Install
$ agentstack add skill-alvin-yang-ay-skills-ay-app-store ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AY App Store
Move an Apple release through verified states. Never equate a green local build with a processed build, a submitted version, an approved version, or a downloadable storefront listing.
Approval contract
- Read the full request and investigate discoverable facts before asking the user.
- Treat review, diagnosis, explanation, and planning as read-only unless the user also requests change.
- Treat a precise instruction as approval when target, observable result, and acceptance boundary are clear.
- A broad outcome authorizes investigation, not file or artifact changes based on choices the agent must invent.
- For a materially underspecified change, present one recommended proposal and wait for approval.
- After approval, execute autonomously inside the approved boundary; do not ask about ordinary implementation details.
- Reopen approval only when new evidence changes behavior, architecture, data contracts, dependencies, scope, risk, cost, rollback, or external actions.
- Perform external actions only when the request or approved proposal includes them. Confirm the exact target before an irreversible action.
- Preserve unrelated and user-authored work. Verify the real requested outcome before claiming completion.
Establish facts
Inspect the repository, git state, build settings, entitlements, packaged purpose strings, privacy manifests, StoreKit, legal links, screenshots, and release automation. python3 scripts/scan_apple_release.py produces a read-only inventory, never a compliance verdict.
Refresh Apple documentation before policy conclusions. Use [Apple workflow](references/apple-workflow.md) for official checks and [tooling](references/tooling.md) for credential boundaries.
Reconcile:
- Identity: app record, Bundle ID, platform, version, build, team, SKU.
- Privacy: data flow, SDKs, labels, policy, in-app entry, permissions.
- Commerce: product IDs, types, periods, prices, entitlements, restore, review items.
- Review: localizations, screenshots, URLs, rating, contact, notes, attachments.
- Account: agreements, tax, banking, trader status, roles.
Prefer live App Store Connect state over code or email inference. “Changes needed” is only a pointer; inspect every rejected item and Resolution Center message.
Resolve and prove
Classify gaps as code/build, metadata, commerce, explanation, or account work. Use [rejection playbook](references/rejection-playbook.md) for privacy, subscription/EULA, missing-item, and summary-email cases.
Prove states independently:
- Source or metadata changed.
- Tests and archive passed.
- Upload finished Apple processing.
- Build and IAP items joined the intended submission.
- Submission ID and review state are confirmed.
- Review passed.
- Version is Ready for Distribution.
- Storefront download works.
Report the highest proven layer and all unverified layers.
Operate live surfaces
Prefer supported APIs or existing automation; use signed-in web UI for review messages and account fields. Installing tools, reusing cookies, or calling private APIs needs approval.
A precise request to submit or resubmit the named app/version is approval; do not ask twice. Unrequested cancellation, deletion, pricing, territories, agreements, banking/tax, credentials, members, or reviewer replies need their own boundary.
Before mutation, recheck app, platform, version, build, products, and submission. Afterwards, reread state and capture stable IDs. Never store secrets or full banking/identity data in files, chat, or Git.
assets/release-dossier-template.md is optional.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ALVIN-YANG
- Source: ALVIN-YANG/ay-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.