Spaced repetition.
Study apps split into two camps: the powerful one everyone finds intimidating, and the friendly ones that charge a subscription and keep your decks on their servers. Either way, the cards you spent hours writing live somewhere you do not control, one policy change away from a paywall or a shutdown. This blueprint puts the deck back in your hands. You describe the study app you want, and it lives in your repository, your cards and your progress included.
A flashcard study app with flip-card animations and support for building your own decks, plus a spaced-repetition sort that reorders cards based on whether you marked each one Hard, Medium, or Easy. The cards you struggle with resurface sooner, the ones you know drift back, so a review session spends your time where it counts.
You watch it come together in the task workspace: the agent scaffolds the project, wires the flip animation and the sorting logic, starts the dev server, and steps through a deck before handing you a live preview. The code lands on a branch in your repository with a pull request ready.
The first version is a base you steer with plain follow-up messages:
Each follow-up wakes the same repository and the agent continues on its own code.
Do I need to know how to code? No. You describe the study app; the agent writes it, verifies a deck runs through, and ships the code to your repository.
Where do my decks live? In your app, in your repository, under your account. No subscription stands between you and your own cards.
Does spaced repetition need a backend? No. The Hard, Medium, and Easy sorting runs in the app, so your review order works without a server.