Your AI Skills Setup Is Probably Wrong
I ran 51 multi-turn evals across 4 configurations and read Claude Code's source. Skills and CLAUDE.md are both just prompt. The difference is whether the prompt reaches the model.
Codeminer42's Engineering Blog
What Codeminer42 engineers dig up at work: field notes on Rails, AI tooling, security, and keeping product teams shipping.

I ran 51 multi-turn evals across 4 configurations and read Claude Code's source. Skills and CLAUDE.md are both just prompt. The difference is whether the prompt reaches the model.
I asked an LLM how much my neighbor's house might be worth, a 300m² place with 3 bedrooms, not too old, built in the early 2000s. It gave…
I used the Chrome DevTools MCP to configure a WordPress plugin on a production site - logging in, changing settings, adding widgets, uploading plugins, purging cache - all from Claude Code without touching the browser.
I installed Polylang on our production blog and immediately regretted it. So I built our own multilingual WordPress plugin in two days with Claude Code. Some context: we…
A lot has been talked about what the best way is to drive when practicing agentic engineering. Some people still find it frustrating because of their expectations: they…
Running Two Claude Code Accounts on the Same Machine If you have two Anthropic accounts, say, a personal one and a work one, you've probably hit the same…