Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rshankras/subscription-lifecycle
Generates StoreKit 2 subscription lifecycle management — grace periods, billing retry, offer codes, win-back offers, upgrade/downgrade paths, and subscription status monitoring.
Passed 14 of 22 test cases with the skill, and 10 of 22 without it.
and 3 more in the full report
4 fixed10 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
When a subscriber enters an App Store grace period due to a payment failure, my team wants to immediately block app feature access until payment succeeds to protect revenue. How should the subscriber state monitor evaluate access during grace periods?
| Checked | Without skill | With skill |
|---|---|---|
| Maintains feature access (hasAccess evaluates to true) during grace period. | Missed | Passed |
| Recommends showing a payment warning banner while access remains active. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate production StoreKit 2 subscription lifecycle management with real-time status monitoring, grace period handling, billing retry detection, offer code redemption, win-back offers, and upgrade/downgrade path support.
Different from paywall-generator: The paywall generator handles the purchase UI and initial transaction. This skill handles everything that happens after purchase — monitoring subscription state changes, handling payment failures, retaining churning users, and managing tier transitions.
Why retention math dominates acquisition (per Apple's Tech Talk):
Use this skill when the user:
Search for existing subscription code:
Glob: **/*Store*.swift, **/*Subscription*.swift, **/*Entitlement*.swift
Grep: "import StoreKit" or "Transaction.updates" or "Product.SubscriptionInfo"
If paywall-generator output found:
StoreKitManager — don't duplicate product loadingtest cases passed, vs 10 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.