What using Claude Code actually looks like
Using Claude Code is a loop: ask, change, check, decide. Here is what a normal session looks like, six commands worth learning first, and how to recover when it goes wrong.
Claude Code skills: building a workflow that runs itself
The control layer of my work system is markdown and small scripts. How a workflow combines Claude Code skills, rules, model routing, and parallel sub-agents.
Most of my AI pipeline isn't AI
By volume, most of my AI pipeline is plain Python. The model is a small, expensive part I call as little as possible. The script-first split, and why it wins.
The Claude Code plugins I built and run
I put the Claude Code tools I reuse across projects into one public toolshed: generators, workflow commands, anti-slop checks, search visibility, rule packs, and prompts.
My AI was smart. It just couldn't see my job.
My work context was scattered across email, meetings, documents, and notes. So I wired it into a private Obsidian vault Claude Code can read.
Four calendar days, one person, one full redesign
A full site redesign in four calendar days, from design system to admin stack. The real question is what product teams should do with the time AI gives back.
A safe way to edit database content with AI coding tools
AI coding tools edit files. Your content lives in a database. This is the pull, diff, push workflow that connects the two without hand-writing SQL against production.
How I built this site with Claude Code.
Three weeks, end to end: PHP backend, vanilla JS, a CSS design system I built by hand, the lot. Claude did most of the typing. The speed is the obvious story. The one worth telling is which decisions I'd still own and which I'd hand back.
Claude Code and the context window on bigger projects
My website is close to a thousand files. I keep Claude Code useful by giving each session one task, naming the files involved, and keeping the project instructions current.
Fixing bugs with Claude Code (without losing your mind)
Something broke. Describe what you expected, show what happened, let Claude investigate, then test the proposed fix.
Claude Code permissions: what to allow and what to block
Claude Code can change real files and run commands. Check the permission mode, protect secrets, review the diff, test the result, and keep a restore path.
What is vibe coding, and when should you use it?
Vibe coding is useful for disposable experiments where failure is cheap. Software you intend to keep needs review, tests, version control, and an owner.
Keeping your Claude Code project organized
Give each file an obvious home, document the stable rules, and test what your deployment actually includes.
Teaching Claude Code your standards with rule files
Use CLAUDE.md for project-wide facts and rule files for detailed standards, including rules that load only for matching paths.
Creating reusable Claude Code skills
If you keep pasting the same prompt, save it as a small Claude Code skill. You can run it with a short command and add templates or scripts later.
The CLAUDE.md file: what to put in it, and what to leave out.
Each Claude Code session starts with fresh context. CLAUDE.md loads the project facts and instructions you want available, while auto memory stores patterns Claude learns.
When Claude Code goes wrong (and it will)
Claude Code will sometimes make the wrong change. Inspect the diff, use checkpoints for session recovery, and keep Git for a durable restore point.
Set up Claude Code so you can review changes as they happen
Keep Claude Code and the result visible at the same time so you can review each change before asking for the next one.
Asking Claude Code to do multiple things at once
Claude Code can delegate independent parts of a task to subagents. Use parallel work for separate research or checks, then review one combined result before editing.
Giving Claude Code better instructions
Give Claude Code the problem, relevant context, and the result you expect. A specific instruction reduces guessing, but you still need to review the result.
How Claude Code sees your files
The folder where you start Claude Code is its main working directory. Keep one project in scope, then add other directories only when the task needs them.
Your first conversation with Claude Code
Create a separate practice folder, then use three prompts to inspect it, create a file, and edit that file while reviewing each action.
Installing Claude Code without the old Node.js setup
Install Claude Code with Anthropic's current native installer on Windows, macOS, or Linux. No Node.js, no npm, and the fixes for when the command is not found.
Opening the terminal for the first time
You need four terminal actions to start Claude Code: open it, run a command, move to the project folder, and close it when you are done.
Meet your AI assistant that actually does things
Claude Code can inspect a project, use development tools, and apply approved changes. Your job is to decide what should happen and check the result.