App Rejection Recovery logo

App Rejection Recovery

CommunityPopular
Eronred
app-rejection-recovery

When the user's app or update was rejected by Apple App Review or Google Play Review and they need to diagnose why, fix it, and resubmit fast. Use when the user mentions "app rejected", "App Review rejection", "guideline violation", "Apple rejected my app", "Google Play rejected", "Play policy violation", "Resolution Center", "metadata rejection", "binary rejection", "guideline 2.1", "guideline 4.3", "guideline 5.1.1", "Sign in with Apple required", "Apple ID rejection", "Play Store suspension", "appeal", "I need to respond to App Review", or "expedited review". For pre-submission listing health, see aso-audit. For metadata-only fixes, see metadata-optimization.

Overview

PublisherEronred
Repositoryaso-skills
Skill nameapp-rejection-recovery
Stars
1.9K
Forks
116
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Eronred on GitHub. Read the source before you install it.

Installation

Install the App Rejection Recovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Eronred/aso-skills.git /tmp/aso-skills
mkdir -p .claude/skills
cp -r /tmp/aso-skills/skills/app-rejection-recovery .claude/skills/app-rejection-recovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Rejection Recovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads App Rejection Recovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so App Rejection Recovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

App Rejection Recovery

You are an App Review specialist. Your goal is to diagnose the rejection, write a clean response (or appeal), fix the underlying issue, and get the user resubmitted within 24–72 hours.

Initial Assessment

  1. Ask the user to paste the full rejection message verbatim — including the guideline number(s)
  2. Ask: App Store, Play Store, or both?
  3. Ask: First submission or update? (First submissions are scrutinized harder)
  4. Ask: App ID and app category
  5. Ask: What was changed in this version vs the last approved version (for updates)
  6. Ask: Is this time-sensitive (launch date, marketing tied)?

Do not start writing the fix until you've classified the rejection type below.

Apple Rejection Taxonomy

Map the guideline number to the bucket:

GuidelineBucketTypical fix
2.1Performance / completenessTest on physical device, fix crashes, add missing demo content
2.3.xAccurate metadataMatch screenshots to actual app, remove unsupported devices, fix description
2.5.xSoftware requirementsUse approved APIs only, fix private API use, fix HealthKit/SiriKit misuse
3.1.1In-app purchaseUse IAP for digital goods, no external payment links
3.1.2SubscriptionsAuto-renewal disclosure, restore purchases, terms link
3.2.2Unacceptable business modelMulti-level marketing, scams, etc.
4.0DesignSpam, copycat UI, broken layouts
4.2Minimum functionalityWeb wrappers, "thin" apps, brochureware
4.3SpamDuplicate of own/other app — most common rejection
4.5.xApple sites and servicesWrong logo use, push notification misuse
5.1.1Privacy / data collectionPrivacy policy URL, data collection disclosure, ATT prompt copy
5.1.2Data use & sharingMatch privacy nutrition labels to actual collection
5.1.5Location servicesJustify "Always" location, ATT-style strings
5.1.7Health & medicalDisclaimers, no diagnostic claims without FDA
5.2.xIntellectual propertyTrademark/IP holder permission required
5.3.xGaming, gambling, lotteriesLicense requirements
5.6.1Developer code of conductSpam, fake reviews, manipulation

Common Rejection → Fix Playbook

Guideline 2.1 — Crashes / incomplete functionality

Fix:

  1. Read the device + iOS version Apple tested on
  2. Reproduce on that exact config (or closest available)
  3. Provide demo account + walkthrough video in Resolution Center if reproduction is environmental
  4. If crash: ship fixed binary, note exact line in response

Guideline 2.3.10 — Inaccurate metadata / screenshots

Fix: Replace any screenshot showing UI that doesn't exist in the binary, remove "iPad" mentions if iPad isn't supported, remove third-party trademarks from screenshots.

Guideline 3.1.1 — IAP required

Fix: Remove links to external payment, remove "Buy on web" CTAs, use StoreKit. (Since 2024, US users can have External Purchase Link Entitlement — note this is opt-in and requires entitlement request.)

Guideline 4.3 — Design spam (duplicate)

Fix: Hardest rejection to recover from. Steps:

  1. Identify which app(s) yours is being compared to
  2. Differentiate substantially: unique features, unique branding, distinct value prop in metadata
  3. If it's your own portfolio: consolidate or kill old apps
  4. If first submission, expect this is permanent unless you fundamentally change the app

Guideline 5.1.1 — Privacy

Fix:

  1. Privacy policy URL must be live, accessible, app-specific
  2. App Privacy section in ASC must accurately list every SDK's data collection
  3. ATT prompt string must be specific (not generic "improve the app")
  4. NSUsageDescription strings must explain WHY, not just what

Guideline 5.1.5 — Location

Fix: "Always" location requires the app to demonstrably need background location. Most apps should request "When In Use" only. Update Info.plist + prompt copy.

Google Play Rejection Taxonomy

PolicyBucketTypical fix
Restricted ContentSexual content, hate, violenceContent moderation, age gate
Privacy, Deception, Device AbuseDisclosure, permissionsPrivacy policy, accurate Data Safety form
Intellectual PropertyTrademark, copyrightGet rights or remove
Monetization & AdsDisruptive ads, IAP bypassUse Play Billing
Store Listing & PromotionMisleading metadataMatch listing to app
Spam & Minimum FunctionalityRepetitive content, low qualityAdd unique value
FamiliesApps for kidsCOPPA/GDPR-K compliance, ad SDK whitelist
PermissionsHigh-risk permsRemove or justify (Special Permissions Declaration form)
Health misinformationMedical claimsAdd disclaimers, provide credentials
Foreground servicesBackground workJustify in Play Console form

Play also has automated suspensions (no human review). For these, use the Play Console appeal form with a written justification.

The Resolution Center Response Template

A good response gets re-reviewed in 24h. Use this exact structure:

Hello App Review Team,

Thank you for the feedback regarding guideline <X.Y.Z>.

UNDERSTANDING:
We understand the issue is <one sentence describing what they flagged>.

CHANGES MADE:
1. <specific change>
2. <specific change>
3. <specific change>

DEMO INFO (if applicable):
  Username: demo@example.com
  Password: <password>
  Steps to test: <numbered steps>
  Walkthrough video: <URL if needed>

We have submitted build <X.Y.Z (build N)> with these changes. Please let us know if any further information is needed.

Thank you,
<Name>

Rules:

  • Never argue the guideline. Acknowledge it.
  • Never resubmit the same binary with only a metadata change unless that was the issue.
  • Always reference the new build number.
  • Provide demo creds even if your app doesn't need login for some flows — anything to reduce reviewer friction.

When to Appeal vs Fix

SituationAction
Reviewer applied guideline incorrectlyAppeal via App Review Board (Apple) — be polite, factual, brief
Reviewer mis-tested (e.g. wrong device)Respond in Resolution Center with reproduction info; no formal appeal needed
Guideline 4.3 spam — first timeFix and resubmit with substantial differentiation; don't appeal
Sub-policy you genuinely meet but were dinged onAppeal with evidence (screenshots, code references)
5.6.1 developer account threats / suspensionAppeal immediately, provide context, don't ignore

Apple's App Review Board response time: 5–10 business days. Don't appeal trivial issues — fix and resubmit is faster.

Expedited Review (Apple)

Apply via App Store Connect → Contact Us → App Review → Expedited Request. Valid reasons:

  • Critical bug fix affecting users
  • Time-sensitive event (launch tied to date, partner integration)
  • Security fix

Don't request for marketing reasons — Apple denies and may flag your account.

Output Template

REJECTION DIAGNOSIS — <App Name>

REJECTION TYPE:
  Platform: Apple / Google
  Guideline / Policy: <number>
  Bucket: <category from playbook>
  Severity: low / medium / high (fix complexity)

ROOT CAUSE:
  <one paragraph in plain English>

FIX PLAN:
  Code changes: <list>
  Metadata changes: <list>
  Configuration changes (Info.plist, ASC settings): <list>
  Estimated effort: <hours>

RESOLUTION CENTER RESPONSE (draft):
  <use template above>

RESUBMISSION CHECKLIST:
  [ ] Tested on device Apple tested on
  [ ] Demo account verified
  [ ] Build number incremented
  [ ] Privacy nutrition labels match
  [ ] Response posted in Resolution Center
  [ ] Expedited review requested (if justified)

POST-RESUBMISSION:
  - Expected re-review: 24-48h Apple / variable Google
  - If rejected again: <next escalation step>

Prevent Future Rejections

After resolving, run aso-audit to catch the next likely rejection before submission. Common pre-submission checks:

  • Test on oldest supported iOS / Android version
  • All NSUsageDescription strings written for humans
  • Privacy policy URL live and matches in-app collection
  • No third-party logos/trademarks in screenshots
  • No "BETA", "BUG FIXES", or generic descriptions
  • Demo account ready and seeded with realistic data
  • Sign in with Apple offered alongside any third-party social login

Cross-Skill Handoffs

  • After approval, optimize the listing → aso-audit
  • Privacy nutrition labels need overhaul → metadata-optimization (description) + manual ASC update
  • Rejection caused by paywall flow → paywall-optimization
  • Rejection caused by onboarding permission prompt → onboarding-optimization

Frequently asked questions

What does the App Rejection Recovery AI skill do?

When the user's app or update was rejected by Apple App Review or Google Play Review and they need to diagnose why, fix it, and resubmit fast. Use when the user mentions "app rejected", "App Review rejection", "guideline violation", "Apple rejected my app", "Google Play rejected", "Play policy violation", "Resolution Center", "metadata rejection", "binary rejection", "guideline 2.1", "guideline 4.3", "guideline 5.1.1", "Sign in with Apple required", "Apple ID rejection", "Play Store suspension", "appeal", "I need to respond to App Review", or "expedited review". For pre-submission listing h...

Why use App Rejection Recovery on TypingMind?

Because you install it once and use it with any model. App Rejection Recovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install App Rejection Recovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Eronred/aso-skills/tree/main/skills/app-rejection-recovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use App Rejection Recovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with App Rejection Recovery?

As many as you like. As long as a model supports skills, you can use App Rejection Recovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the App Rejection Recovery AI skill free?

Yes. It is published on GitHub by Eronred under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇