- Home
- Skills
- Mobile Development
- Store Listing Accuracy Check (Flutter & React Native)
Works with the AI Agents you already use
Store Listing Accuracy Check (Flutter & React Native)
Check that the App Store and Play listing of your Flutter, React Native or Expo app describes the app that actually exists, before review finds the gap.
Free
Store Listing Accuracy Check (Flutter & React Native)
Example session with this skill installed
I removed the leaderboard last week. Is the store listing still true?
- Read your context and instructions
- Compiled the store listing accuracy
What I ran
Listing accuracy: row-counter (11 listing file(s), en-US)
ok Every name in the listing exists somewhere in the app
ok Advertising, purchase, account and online claims match the code
ok Counted claims in the listing were checked against the code
WARN The listing says "16 colours" and the code has
9 (colors). One of them is stale.
Listing and app agree. (warnings above)
What it means
The listing and the app agree on features, ads, purchases and accounts. One count is stale: the description promises 16 colours and the code ships 9.
Next steps
- Decide which is true. Either add the colours or change the listing to 9.
- Update the matching line in every locale, not just en-US.
- Re-run before submitting; a stale count is the kind of thing review flags under 2.3.
Output is from a real run on one of my live apps (name changed).
Connects securely to your tools. The creator never sees your data.
About this skill
Listings drift. You cut a feature, rename a mode or drop a currency, and the description, keywords, release notes and App Review notes still describe the old app. Apple rejects that under guideline 2.3, usually with "we were unable to locate" a feature you mention.
This skill compares your fastlane metadata (description, subtitle, keywords, promotional text, release notes, Android changelogs, review notes) with the app's code and strings: Dart for Flutter, and TypeScript or JavaScript (comments removed) plus i18n JSON for React Native and Expo. It flags feature names the app doesn't contain, claims about ads, purchases, sign-in, online play or leaderboards that the code contradicts, and counts that are out of date ("50 levels" when there are 40).
For Expo projects it also reads store.config.json (EAS Metadata) for the App Store copy and review notes, and in React Native code it checks counts against TypeScript const arrays and enums.
It expects metadata under fastlane/metadata; the per-platform ios/fastlane and android/fastlane layouts are found too.
Script: check_listing.py. Python 3.9+, no packages.
These are free and MIT-licensed, and the source is at github.com/jameskrupnik/indie-app-skills. If you ship several apps, my paid skills cover the rest of the release: new-app (forking without carrying the parent's Firebase and ad ids), ship-ios (fork to App Store review), bug-hunt and daily-update (pacing releases across many apps).
Only tested in Claude Code. What the script prints is a list of things to check, not a verdict, and the SKILL.md says what the script can't see.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Permissions
File Scopes
Reads your project and runs python3. No writes, no network.