who want a structured review of why an app is not getting downloads. After this guide you will know what the skill does, how to install it, how to ask for an audit in plain language, and what to check before trusting the results.
App Store Listing Auditcoreyhaines31/marketingskills · MIT Download the skill Quick start
- 1Download the ZIP. Get the aso skill ZIP from this page.
- 2Unzip into a skills folder. Extract it to ~/.claude/skills/ for personal use or to .claude/skills/ inside a project.
- 3Or upload in the Claude apps. Go to Settings → Capabilities → Skills and upload the skill if you use the Claude apps.
- 4Find the listing URL. Copy the App Store or Google Play link for your app, or note the app name.
- 5Ask for an audit. Describe what you want in plain language, such as audit my listing, and include the URL.
- 6Review the scores and plan. Read the per-area scores and the prioritized list of changes.
- 7Check official data. Confirm figures such as ratings and last update date in App Store Connect or Play Console.
What is an agent skill and what does aso make the agent do?
An agent skill is a folder containing a SKILL.md file and supporting reference files. When a request matches the skill's description, the agent reads these instructions and follows them for that task.
Once installed, the aso skill lets the agent fetch a public App Store or Google Play listing and review its title, subtitle or short description, long description, screenshots, ratings, reviews and other fields against app store optimization best practices. It scores each area, adjusts expectations based on how well known the app is, and returns a prioritized list of changes aimed at discoverability and download conversion.
- Detects the store from the URL and fetches the listing page
- Scores dimensions such as title and subtitle, description, visual assets and ratings and reviews
- Classifies the app as Dominant, Established or Challenger before scoring, so well-known brands are not judged by the same rules as new apps
- Returns a prioritized action plan
How do you install the aso skill?
Download the ZIP from this page and unzip it. You can install it in one of two places. For your personal use across projects, unzip it into ~/.claude/skills/. For a single project, unzip it into that project's .claude/skills/ folder.
If you use the Claude apps, you can instead upload the skill under Settings → Capabilities → Skills.
- Personal install: ~/.claude/skills/
- Project install: .claude/skills/ inside your project folder
- Claude apps: Settings → Capabilities → Skills, then upload
How do you trigger the skill with a natural request?
You do not need a special command. Describe what you want in ordinary language. The skill's description lists trigger phrases such as 'ASO audit', 'app store optimization', 'audit my listing', 'why aren't people downloading my app' and 'compare my app to competitors'. Sharing a store URL and asking for improvements also works.
If you only give an app name, the agent is directed to search the web for the listing using site-restricted queries on apps.apple.com or play.google.com.
- Paste a URL and say: audit this listing and tell me what to fix
- Say: why aren't people downloading my app? Here is the link
- Say: compare my app to these two competitors on the store
What does the audit need from you and from the agent's tools?
The skill relies on a WebFetch tool to retrieve listing pages. A browser or screenshot tool is optional, used to assess visual assets such as icon quality, screenshot captions and preview video. If you do not have one, you can paste a screenshot of the listing into the chat. A web search capability is needed only when you give an app name instead of a URL.
Some data may be missing. Stores often render pages in the browser, so the fetch can return incomplete fields. The skill then notes the gaps and works with what is available, and may ask you to paste fields that are critical.
- WebFetch: needed to read the listing page
- Browser or screenshot tool: optional; you can paste a screenshot instead
- Web search: needed only for app-name lookups
What are the safety notes for scripts and network access?
The skill does not run scripts. It does use the network, because it fetches live store pages. The skill also tells the agent to treat fetched listing text and reviews as untrusted content and to ignore any instructions hidden in listing copy, reviews or page HTML.
Some results are also limited by design. The skill is not a source of official store data. It suggests checking App Store Connect or Play Console manually for information only those consoles show.
- No scripts are run by this skill
- Network access is used to fetch public listing pages
- Listing text and reviews are analyzed as data, not followed as instructions
- Official figures from App Store Connect or Play Console must be checked by you
What tips help you get useful results?
Give the agent context about your app and goals if you have it. The skill checks for a product marketing context file at .agents/product-marketing.md or .claude/product-marketing.md and reads it first if present. Be clear about which competitors you want compared, and say which platform matters most to you.
Treat the output as a prioritized set of recommendations, not guaranteed results. The skill is explicit that it gives advice based on best practices and benchmarks rather than measured outcomes.
- Name the store and country you care about
- Share competitor URLs for comparison
- Ask for the top three changes first if you want a short list
- Verify recommended character counts against the official store limits before editing
What people use it for
- Auditing a new indie app's title, subtitle and screenshots before a launch
- Comparing your app's listing against two or three competitors in the same category
- Diagnosing low downloads by reviewing visuals, ratings and description together
- Finding keyword gaps in the Google Play short and full descriptions
Frequently asked questions
Is the aso skill free?
The skill is published under the MIT licence, as stated on this page. Check the licence file in the repository for the full terms before reusing it.
What do I need to install the aso skill?
You need an agent environment that supports skills, plus a way to unzip the ZIP into ~/.claude/skills/ or a project's .claude/skills/ folder. The skill also expects a WebFetch tool to read listing pages.
Does the aso skill work with Google Play as well as the App Store?
Yes. The skill detects the store from the URL and includes Google Play fields such as the 80-character short description and the full description, which Google indexes for search.
Why does the skill say some data is missing?
Store pages can render content in the browser, so a plain fetch may not capture every field. The skill notes these gaps and may ask you to paste the missing information.
Can the skill guarantee more downloads or a higher ranking?
No. The skill gives recommendations based on best practices and benchmarks, not measured outcomes. It is not suited to guaranteeing ranking or download results.
Does this skill replace App Store Connect or Play Console?
No. The skill works from public listing pages and suggests checking App Store Connect or Play Console manually for official store data.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use the aso skill if you are an indie developer, startup or growth marketer who wants a structured, public-data review of an app listing and a prioritized list of fixes. Pick something else if your listing is private or behind a login, or if you need guaranteed rankings or official store analytics.
Download the skill