Back in 2016 I made a lot of cinemagraphs for HBO.
They took a surprising amount of work. Masking footage, finding the right loop, freezing parts of the frame and getting everything to transition cleanly.
I’ve had an idea for a simpler cinemagraph tool kicking around in my head ever since.
About a month ago I built another small tool using Toolcraft as the starting point, so yesterday I wanted to see if it could handle this idea too.
A few hours later I had a working cinemagraph editor.
Drop in a video → find your loop → choose how it loops → paint the areas you want to keep still → export.
Basically the workflow I used 10 years ago, condensed into a few controls.
Still rough around the edges, but kind of wild to finally build a tool I’ve been thinking about for a decade.
7
26
402
I started messing around with a concept for a crossfit app as I've recently switched from strength training to crossfit style workouts.
Concept images from the onboarding using @adamlyttleapps (https://x.com/adamlyttleapps) Onboarding Questionnaire skill.
The artwork will be animated and looping on each page.
10
109
My X feed filled up with people shipping little games with the new Astra model.
When I finally got access, I started one of my own.
I made three concept images in ChatGPT first. Neon arena. Industrial pit. The kind of Smash TV energy I grew up on. Then I handed those to an agent and let it build.
What came back was playable faster than I expected. Twin-stick arena shooter. Short runs. Waves. A boss. Browser, mobile and desktop.
The first prototype took about 30 minutes and everything after has been fine tuning the gameplay and polish.
The first iterations were too easy, so I cranked up the difficulty which helped a lot.
Bolt Pit is public now if you want to try a run:
https://bolt-pit.froessell.chatgpt.site
I'm working on porting it to Unity now also as I want to take advantage of the unity engine.
8
28
848
Memory Bank is a private family app designed to capture the small moments that usually get lost.
We take thousands of photos every year, but the little things often disappear: a note before a test, a flower picked on the way home from school, a funny photo of the family cat, or a simple “good luck” message from a parent.
Memory Bank gives families a shared space where they can add photos, notes, and emojis throughout the day. These contributions form a collaborative daily memory that lives on the home screen as a widget.
At midnight, the day’s memory is automatically captured as a Polaroid and saved to a family archive. Over time, families build a collection of memories together, one day at a time.
For this project, I wanted to experiment with a different design workflow.
Instead of starting in Figma, I used Codex and the Build-iOS-App workflow to generate a working Swift prototype first. My goal was to validate the interaction and product flow before investing time in visual design.
Once the concept felt promising, I used Figma MCP to bring the app screens into Figma, where I explored different visual directions, refined the user experience, and iterated on the overall concept.
I then used Figma Make to prototype key interactions and validate the experience before bringing those improvements back into the app.
Finally, I created the launch trailer and supporting assets using Hyperframes, Codex, and Figma MCP, allowing me to iterate on both the visual design and the story as the concept evolved.
The result was a workflow that felt much more fluid than the traditional path of Idea → Design → Prototype → Build.
Instead, the project evolved through a continuous loop of Idea → Prototype → Figma → Prototype → Launch.
Memory Bank started as a Makeathon experiment, but quickly became something I genuinely want to build for my own family.
Figma Make prototype (https://rival-froze-78657400.figma.site)
Social post (https://x.com/froessell/status/2067606498163782048)
8
30
732