Latest Blog Posts & Articles

stockpile logo image

stockpile: know what’s in your arsenal

At some point, I stopped knowing what was on my Mac. A tool here, a dependency my agent dropped in there. Collectively, a mystery. I was losing track. To help, I created stockpile.

Claude code mascot

So I Put My AI Skills in a Marketplace

Everyone's building custom skills for their AI coding assistants right now. Commit helpers, linting rules, project scaffolding. Little markdown files that make Claude Code do things your way instead of the default way. I've been doing the same thing. But the more skills I wrote, the more I wanted them to follow me between machines…

Three AIs Missed It. One Human Didn’t

I had done everything right. Or at least, everything the current playbook says to do. Used AI to fill the gaps, reviewed it myself, then handed it off to more AI.

Free note papers business plan

AI Chose Your UI (Did It Choose Wrong?)

After years of building, maintaining, and supporting in-house design systems with real tokens, governance, versioning, support, and contribution models, I recently found myself building with Tailwind and shadcn. Thanks, AI!

close up shot of keyboard buttons

npm uninstall humans

In software, a dependency is a risk you accept. It's a package you didn't write, maintained by someone you've never met, that can break your entire application if it disappears. Good engineering means knowing which dependencies are worth the risk and which ones aren't. Right now, I'm watching our industry decide that people aren't worth…

Chalkboard with math is hard written on it.

You’re Automating the Wrong 70%

I came across a Medium post titled "AI Will Replace 70% of Design System Work." The premise is that most design system work, documentation, component building, token management, accessibility audits, is "structurally automatable," and that the real value lies in governance. The author argues that teams need to move "upward from execution to orchestration" or…

Your Design System’s Got Skills?

I've been tinkering with something lately that I think more design system teams should pay attention to. I'm trying to teach AI how my design system works through Claude skills and Cursor rules.

Let Me Reintroduce Myself

I came across a post by Cassidy Williams a few weeks ago about LLM discoverability. The gist: she asked ChatGPT some tech discovery questions, noticed it didn't recommend her, then asked why. The AI gave her a list of things to fix. She fixed them. It worked.

The AI Productivity Paradox

Satya Nadella said AI would fuel a "creative revolution." GitHub told us Copilot would let developers "focus on creative and strategic work." Sam Altman measures ChatGPT's success by the percentage of human work it can accomplish. So why am I spending more time reviewing and fixing AI output than I ever imagined?

Why AI Needs UX Developers

The UX developer role has always been hard to explain to everyday folks. “So you design stuff?” Not exactly. “So you code stuff?” Sort of. For years, people who sit between design and engineering have fought for a seat at a table that wasn’t really built for them. Then AI showed up and flipped the…