Ipaship Audit logo

Ipaship Audit

Community
atharvnaik1
ipaship-audit

Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.

Overview

Publisheratharvnaik1
Repositoryipaship-audit
Skill nameipaship-audit
Stars
104
Forks
92
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by atharvnaik1 on GitHub. Read the source before you install it.

Installation

Install the Ipaship Audit 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/atharvnaik1/ipaship-audit/tree/main/wrappers/claude-code
  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/atharvnaik1/ipaship-audit.git /tmp/ipaship-audit
mkdir -p .claude/skills
cp -r /tmp/ipaship-audit/wrappers/claude-code .claude/skills/ipaship-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ipaship Audit 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 Ipaship Audit 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 Ipaship Audit 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.

ipaShip — ipaship-audit

Audit your iOS/Android app packages against official store policies before submission. Upload .ipa or .apk files and get a structured compliance report with guideline references, severity ratings, and actionable fixes.

When to Use

  • Before submitting an iOS app to the Apple App Store — catch rejections early
  • Before submitting an Android app to Google Play — identify policy violations
  • During CI/CD to automate pre-submission compliance checks
  • When reviewing third-party apps for compliance risks
  • As part of a code review workflow for mobile apps

Setup

Prerequisites

RequirementDetails
Accountipaship.com — free to use
API KeyGet yours at ipaship.com
App Package.ipa (iOS), .apk (Android), or .zip file (max 150MB)
DependenciesThe server needs unzip installed

Environment Variables

bash
export IPASHIP_API_KEY="your-api-key-here"

Usage

1. Web Interface (No Code Required)

  1. Go to ipaship.com
  2. Upload your .ipa or .apk file
  3. Select your AI provider (Claude, GPT, Gemini, or OpenRouter)
  4. Click "Audit" and wait for the streaming report

2. CLI via cURL

bash
# Basic audit with default provider (Anthropic Claude)
curl -X POST https://ipaship.com/api/audit \
  -H "Authorization: Bearer $IPASHIP_API_KEY" \
  -F "file=@/path/to/your-app.ipa" \
  -F "provider=anthropic" \
  -F "model=claude-3-5-sonnet-20241022"

# With context about your app
curl -X POST https://ipaship.com/api/audit \
  -H "Authorization: Bearer $IPASHIP_API_KEY" \
  -F "file=@/path/to/your-app.ipa" \
  -F "provider=anthropic" \
  -F "model=claude-3-5-sonnet-20241022" \
  -F "context=This is a social media app with user-generated content"

# Using OpenAI
curl -X POST https://ipaship.com/api/audit \
  -H "Authorization: Bearer $IPASHIP_API_KEY" \
  -F "file=@/path/to/your-app.apk" \
  -F "provider=openai" \
  -F "model=gpt-4o"

3. Python Wrapper

python
# wrappers/python/ipaship.py
from ipaship import audit_app

result = audit_app(
    file_path="build/YourApp.ipa",
    provider="anthropic",
    model="claude-3-5-sonnet-20241022",
    api_key="your-key"
)
print(result)

4. Programmatic — All Language Wrappers

The repo ships wrappers in 15+ languages under wrappers/:

LanguagePathStatus
Pythonwrappers/python/ipaship.py✅
Node.jswrappers/npm/index.js✅
Gowrappers/go/ipaship.go✅
Rustwrappers/rust/src/main.rs✅
Rubywrappers/ruby/lib/ipaship.rb✅
Javawrappers/java/✅
Kotlinwrappers/kotlin/✅
Swiftwrappers/swift-cocoapods/✅
Flutter/Dartwrappers/flutter-dart/✅
PHPwrappers/php/✅
C++wrappers/cpp/✅
C# (.NET)wrappers/csharp-dotnet/✅
Rwrappers/r/✅
Expowrappers/expo/✅
Homebrewwrappers/homebrew/✅

Features

Supported AI Providers

ProviderModels
AnthropicClaude Sonnet 4, Claude 3.5 Sonnet, Claude 3 Opus
OpenAIGPT-4o, GPT-4o-mini
Google GeminiGemini 2.5 Flash, Gemini 2.0 Pro
OpenRouterAny model (e.g., anthropic/claude-3.5-sonnet)
ipaShip (NVIDIA)Llama 3.1 405B, NVIDIA NIM models

Audit Report Structure

Every report includes:

  1. Executive Summary — What the app does (from code analysis)
  2. Dashboard — Risk level (LOW/MEDIUM/HIGH), readiness score, issue counts
  3. Phase 1: Policy Compliance — Per-guideline checks with PASS/WARN/FAIL
  4. Phase 2: Remediation Plan — Prioritized fix table with file references
  5. Submission Readiness — Go/no-go verdict with score

Key Capabilities

  • Multi-provider AI — Choose your preferred LLM backend
  • Real-time streaming — Watch the audit generate live
  • IPA & APK support — Both iOS and Android
  • Export — Download as Markdown or PDF
  • Zero-trust — Files deleted after analysis, API keys stay client-side
  • Rate limited — 5 requests/minute per client (DDoS protection)

Common Pitfalls

  1. Forgetting unzip — The server needs unzip installed to extract packages. If you see extraction errors, install it: sudo apt-get install unzip.
  2. File too large — Maximum upload size is 150MB. For larger apps, trim the .ipa/.apk first.
  3. No source files found — Ensure your app package isn't encrypted or DRM-protected. The auditor only analyzes readable source code (.swift, .java, .kt, etc.).
  4. API key in the wrong place — The server uses NVIDIA_KEY or NEXT_PUBLIC_API_KEY env vars for the backend. For BYOK (bring your own key), pass it in the upload form.
  5. Binary-only apps — Apps compiled without source code (e.g., Unity builds with only IL2CPP binaries) will have few files to analyze. The audit quality depends on available source.

Verification

After setting up:

  1. Deploy the app locally: npm run dev
  2. Upload a test .ipa or use the cURL command above
  3. Verify you get a streaming JSON response starting with {"type":"meta","filesScanned":N}
  4. Check that the final report includes both Phase 1 (compliance checks) and Phase 2 (remediation plan)
  5. Test with different providers by changing the provider field

References

Frequently asked questions

What does the Ipaship Audit AI skill do?

Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.

Why use Ipaship Audit on TypingMind?

Because you install it once and use it with any model. Ipaship Audit 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 Ipaship Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/atharvnaik1/ipaship-audit/tree/main/wrappers/claude-code. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ipaship Audit?

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 Ipaship Audit?

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

Is the Ipaship Audit AI skill free?

Yes. It is published on GitHub by atharvnaik1 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 👇