CREATOR COLUMN |
How to Actually Use Claude Code (Without Being a Developer) |
|
Twelve weeks ago, the terminal scared me. |
I am not a developer. Not overly technical. The CLI looked like Greek. |
Today, Claude Code runs about 80% of my content business. |
The fear is the only thing in your way. Claude Code is genuinely easy. The CLI is just another text box. You type what you want. Claude does it. |
Six weeks ago I co-wrote a piece called Beginner to Advanced. I was the beginner. Six weeks later, I am still not the advanced one. But Claude Code now runs most of what I do. |
Below are the 6 features that take you from terrified to fluent. If you would rather watch than read, I recorded a walkthrough on YouTube with live demos inside Claude Code. |
1. Pick how you want to run it |
Four options. Same engine, different shoes. |
Terminal (CLI) is the fastest and most full-featured. Open Terminal on Mac (Spotlight search "Terminal"). Windows wants WSL or PowerShell. Run curl -fsSL https://claude.ai/install.sh | bash. When that finishes, type claude. |
|
Desktop app gives you a native Mac or Windows app with a clean visual interface and no terminal anxiety. Go to claude.ai, download, sign in. |
|
VS Code extension runs the same engine inside your code editor. You see Claude editing files in real time and approve each change before it sticks. Install the terminal version first, then add "Claude Code for VS Code" from the marketplace. |
|
Web app at claude.ai/code runs in your browser. No installation. The easiest way to try without committing. |
|
If you start today, use the desktop app. |
|
Claude Code runs on plain text files ending in .md. You do not write code. You write words. |
The most important file is CLAUDE.md. It sits in your project folder. Claude reads it before every reply. |
|
A good CLAUDE.md tells Claude who you are, how you write, what to never do, and how to handle every recurring task in your business. |
Without one, Claude has no idea who you are. |
The build is simple. Create the file. Start writing. Then tell Claude: |
"When you figure out a recurring pattern in our work, update CLAUDE.md so we do not have to redo this every session." |
It builds itself as you work. |
If you want a strong template, save Boris Cherny's CLAUDE.md. He built Claude Code. His version is engineering-focused, but the structure (workflow rules, task management, core principles) translates to any kind of work. |
|
Run /init to write the first version. The rest writes itself. |
|
3. Use Plan Mode for everything |
This is what stops you being scared. |
Boris Cherny built Claude Code. The first rule in his own CLAUDE.md under "Workflow Orchestration" is "enter plan mode for any non-trivial task". Build this rule into every workflow you run. |
Without a plan, Claude might do something you did not intend. Like delete a file. Or rewrite something you wanted left alone. |
|
Plan Mode shows you exactly what Claude will do before it acts. You read the plan. You approve. Claude executes. |
If the plan is wrong, tell Claude what to fix. It rewrites the plan. You loop until it is right. |
Activate it by typing /plan, or hit Shift+Tab to toggle mid-session. |
There is a second reason: it saves usage credits. A failed run costs more tokens than 10 minutes of planning. If you are using Claude Code seriously, you will hit usage limits fast unless you plan first. |
4. Skills turn Claude into your specific team |
A skill is a folder of instructions. Same idea in Chat, Cowork, and Code. But Code is where it gets interesting, because Claude Code can hit APIs the others cannot. |
|
The Gemini API is my favourite. Gemini is multi-modal where Claude is not. Feed it an Instagram Reel or a YouTube video, pair it with Apify for scraping, and you have a content-analysis machine running inside your terminal. |
Paste your Gemini key into Claude Code and Claude becomes a cyborg LLM. |
Last week I gave away a load of my Claude skills for free. Drop them into Claude Code, Cowork, Chat, or any interface that supports skills. Writing, design, video, plus a few that would bore you. |
Grab the skills library at github.com/charlie947/social-media-skills. |
|
5. Custom commands save your prompts |
Most of the time in Claude Code, you just type. "Help me do something." Claude reads CLAUDE.md, picks the right skill, and goes. |
There is a layer above that. Custom slash commands. |
|
Claude Code already ships with hundreds of built-in slash commands. Session tools, task tools, code review, init, bug reports. You did not have to build any of these. They are sitting there waiting. |
Type / and have a scroll. There is probably already a command for the thing you were about to write a 200-word prompt for. |
Where it gets interesting: you can add your own. A custom command is one markdown file saved to ~/.claude/commands/. It shows up in the same menu as the built-ins, ready to fire. |
To create your own, do not write the file by hand. Build the workflow with Claude first. When it works end to end, say: "save this as a custom command we can execute." Claude writes the file, names the command, wires it up. |
6. Sub-agents are how Claude becomes a team |
A sub-agent is a specialist Claude that runs in its own context. |
You hand it a task. It goes off, does the work, reports back to the main session. |
Sub-agents are good for research, scraping, drafting, and review. Anything where you want focus without polluting the main conversation. |
An agent team is a full production pipeline. Multiple agents, working in parallel, each with their own role and context, all coordinating through a shared task list |
Build them by describing what you want in plain English, like briefing a clever new hire. |
You knew the features existed. You had an idea of what to build. Tell Claude to do the rest. |
That is the whole trick. |
The gap is smaller than you think |
Twelve weeks ago, the terminal was scary. |
Now Claude Code runs 80% of a content business. |
The gap between "I cannot do that" and "I run my business on this" was weeks of typing what I wanted into a text box. |
If you have been avoiding Claude Code because it looks technical, this is the article that says you can stop. |
Have a play with it. If you want the deeper builds, the frameworks, and the next experiments as I run them, I write about all of it on MarTech AI! |
-Charlie |
Want even more from Claude? Get 60 ways you can put Claude to work right now! |
|
