ParthJadhav/app-store-screenshots

end to end app store screenshot creation using AI

What it solves

It automates the creation of professional, store-ready marketing screenshots for the Apple App Store and Google Play Store. Instead of manually designing each slide in a graphic design tool, it provides a specialized editor that handles device frames, precise store resolutions, and multi-platform exports.

How it works

This project is a "skill" for AI coding agents (like Claude Code or Cursor). When invoked, the agent scaffolds a full Next.js application that serves as a dedicated screenshot editor. This editor features a connected canvas where users can drag elements across screen boundaries, an inspector for editing copy and layouts, and a system that saves the project state to a JSON file for version control. Once the design is complete, the tool exports a ZIP bundle of PNGs scaled to the exact resolutions required by both Apple and Google.

Who it’s for

App developers and designers who need to generate high-quality marketing assets for multiple devices and locales without manually resizing images for every single store requirement.

Highlights

  • Connected Canvas: Design a continuous strip of screenshots where elements can span across multiple slides.
  • Multi-Platform Support: Generates assets for iPhone, iPad, Android phones, Android tablets, and Play Store feature graphics.
  • Store-Ready Exports: One-click export of PNG bundles at the exact resolutions required by the App Store and Google Play.
  • Agent-Driven Setup: Designed to be installed and configured via AI coding agents using the skills framework.
  • Localization Support: Built-in handling for different locales and RTL-aware layouts.

Related

  • Project
    clearml/clearml

    An open-source MLOps and LLMOps suite that provides experiment tracking, orchestration, and data management to streamline the deep learning development lifecycle.

  • Project
    deepspeedai/DeepSpeedExamples

    A collection of practical examples, benchmarks, and applications demonstrating how to use the DeepSpeed library for training, inference, and model compression.

  • Project
    cazala/synaptic

    A JavaScript neural network library for Node.js and the browser that allows the creation and training of flexible, architecture-free neural networks.

  • Project
    interpretml/interpret

    An open-source framework that provides both inherently interpretable glassbox models and tools to explain complex blackbox machine learning systems.