Samuel Lawrentz · engineer & team lead · 9+ years

I build interfaces,
systems, and teams.

Nine years of shipping pixel-perfect UIs and the systems behind them. I write monthly about the craft - code, tools, and leading engineers.

Sep 12, 2026

claude plugin eval - Finally a Way to Prove Your Skill Does Anything

Claude Code can now run your plugin or skill against test cases, score the runs, then run the same cases without it and show the delta. I wrote an eval for one of my skills. Here is the file format, and the wall I hit.

Read post

Writing

All posts

Projects

GitHub

Hacks

Browse all
00:00

This helps me increase the session time of my site. Thank you!

Can you stay a bit longer?