App Store Listing logo

App Store Listing

Community
Innei
app-store-listing

Use when preparing an iOS app for a first App Store listing or a listing refresh — App Store Connect questionnaires (age rating, App Privacy, encryption, content rights, review notes), zh/ja/en store copy, or framed screenshot decks from a real simulator. Also use for /app-store-listing, 上架, 截图, 营养标签, 年龄分级.

Overview

PublisherInnei
RepositorySKILL
Skill nameapp-store-listing
Stars
81
Forks
2
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the App Store Listing 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/Innei/SKILL.git /tmp/SKILL
mkdir -p .claude/skills
cp -r /tmp/SKILL/skills/content/app-store-listing .claude/skills/app-store-listing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Store Listing 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 App Store Listing 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 App Store Listing 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 listing

Generate a complete first-listing pack in one run: store copy, official-bezel screenshots, and answered Connect checklists. Do not stop after pretty slides.

Capability contract

  • Outcome: a directory the user can paste into App Store Connect (copy + PNGs + questionnaire answers). Optional: push via asc after they confirm.
  • Preconditions: macOS, a runnable iOS build or simulator app, ImageMagick (magick), axe or simctl, and a way to render local HTML (agent-browser or equivalent).
  • Boundaries: does not invent privacy/age answers. Does not submit to Apple until the user confirms. Does not redistribute Apple bezel files.

Hard rules

  • Capture the real app. Never image_gen / image_edit a fake UI.
  • Frame with Apple's Product Bezels only. Never CSS-draw a phone.
  • Render slide headlines in HTML/CSS. Image models garble CJK and exact type.
  • One locale per deck. Chrome, body content, and headline language must match.
  • Do not ship an empty signed-out Settings / Me screen as a marketing slide.
  • Do not infer App Privacy answers from the app name or store copy. Read the binary, SDKs, and network calls.

One-shot workflow

Copy this list and check it off:

- [ ] 1. Discover
- [ ] 2. Write listing.md
- [ ] 3. Answer questionnaires
- [ ] 4. Capture simulator screens
- [ ] 5. Compose official-bezel slides
- [ ] 6. Validate
- [ ] 7. Stop (or push after confirm)

Output root: <app>/tmp-asc/ (or the path the user names).

1. Discover

Read the app until these are known. Ask only for what the repo cannot answer.

NeedWhere to look
Display name, bundle id, schemeapp.config.ts, Info.plist, overlay
Who downloads itlocked to one site → write as that author's reader; generic client → say so
Privacy / support URLsoverlay, site config
Tabs / hero screensrouter, official previews, running app
Tokensdesign system (paper bg, accent, serif)
Localesdefault zh-Hans; add ja / en-US when asked
How to boot iOSExpo overlay, Metro port, xcrun simctl, axe

Default slide set (4): list, long-read, signature screen, secondary feed. Drop any screen that is mock, broken, or empty.

2. Write listing.md

Follow references/listing-fields.md. Write every locale in one file.

Buyer-facing copy describes what a stranger sees after install. If the binary is locked to one site, do not sell it as a generic CMS client.

3. Answer questionnaires

Follow references/checklists.md. Write answers into tmp-asc/questionnaires.md. Mark any item UNKNOWN instead of guessing.

4. Capture

  1. Boot the matching simulator. Override the status bar to 9:41, charged, not showing a lightning bolt if simctl status_bar allows it.
  2. Force dark or light to match the deck.
  3. Point the dev client at this app's Metro. Simulator localhost is not the Mac; use the LAN IP. --localhost binds IPv6-only and will fail.
  4. Switch in-app locale, wait for content sync, then shoot. Deep-link with the app scheme when possible.
  5. Save tmp-asc/captures/<locale>/<id>.png at the device's native pixels (iPhone 17 = 1206x2622).

5. Compose

bash
bash scripts/ensure-bezel.sh
python3 scripts/measure-bezel.py "$BEZEL_PNG"
python3 scripts/render-slides.py tmp-asc/deck.json

deck.json lists per-slide title, subtitle, capture path, and locale. The renderer overlays the capture into the official bezel hole, then paints headlines in HTML at 1290x2796.

6. Validate

bash
python3 scripts/validate-listing.py tmp-asc/listing.md

Then visually open every tmp-asc/out/<locale>/*.png:

  • official metal frame, island, and side buttons present
  • no locale mix
  • no leftover markdown / mock labels
  • no alpha (App Store rejects transparency)

7. Push (optional)

Only after the user says to upload:

  • copy → asc metadata
  • slides → asc screenshots
  • age / encryption / content rights → asc public API
  • App Privacy → asc web privacy (needs an Apple web session)

Dry-run first. Never asc review submit without an explicit confirm.

Companion tools

Install if missing, do not reimplement:

JobTool
Questionnaire braincharleswiltgen/axiom@axiom-app-store-submission + @axiom-app-store-ref
Write to Connectrorkai/app-store-connect-cli-skills
Pre-submit scantruongduy2611/app-store-preflight-skills
Expo build/uploadexpo/skills@eas-app-stores

Red flags

ExcuseReality
"I'll generate the UI with Imagine"Fake UI is a 2.3.3 rejection. Recapture.
"A CSS phone is close enough"Use Apple bezels.
"Privacy labels can wait"First submit blocks without a published App Privacy record.
"Me screen shows the product"Signed-out settings is not a benefit slide.
"English chrome + Chinese body is fine"Reshoot that locale.

Verification

  • listing.md exists for every requested locale; validate-listing.py exits 0
  • questionnaires.md has no silent blanks (only answers or UNKNOWN)
  • out/<locale>/ has 4 PNGs at 1290x2796, no alpha
  • Each slide uses the official bezel and matching-locale capture

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 App Store Listing AI skill do?

Use when preparing an iOS app for a first App Store listing or a listing refresh — App Store Connect questionnaires (age rating, App Privacy, encryption, content rights, review notes), zh/ja/en store copy, or framed screenshot decks from a real simulator. Also use for /app-store-listing, 上架, 截图, 营养标签, 年龄分级.

Why use App Store Listing on TypingMind?

Because you install it once and use it with any model. App Store Listing 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 App Store Listing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Innei/SKILL/tree/main/skills/content/app-store-listing. 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 App Store Listing?

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 App Store Listing?

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

Is the App Store Listing AI skill free?

It is published on GitHub by Innei. Check the repository for licensing terms. 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 👇