Deep dives into building with language models — Claude, GPT, and beyond.
A ski marketing page I built to play with scroll animations and chase that wow effect. Every motion runs on native CSS scroll-driven timelines — no JavaScript — and I've rebuilt each one here as a live preview you can scrub yourself.
Read →How I encoded our take-home review into a Claude Code skill that does a fast, consistent first pass — and why, when AI writes the happy path for free, the bar shifts from "can they code" to "can they reason about architecture and trade-offs."
Read →How I split a feature-development agent into five small, single-responsibility skills that hand off compressed JSON — and why dropping context between steps makes the output more honest, not worse.
Read →A content feed had 2.2 million DOM nodes and 1.3 million event listeners. Here's how we diagnosed it, why the masonry grid had to go first, what happened after we shipped, and what the numbers looked like at the end.
Read →How to build a custom Claude Code status line, wire it into settings, and display your own live session metadata at the bottom of the UI.
Read →How I built a fully local RAG system for cocktail discovery — from raw API data to vector embeddings, semantic search, and a streaming chat interface with 3D visualizations. Zero API costs.
Read →How to define, configure, and deploy a Custom GPT using an OpenAI Actions schema — from writing the JSON spec to wiring it up in the GPT Builder UI.
Read →How to build a Claude Code skill that takes a Jira ticket ID, spins up an isolated Claude worktree, names the branch after the ticket, and launches a Portless dev server at a URL you can actually remember.
Read →Astro is the best framework for a content-focused blog in 2025 — zero JS by default, MDX out of the box, and a first-party integration for everything you actually need.
Read →How to write SKILL.md files that turn repetitive CLI workflows into conversational commands — with a real example automating translation key management.
Read →