Tagged · 7 notes
#Claude.
Everything tagged Claude, wherever it's filed, newest first.
When a long back-and-forth with an AI finally lands somewhere good, the method is worth more than the answer. How I pull the method out and turn it into a prompt I can run again.
Thread: Building with Claude and MCP ↗
A three-phase reflection prompt for a pattern you keep falling into, built to offer its reads as guesses you can confirm or reject rather than pronouncements.
Thread: Prompts that hold up a mirror ↗
A custom slash command is a saved prompt you run with a slash. How they work in Claude Code now that they've been folded into skills, and which of the ones in my notes actually have a job.
Thread: Building with Claude and MCP ↗
My notes on safe updates were written for a big team with canary releases and approval chains. Here's the same idea cut down for one person with a project that still has to work tomorrow.
Thread: Dev habits for a team of one ↗
My old CLAUDE.md template tried to hold everything. The one that runs this blog is about twenty lines. Here's where the file lives, what earns a line in it, and what doesn't.
Thread: Building with Claude and MCP ↗
How to add an MCP server to Claude Code or Claude Desktop, where the config actually lives, and the short checklist I run when a server won't show up.
Thread: Building with Claude and MCP ↗
A prompt and a small Python toolkit that turn one long AI conversation into a numbered, source-cited project folder you can build a book from.
Thread: Prompts for plans, apps and side hustles ↗