Back
Experiments

jhsu.xyz

jhsu.xyz
RoleDesigner & Developer
TeamSolo · Claude
Timeline2 weeks · 2026
View Paper Artboard ↗

jhsu.xyz was designed and built with Claude — from the first wireframe in Paper to the final commit.

The meta-experiment: apply the same rigor to the portfolio as to any product it exists to frame.

Process
Designing the Thing That Frames Everything Else

Designing a portfolio is a strange brief — the work has to be confident enough to have a point of view, but restrained enough that it doesn't become the loudest thing in the room. Every decision — forest green, Geist, no hero image, the discipline around animation — came from that tension: how do you make something opinionated without it upstaging what it's supposed to showcase?

Every page was wireframed in Paper before a line of code was written. That's not a workflow preference — it's what kept decisions intentional. Spacing systems, component hierarchy, content structure: all resolved in the canvas, so implementation had a clear brief to follow. The style guide came after shipping, working backwards from production to document what had already been applied — which also surfaced a handful of one-off styles that had quietly drifted from the system.

Designing the Thing That Frames Everything Else
Outcome
What You Learn When Claude Is the Collaborator

TiltedCard physics on the work cards was prototyped and cut. The spring physics were genuinely fun — but watching them, it was clear the card was becoming the interesting thing. That's the wrong outcome for a portfolio. The ScrambledText hover on the hero name was the only animation that made it through.

C
Claude· snippets of what my Claude usage looks like
can we add TiltedCard to the work cards — want to see how it feels
C
Sure. I'll wire it up with a subtle max tilt and spring physics so it reacts to cursor position without being distracting. One dep to add — @react-spring/web if you don't have it.
go for it
C
Done. Cards now tilt up to 8° on hover with a spring ease-out. Try it and let me know.
played with it — not the direction. the physics are cool but it's pulling attention to the card itself rather than the work inside it
C
Makes sense. The tilt makes the container the interesting thing, which is the opposite of what a portfolio card should do — the work should carry the weight, not the frame. I'll pull the component and the dependency.
yeah do that
C
Removed TiltedCard and @react-spring/web. Cards are back to static — no dead code left.

Working with Claude across the whole build — architecture, implementation, content, code review — reinforced something that applies to any collaborator: velocity and direction are different things. Claude was fast; I was responsible for what we were building toward. The real skill wasn't prompting — it was briefing. Specificity about intent, not just instructions.