Asc Release Flow logo

Asc Release Flow

Community
hanamizuki
asc-release-flow

Orchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review. Use when the user wants to prepare or execute a release. Keep Game Center item preparation in this skill; route other readiness failures, stuck submissions, cancellation, and retry decisions to asc-submission-health.

Overview

Publisherhanamizuki
Repositorysolopreneur
Skill nameasc-release-flow
Stars
150
Forks
9
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Asc Release Flow 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.
  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/hanamizuki/solopreneur.git /tmp/solopreneur
mkdir -p .claude/skills
cp -r /tmp/solopreneur/plugins/claude/ios-dev/skills/asc-release-flow .claude/skills/asc-release-flow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asc Release Flow 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 Release Flow 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 Release Flow 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 release orchestration

Use this skill to carry a release from an approved plan to App Store review. Keep Game Center item preparation here; keep other blocker diagnosis and review recovery in asc-submission-health.

Ownership boundary

This skill owns:

  • staging metadata and attaching a build;
  • publishing an IPA or building locally;
  • submitting a prepared version;
  • assembling a multi-item review submission.

Use the preparation section for Game Center item preparation or attachment blockers. Use that reference's assembly and submission sections only after the app version is staged and the multi-item lane is selected. Stop and use asc-submission-health for other validation blockers, a stuck submission, cancellation, or retry decisions.

Preconditions

  • Resolve APP_ID, the version string, VERSION_ID when needed, and BUILD_ID when a build already exists.
  • Configure auth with asc auth login or ASC_* environment variables.
  • Confirm the intended platform. Use IOS unless the app targets another platform.
  • Keep canonical metadata in ./metadata when the workflow applies metadata.
  • Require a dry run before a mutating high-level command, then require --confirm for submission.

Choose the release lane

IntentCommand
Prepare metadata and attach an existing build without submittingasc release stage
Submit an already prepared versionasc review submit
Upload an IPA or build locally, then optionally submitasc publish appstore
Submit the app version with IAP, subscription, or Game Center version itemslower-level asc review submission commands

Do not mix lanes after one has already created a review submission. Inspect the existing submission first and continue through the matching lower-level commands.

Run the readiness gate

Apply this gate to a version that already has the intended build attached. For the staging lane, first complete Stage an existing build; asc release stage attaches the build and runs validation, after which this gate can be evaluated. Do not route an expected pre-staging "build not attached" result to asc-submission-health.

Validate before any submission:

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

Use strict mode when warnings must stop automation:

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

Digital goods are a hard gate. If the release includes IAPs or subscriptions, stop and run the relevant product checks in asc-submission-health. Resume this flow only after those checks have no blocking issues and the intended product versions are prepared.

For Game Center items, complete only Prepare every item, then return to this flow. Do not assemble or submit the multi-item review submission during readiness.

If app validation reports a Game Center item blocker, stop and use that preparation section. If the only blocker is an unattached build in the staging lane, continue to the staging section. For every other blocker, stop the release flow and use asc-submission-health. Do not bury unrelated remediation inside the release run.

Stage an existing build

Use asc release stage to verify the selected build belongs to the app before changing the version, apply or copy metadata, attach the build, and run validation without creating a review submission.

Preview metadata-driven staging:

bash
asc release stage \
  --app "APP_ID" \
  --version "1.2.3" \
  --build "BUILD_ID" \
  --metadata-dir "./metadata/version/1.2.3" \
  --dry-run \
  --output table

Apply the reviewed plan:

bash
asc release stage \
  --app "APP_ID" \
  --version "1.2.3" \
  --build "BUILD_ID" \
  --metadata-dir "./metadata/version/1.2.3" \
  --confirm

Use --copy-metadata-from "1.2.2" instead of --metadata-dir when carrying localization metadata forward. Add --strict-validate when warnings should fail the stage.

If the metadata plan contains deletes, the dry run and confirmed run both require --allow-deletes. Review those deletes first; the flag also disables fallback to an existing locale when that locale is absent locally.

Use --routing-coverage-file "./coverage.geojson" when the release includes routing app coverage. This experimental step validates the GeoJSON before mutation and stages it before readiness checks.

Structured output includes a validate_build step at the start of steps[]. Match steps by name rather than array position.

Submit a prepared version

Use asc review submit after metadata, review details, availability, build processing, and product readiness are already resolved.

bash
asc review submit --app "APP_ID" --version "1.2.3" --build "BUILD_ID" --dry-run --output table
asc review submit --app "APP_ID" --version "1.2.3" --build "BUILD_ID" --confirm

Use --version-id "VERSION_ID" instead of --version when the exact version ID is known. --build may be omitted only when the intended build is already attached and verified.

Upload or build, then publish

Use asc publish appstore when the release starts from an IPA or a local Xcode project/workspace.

Preview an IPA upload and submission:

bash
asc publish appstore \
  --app "APP_ID" \
  --ipa "./App.ipa" \
  --version "1.2.3" \
  --submit \
  --dry-run \
  --output table

Run it after reviewing the plan:

bash
asc publish appstore \
  --app "APP_ID" \
  --ipa "./App.ipa" \
  --version "1.2.3" \
  --submit \
  --wait \
  --confirm

For local-build mode, provide --workspace or --project with --scheme instead of --ipa. Use --metadata-dir when the publish command should apply canonical version metadata after ensuring the version.

Omit --submit when the user wants upload and attachment only.

Submit multiple review items

Read references/multi-item-submissions.md when the app version must ship with versioned IAP, subscription, subscription-group, or Game Center items. Add only items the user has resolved and inspected.

Handoff after submission

Report:

  • the app, version, platform, build, and submission IDs;
  • which lane ran and whether it completed;
  • every mutation confirmed by the user;
  • the exact command to monitor the resulting submission.

Use asc-submission-health for monitoring, cancellation, rejection diagnosis, or retry decisions.

Guardrails

  • Do not use removed submit-preflight, submit-create, or release-run shortcuts.
  • Do not add --confirm until the dry-run plan matches the requested release.
  • Do not create a second review submission when one already exists for the version.
  • Do not turn a validation failure into a partial release; stop at the failing gate.
  • Keep data on stdout and diagnostics on stderr when wrapping commands in automation.

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 Release Flow AI skill do?

Orchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review. Use when the user wants to prepare or execute a release. Keep Game Center item preparation in this skill; route other readiness failures, stuck submissions, cancellation, and retry decisions to asc-submission-health.

Why use Asc Release Flow on TypingMind?

Because you install it once and use it with any model. Asc Release Flow 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 Release Flow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hanamizuki/solopreneur/tree/main/plugins/claude/ios-dev/skills/asc-release-flow. 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 Release Flow?

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 Release Flow?

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

Is the Asc Release Flow AI skill free?

Yes. It is published on GitHub by hanamizuki 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 👇