Generates smart App Store review prompt infrastructure with configurable conditions and platform detection. Use when user wants to add review prompts, request ratings, or implement StoreKit reviews.
npx skills add https://github.com/rshankras/claude-code-apple-skills --skill review-prompt
Generate smart App Store review prompting with configurable trigger conditions, platform detection, and proper timing logic.
Use this skill when the user:
This skill only applies to App Store distributed apps.
Detection steps:
com.apple.application-identifier entitlementSearch for existing implementations:
Grep: "requestReview" or "SKStoreReviewController" or "StoreKit"
Glob: **/*Review*.swift
If found, ask user:
Ask user via AskUserQuestion:
Generate these files:
ReviewPromptManager.swift - Core logic and timingReviewPromptCondition.swift - Configurable conditionsReviewPromptStorage.swift - Persistence for trackingCheck project structure:
Sources/ exists → Sources/Reviews/App/ exists → App/Reviews/Reviews/For macOS, include:
#if os(macOS)
// Check if running from App Store
guard Bundle.main.appStoreReceiptURL?.lastPathComponent != "sandboxReceipt" else {
// Running in sandbox but not App Store - skip
return
}
#endif
After generation, provide:
Sources/Reviews/
├── ReviewPromptManager.swift # Core logic
├── ReviewPromptCondition.swift # Conditions enum
└── ReviewPromptStorage.swift # UserDefaults persistence
Option 1: Automatic (Recommended)
@main
struct MyApp: App {
var body: some Scene {
WindowGroup {
ContentView()
.onAppear {
ReviewPromptManager.shared.incrementSession()
}
}
}
}
// In relevant places (after positive actions):
ReviewPromptManager.shared.recordPositiveAction()
ReviewPromptManager.shared.requestReviewIfAppropriate()
Option 2: Manual Trigger Points
// After user completes a significant action
func completeTask() {
// ... task completion logic ...
ReviewPromptManager.shared.recordPositiveAction()
ReviewPromptManager.shared.requestReviewIfAppropriate()
}
ReviewPromptManager.debugAlwaysShow = trueReviewPromptStorage.reset()For custom UI or macOS direct distribution:
// Deep link to App Store review page
let appID = "YOUR_APP_ID"
let url = URL(string: "https://apps.apple.com/app/id\(appID)?action=write-review")!
NSWorkspace.shared.open(url) // macOS
UIApplication.shared.open(url) // iOS
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take rshankras/review-prompt from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.