agentleFS
fatih-developerfatih-developer/fth-skills/skills/app-store-reviewer/SKILL.md

app-store-reviewer

Skill7 starsChanged 43 days agoMITView on GitHub

Check an app against App Store and Google Play review guidelines before submission, diagnose rejection reasons, and optimize store metadata (title, screenshots, description, privacy disclosures). Use when the user is preparing a store submission, received a rejection, or wants a store-readiness review.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Check against common rejection reasons:

    line 39
  2. Distinctive:

    Create a structured report detailing the findings, quoting the specific guideline violated, and providing an actionable fix.

    line 50
  3. Distinctive:

    Quote the Rules: Always back up a rejection risk with a specific guideline number or concept (e.g., "Guideline 5.1.1" or "Play Console Spam …

    line 97
  4. Distinctive:

    Platform Specificity: Do not apply Apple rules to Google (like 30-character title limits, which differs between stores).

    line 99

≈ “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 Reviewer Protocol

The submission process is critical. A rejection costs days. This skill acts as a preemptive store reviewer. It evaluates app metadata, features, and submission history against Apple's App Store Review Guidelines and Google Play Developer Policies.

Core principle: Find the rejection before the real reviewer does.


Workflow

1. Identify target platform (iOS, Android, or both)
2. Analyze provided metadata and feature list
3. Cross-reference with current store guidelines
4. Flag violations (Critical, Warning, Optimization)
5. Generate submission readiness report

Step 1: Platform Context

Determine if the review is for the App Store (iOS), Play Store (Android), or both. Their policies differ significantly (e.g., Apple's strictness on in-app purchases vs. Google's focus on permissions).

Step 2: Input Analysis

Review the user's provided inputs:

  • App Title & Subtitle
  • Promotional Text & Description
  • Keywords (iOS)
  • Screenshots & Video descriptions
  • Core features and permissions requested (e.g., location, camera)
  • In-App Purchase (IAP) structures

Step 3: Guideline Verification

Check against common rejection reasons:

  • iOS Top Rejections: 2.1 Performance (Crashes/Bugs), 2.3.3 Accurate Metadata, 3.1.1 In-App Purchase logic, 4.0 Design (Spam/Copycats), 5.1.1 Data Collection and Storage (Privacy).
  • Android Top Rejections: Broken Functionality, Inappropriate Content, Misleading Claims, Improper Use of Permissions, Sign-in Wall without Guest Mode (in some cases).

Step 4: Issue Categorization

Categorize findings into:

  • [CRITICAL] Will definitely cause a rejection. Must fix.
  • [WARNING] High risk of rejection depending on reviewer interpretation.
  • [OPTIMIZATION] Safe, but metadata could be improved for ASO (App Store Optimization) or clarity.

Step 5: Output Generation

Create a structured report detailing the findings, quoting the specific guideline violated, and providing an actionable fix.


Output Format

# 📋 Store Review Readiness Report

**Target Platform(s):** [App Store / Google Play]

## 🚨 Critical Violations
*Issues that will trigger a definitive rejection.*

1. **[Violation Area]** (e.g., In-App Purchases)
   - **Guideline:** [Quote or reference the guideline, e.g., Apple 3.1.1]
   - **Finding:** [Explain what is wrong, e.g., "Using Stripe for digital goods instead of IAP."]
   - **Fix:** [Actionable solution]

## ⚠️ High-Risk Warnings
*Subjective areas where a reviewer might push back.*

1. **[Risk Area]** (e.g., Privacy / Permissions)
   - **Guideline:** [Reference]
   - **Finding:** [Explanation]
   - **Mitigation:** [How to reduce the risk]

## 💡 Metadata Optimization
*Suggestions for better conversion and ASO.*

- **Title/Subtitle:** [Suggestion]
- **Screenshots:** [Suggestion]
- **Description:** [Suggestion]

## Next Steps
[Summary of what the developer must do before hitting "Submit"]

When to Skip

  • The task is purely code formatting or UI design with no store-facing implications.
  • The user is asking about marketing strategy outside the store listing.

Guardrails

  • Quote the Rules: Always back up a rejection risk with a specific guideline number or concept (e.g., "Guideline 5.1.1" or "Play Console Spam Policy").
  • No Guarantees: Explicitly state that fixing these issues does not guarantee approval, as human reviewers vary.
  • Platform Specificity: Do not apply Apple rules to Google (like 30-character title limits, which differs between stores).

References

See references/EXAMPLES.md for a worked case.

🔗 Next Steps & Handoffs

<!-- BEGIN GENERATED: handoffs (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->

Ecosystem: @ecosystem-mobile — Mobile App Domain.

Workflows:

  • Production Release Flow (mobile-release, step 1 of 3): next → @release-orchestrator.

Handoff contract: pass results to the next skill through an inline Handoff block in your reply with the fields skill, workflow, created_at, inputs, summary, and next (the handoff contract of @ecosystem-mobile). If a next skill is not installed, continue with its step from the ecosystem map, or install it with npx skills add fatih-developer/fth-skills --skill <name> after the user agrees.

<!-- END GENERATED: handoffs -->

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.