Mobile Pro Max logo

Mobile Pro Max

Organization
vurakit
mobile-pro-max

Mobile development intelligence. 12 domains, 9 stacks, 250+ entries. Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check mobile code. Domains: pattern, package, error, perf, test, security, interface, arch, idiom, anti, tooling, dependency. Stacks: flutter, react-native, swiftui, jetpack-compose, kotlin-multiplatform, capacitor, expo, native-ios, native-android. Integrations: arch_system generator.

Overview

Publishervurakit
Repositoryagentup
Skill namemobile-pro-max
Stars
56
Forks
14
Bundled files
27
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.

  • 27 bundled files

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

  • Open source

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

Installation

Install the Mobile Pro Max 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/vurakit/agentup/tree/main/skills/mobile
  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/vurakit/agentup.git /tmp/agentup
mkdir -p .claude/skills
cp -r /tmp/agentup/skills/mobile .claude/skills/mobile-pro-max
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile Pro Max 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 Mobile Pro Max 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 Mobile Pro Max 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.

Mobile Pro Max - App Generator

When User Requests Mobile Work

Follow this workflow for every mobile-related task:

1. Analyze Requirements

Extract from the user's request:

  • Platform: iOS, Android, cross-platform, web-to-mobile
  • Project type: consumer app, enterprise app, e-commerce, social, fintech, health
  • Domain: UI/UX, networking, storage, auth, payments, maps, camera, push notifications
  • Constraints: specific framework? offline-first? real-time? performance-critical?
  • Scale: MVP, production, enterprise

Default Stack (always use unless user specifies otherwise)

ComponentDefaultPackage
FrameworkFlutter 3.xflutter
LanguageDart 3.xSound null safety
State MgmtRiverpodflutter_riverpod
NavigationGoRoutergo_router
HTTP ClientDiodio + retrofit
DIGetIt + Injectableget_it + injectable
ModelsFreezedfreezed + json_serializable
Local DBDriftdrift (SQLite)
Secure StorageFlutter Secureflutter_secure_storage
Error Handlingfpdart Eitherfpdart
Testingmocktail + bloc_testmocktail + bloc_test
CI/CDGitHub Actions+ Fastlane for store deployment

Project structure: Flutter Clean Architecture with feature-first:

lib/
  core/
    constants/         — app-wide constants
    theme/             — ThemeData, colors, typography
    utils/             — utility functions, extensions
    errors/            — Failure classes, error handling
    network/           — Dio client, interceptors
  features/
    auth/
      data/            — datasources, models, repository impl
      domain/          — entities, repository interface, use cases
      presentation/    — BLoC/providers, screens, widgets
    home/
      data/
      domain/
      presentation/
    products/
      data/
      domain/
      presentation/
  shared/
    widgets/           — reusable widgets (AppButton, AppCard, etc.)
    services/          — analytics, push notifications, etc.
  l10n/                — localization ARB files
  app.dart             — MaterialApp.router setup
  main.dart            — entry point, DI setup
test/
  unit/                — unit tests (use cases, repositories)
  widget/              — widget tests
  integration/         — integration tests

2. Generate Architecture System (REQUIRED for new projects)

bash
python3 skills/mobile/scripts/search.py "<project description>" --arch-system -p "ProjectName"

This gives you: architecture, packages, error strategy, patterns, structure, testing approach, state management, CI/CD pipeline.

3. Supplement with Domain Searches

Based on the project needs, search relevant domains:

bash
# Patterns for the task
python3 skills/mobile/scripts/search.py "mvvm bloc clean architecture" --domain pattern

# Error handling approach
python3 skills/mobile/scripts/search.py "either result type crash reporting" --domain error

# Security patterns
python3 skills/mobile/scripts/search.py "secure storage certificate pinning" --domain security

# Performance tips
python3 skills/mobile/scripts/search.py "widget rebuild list optimization" --domain perf

# Testing patterns
python3 skills/mobile/scripts/search.py "widget test bloc test mocking" --domain test

# UI/UX guidelines
python3 skills/mobile/scripts/search.py "responsive layout dark mode accessibility" --domain interface

4. Stack Guidelines

If using a specific framework/stack:

bash
python3 skills/mobile/scripts/search.py "state management navigation" --stack flutter
python3 skills/mobile/scripts/search.py "hooks performance memoization" --stack react-native
python3 skills/mobile/scripts/search.py "observable state swiftdata" --stack swiftui
python3 skills/mobile/scripts/search.py "viewmodel stateflow hilt" --stack jetpack-compose
python3 skills/mobile/scripts/search.py "expect actual ktor" --stack kotlin-multiplatform
python3 skills/mobile/scripts/search.py "eas build expo router" --stack expo

5. Implement

Apply all recommendations from the search results:

  • Use recommended architecture and project structure
  • Apply patterns (MVVM, BLoC, Clean Architecture, Repository, etc.)
  • Follow error handling strategy (Either types, typed failures)
  • Implement security best practices (secure storage, certificate pinning)
  • Add tests following testing strategy (unit > widget > integration)
  • Build responsive layouts with design system

6. Always Generate Project Configuration

Every Flutter project MUST include:

pubspec.yaml (core dependencies):

yaml
name: my_app
description: A Flutter application
version: 1.0.0+1

environment:
  sdk: ">=3.2.0 <4.0.0"

dependencies:
  flutter:
    sdk: flutter
  flutter_riverpod: ^2.4.0
  go_router: ^13.0.0
  dio: ^5.4.0
  freezed_annotation: ^2.4.0
  json_annotation: ^4.8.0
  get_it: ^7.6.0
  injectable: ^2.3.0
  fpdart: ^1.1.0
  flutter_secure_storage: ^9.0.0
  drift: ^2.14.0

dev_dependencies:
  flutter_test:
    sdk: flutter
  build_runner: ^2.4.0
  freezed: ^2.4.0
  json_serializable: ^6.7.0
  injectable_generator: ^2.4.0
  drift_dev: ^2.14.0
  mocktail: ^1.0.0
  bloc_test: ^9.1.0
  flutter_lints: ^3.0.0

flutter:
  uses-material-design: true
  assets:
    - assets/images/
    - assets/icons/

analysis_options.yaml:

yaml
include: package:flutter_lints/flutter.yaml

linter:
  rules:
    prefer_const_constructors: true
    prefer_const_declarations: true
    avoid_print: true
    require_trailing_commas: true
    prefer_single_quotes: true

analyzer:
  exclude:
    - "**/*.g.dart"
    - "**/*.freezed.dart"

Makefile:

makefile
run:
	flutter run
test:
	flutter test
analyze:
	flutter analyze --fatal-warnings
format:
	dart format .
build-runner:
	dart run build_runner build --delete-conflicting-outputs
watch:
	dart run build_runner watch --delete-conflicting-outputs
build-apk:
	flutter build apk --release --obfuscate --split-debug-info=build/debug-info/
build-ios:
	flutter build ipa --release --obfuscate --split-debug-info=build/debug-info/
clean:
	flutter clean && flutter pub get

Pre-Delivery Checklist

Before delivering mobile code, verify:

  • flutter analyze --fatal-warnings passes
  • dart format . passes (no formatting issues)
  • flutter test passes with adequate coverage
  • No hardcoded strings (use localization)
  • All user input validated (client-side AND server-side)
  • Sensitive data stored in flutter_secure_storage (not SharedPreferences)
  • No hardcoded API keys or secrets (use --dart-define)
  • Proper error handling (Either types, typed failures, no empty catch blocks)
  • All StreamSubscriptions cancelled in dispose()
  • All Controllers disposed in dispose()
  • Const constructors used where possible
  • BuildContext not used across async gaps (check mounted)
  • Responsive layout tested on multiple screen sizes
  • Dark mode supported and tested
  • Accessibility labels on interactive elements
  • Minimum tap target size 48x48
  • Loading, error, and empty states handled for all async data
  • Code obfuscation enabled for release builds

Quick Domain Reference

DomainWhen to Search
patternNeed a design pattern (MVVM, BLoC, Repository, Clean Architecture)
packageChoosing a pub.dev package for a use case
errorError handling strategy, either types, crash reporting
perfPerformance optimization, widget rebuilds, memory, lists
testTesting approach, widget tests, BLoC tests, mocking, golden tests
securitySecure storage, certificate pinning, obfuscation, auth
interfaceUI/UX design, responsive layout, accessibility, Material Design 3
archProject structure, architecture patterns, modular design
idiomDart conventions, null safety, extensions, pattern matching
antiAvoiding common mistakes (massive widgets, setState abuse, leaks)
toolingFlutter DevTools, Fastlane, FVM, Mason, CI/CD
dependencypubspec.yaml, CocoaPods, Gradle, version management

Resources

  • scripts/: BM25 search engine, architecture system generator
  • data/: 12 domains and 9 stacks with 250+ curated mobile entries

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 Mobile Pro Max AI skill do?

Mobile development intelligence. 12 domains, 9 stacks, 250+ entries. Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check mobile code. Domains: pattern, package, error, perf, test, security, interface, arch, idiom, anti, tooling, dependency. Stacks: flutter, react-native, swiftui, jetpack-compose, kotlin-multiplatform, capacitor, expo, native-ios, native-android. Integrations: arch_system generator.

Why use Mobile Pro Max on TypingMind?

Because you install it once and use it with any model. Mobile Pro Max 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 Mobile Pro Max in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vurakit/agentup/tree/main/skills/mobile. 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 Mobile Pro Max?

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 Mobile Pro Max?

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

Is the Mobile Pro Max AI skill free?

Yes. It is published on GitHub by vurakit 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 👇