Asc Submission Health logo

Asc Submission Health

OrganizationPopular
rorkai
asc-submission-health

Diagnose App Store submission blockers and operate review health with asc, including readiness validation, repair routing, status monitoring, cancellation, and retry decisions. Use when validation fails, a version is not in a valid state, review status is unclear or stuck, or a failed submission must be repaired and retried. For staging, upload, publication, and submission execution, use asc-release-flow.

Overview

Publisherrorkai
Repositoryapp-store-connect-cli-skills
Skill nameasc-submission-health
Stars
1K
Forks
63
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Asc Submission Health 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.
    https://github.com/rorkai/app-store-connect-cli-skills/tree/main/skills/asc-submission-health
  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/rorkai/app-store-connect-cli-skills.git /tmp/app-store-connect-cli-skills
mkdir -p .claude/skills
cp -r /tmp/app-store-connect-cli-skills/skills/asc-submission-health .claude/skills/asc-submission-health
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asc Submission Health 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 Asc Submission Health 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 Asc Submission Health 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 Store submission health

Use this skill to explain why a release cannot proceed and to manage an existing review submission. Hand healthy release execution back to asc-release-flow.

Ownership boundary

This skill owns:

  • readiness validation and blocker diagnosis;
  • public-API, web-session, and manual repair routing;
  • review status and history;
  • cancellation and retry decisions.

Use asc-release-flow for staging, upload, publication, and submission. Switching skills continues the current task with its resolved targets, authorization, and verified progress; it does not require the user to restart the workflow. Continue authorized repairs and return to release execution when healthy. Ask for new authority only when a repair exceeds scope.

Answer order

  1. State whether the version is ready, blocked, or already under review.
  2. Name each blocker and the evidence that proves it.
  3. Separate public-API repairs from web-session and manual work.
  4. Run the read-only checks needed to establish the diagnosis. For diagnosis-only requests, report the evidence and one proposed repair command without executing that repair. For authorized execution, continue the repair queue and report completed work and remaining blockers.

Establish the target

  • Resolve APP_ID, the version string or VERSION_ID, BUILD_ID, platform, and any known SUBMISSION_ID.
  • Configure auth with asc auth login or ASC_* environment variables.
  • Use ASC_BYPASS_KEYCHAIN=1 only for repository tests and isolated verification, not normal user sessions.
  • Prefer IDs once the target is resolved; stop when app, version, or product resolution is ambiguous.

Diagnose readiness

Run the canonical readiness report first:

bash
asc validate --app "APP_ID" --version "1.2.3" --platform IOS --output table

Use --version-id "VERSION_ID" when known. Add --strict when warnings must fail automation.

Ask the review-specific doctor for an ordered explanation:

bash
asc review doctor --app "APP_ID" --version "1.2.3" --platform IOS --output table

Collect direct evidence when the report points at the build or version:

bash
asc builds info --build-id "BUILD_ID" --output table
asc versions view --version-id "VERSION_ID" --include-build --include-submission --output table

For digital goods, run only the relevant product validator:

bash
asc validate iap --app "APP_ID" --output table
asc validate subscriptions --app "APP_ID" --output table

Treat the ordered remediation plan from asc validate as the repair queue. Fix and verify one class of blocker before moving to the next.

Route repairs

Use public API commands when the blocker is build processing, metadata, screenshots, review details, encryption, content rights, age rating, availability, or version-scoped product metadata.

Read references/readiness-repairs.md when diagnostics identify one of those common blockers or a first-release availability gap.

Read references/digital-goods.md only when IAP or subscription validation fails, Apple requires first-review attachment, or a versioned product must join an existing review submission.

Read references/app-privacy.md only when validation reports an App Privacy advisory or the publish state cannot be confirmed through the public API.

When validation reports a Game Center component or version blocker, hand it to asc-release-flow and request the multi-item reference's Prepare every item section. Do not route Game Center through general readiness or digital-goods repairs.

Use the web-session commands only for a gap the public API cannot cover, and say that an authenticated Apple web session is required. Keep a manual App Store Connect fallback when the user declines web-session automation.

Decide whether the version is healthy

A version is ready to return to asc-release-flow when:

  • asc validate has no blocking issues;
  • the attached build is VALID;
  • metadata, screenshots, app info, review details, content rights, encryption, age rating, pricing, and availability are resolved;
  • the relevant asc validate iap and/or asc validate subscriptions checks have no blocking issues, and the required digital-goods versions are prepared;
  • any Game Center version items have been checked through asc-release-flow's multi-item submission reference;
  • App Privacy is confirmed or published.

Do not call a version ready merely because one validator exits successfully. Report any warning that still needs a web-session or manual check.

Monitor review

Use app-scoped status when the submission ID is unknown:

bash
asc review status --app "APP_ID" --version "1.2.3" --platform IOS --output table

Use exact submission or version IDs when available:

bash
asc submit status --id "SUBMISSION_ID" --output table
asc submit status --version-id "VERSION_ID" --output table

Use the release dashboard for surrounding build and review signals:

bash
asc status --app "APP_ID" --include builds,appstore,submission,review --output table

Use history to distinguish a current stall from earlier rejected or completed submissions:

bash
asc review history --app "APP_ID" --version "1.2.3" --paginate --output table

Cancel an unhealthy submission

Resolve the exact active submission before cancelling. Preview status first, then require confirmation:

bash
asc submit status --id "SUBMISSION_ID" --output table
asc submit cancel --id "SUBMISSION_ID" --confirm

When resolving by version, include the app for the modern review-submission lookup:

bash
asc submit status --version-id "VERSION_ID" --output table
asc submit cancel --version-id "VERSION_ID" --app "APP_ID" --confirm

The lower-level equivalent is valid when the exact review submission is already known:

bash
asc review submissions-cancel --id "SUBMISSION_ID" --confirm

Do not cancel a submission solely because review is taking longer than expected. Confirm the state and the user's intent first.

Decide when to retry

There is no dedicated retry command. Use this sequence:

  1. Cancel only if the active submission must be withdrawn.
  2. Repair the proven blockers.
  3. Re-run asc validate and the relevant product validators.
  4. Confirm no active submission already owns the version or review items.
  5. Hand the healthy version and any preserved SUBMISSION_ID to asc-release-flow for submission execution. Reuse an inspected READY_FOR_REVIEW draft; create a submission only when no matching draft or active submission exists.

Common failure routing

SymptomFirst evidenceRepair route
Version is not in a valid stateasc validate, asc review doctorordered readiness repairs
Export compliance must be approvedbuild info and encryption declarationreadiness repairs
Multiple app infos foundasc apps info list --app "APP_ID"resolve exact app-info ID
IAP or subscription is not readyproduct validatordigital-goods reference
Game Center component or version is not readyasc validate diagnosticasc-release-flow multi-item preparation section
App Privacy publish state is unclearvalidation advisoryApp Privacy reference
Review appears stuckreview status plus historymonitor; cancel only with evidence and approval

Guardrails

  • Do not use removed submit-preflight or submit-create shortcuts.
  • Do not submit from this skill; return healthy execution to asc-release-flow.
  • Do not treat web-session automation as public App Store Connect API coverage.
  • Do not retry until the earlier submission state and blocker repairs are verified.
  • Use --output table for human diagnosis and JSON for automation.
  • For macOS, use --platform MAC_OS while keeping the same health lifecycle.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Asc Submission Health AI skill do?

Diagnose App Store submission blockers and operate review health with asc, including readiness validation, repair routing, status monitoring, cancellation, and retry decisions. Use when validation fails, a version is not in a valid state, review status is unclear or stuck, or a failed submission must be repaired and retried. For staging, upload, publication, and submission execution, use asc-release-flow.

Why use Asc Submission Health on TypingMind?

Because you install it once and use it with any model. Asc Submission Health 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 Asc Submission Health in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rorkai/app-store-connect-cli-skills/tree/main/skills/asc-submission-health. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Asc Submission Health?

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 Asc Submission Health?

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

Is the Asc Submission Health AI skill free?

Yes. It is published on GitHub by rorkai 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 👇