DesignCode

I recorded a 13-min video on how to build a 3D website with Claude Code and Opus 5.5 The whole workflow: → find 3D references on Mobbin, right inside Claude → one prompt with the references, the plan and the camera → pick the right medium: what's real 3D, what's painted light, what's a cut-out → the dream loop: Opus screenshots its own build, scores it against a target image, and fixes what's off → furnish the room, then fix the mistakes and make it fast on phones Round 1 scored 4.6. The dream loop took it past 8.

Figma Weave designed this whole page. One canvas made the same frame in four seasons, the depth maps and the motion studies. Then I handed that folder to Claude Code to build it. Prompt below ↓ See the workflow: app.weavy.ai/flow/6yKBise7YH…

this is going to instantly avoid ai slops. url: benji.org/stageshow nitter.cf/benjitaylor/status/211…

The amount of detail in this is staggering. Unreal MCP for Claude Code is my next step into game dev. repo: github.com/EpicGames/unreal-… nitter.cf/xikhar/status/21145672…

This kinda went viral. Some thought it wasn't a real game so here's another gameplay trailer made with Opus 5.5. All three.js.

I got the chance to work on the landing page for a new video model from a lab that grows real brain cells. insanely cheap at half a cent a second. had a lot of fun creating three.js concepts with opus 5.5. here's my workflow. check out mischief-1: app.tbc.co

I've always wanted to play D&D with my kids with AI as the game master. So I made one with Opus 5.5.

I asked @Dola_Trend to create these launch visuals. It blew my mind. It only took one prompt and one screenshot and it produced 3 campaign routes and a Seedream 5.0 Pro hero for each. Here's the workflow, step by step 👇

I made seven small 3D worlds, each from a single image. One picture per world, one per character. @Viggle_PINOC by @ViggleAI, running on their new JST-2 world model, turned them into Gaussian splat worlds and rigged characters that run in the browser. Then Claude Code, connected to the PINOC MCP, walked Fern through every world and directed the camera. All of this is 3D. Imagine it as a landing page, a game or a demo people can explore. viggle.ai/pinoc/app

I made a skill called HTML Reel that turns a post, a video or a landing page into a reel. It writes the script, builds every scene in HTML and cuts each move on a word. Once you record your take, it retimes everything to your voice. fil.design/skills/html-reel

I made these landing pages with MiniMax M3.1 Flash, at a fraction of the cost of frontier models. Three keyboard sites, a SaaS page, a rainy 3D Singapore at night and a little 3D lighthouse game. My favourite is the exploded keyboard one. I made one render of the keyboard in MiniMax first, and every painting, photo and film came from that render, so it's the same board in every room. $0.15 per 1M input tokens, $0.60 per 1M output. Here's the whole process, prompts included.

I made a skill that turns your app into a demo in HTML. So they stay sharp at any size, loop, scrub, jump to any step and stand still for reduced motion. I open-sourced it as a skill: fil.design/skills/html-demo

Me explaining my entire workflow in a 38-min tutorial

You can pretty much reverse engineer any device in your home and build a mac app around it. Applied to lights, doors, ac and even the future robot helper. Here's the skill: github.com/morluto/rea It's crazy what you can build nowadays with a skill and a few prompts.