Free tool

Turn a job you keep asking for into a one-word command

If you find yourself typing the same instructions to Claude over and over, save them once. A command is a shortcut: you type one word, like /recap or /standup, and Claude runs the whole set of instructions you saved behind it. This builds you that command as a file, from a few plain answers.

You do not need to know how to code to use this. The bottom of the page tells you where the file goes, including a way that involves no typing at all.

Name it

This is the word you will type to run it, after a slash. Keep it short. Lowercase words with hyphens work best, and this tidies whatever you type into that shape for you.

What do you want to type to run it? A plain verb is good, like recap, standup, or fix issue.

What it does, in a line

A short phrase describing the command. This is also how Claude knows when it might run the command on its own, so say plainly what it is for. Skip it if you only ever want to run it yourself.

What does this command do? (optional) A few words, like write a plain summary of today's work.

What it should do

The instructions Claude follows every time you run the command. Write them the way you would tell a person the steps once, so you never have to type them again.

Write out the instructions. Plain sentences or a numbered list, as long or short as the job needs.

Does it need something to work on?

Some commands act on a thing you name when you run it, like an issue number, a file, or a topic. If yours does, say what kind of thing here and it gets handed to your instructions. Leave this blank if the command always does the same thing.

What will you hand it? (optional) A few words naming the thing, like issue number or topic.

Who can start it

By default you can run the command by typing it, and Claude can also run it on its own when the moment fits. For anything with real consequences, like changing your files or publishing something, you usually want to be the only one who starts it.

Me, or Claude when it fits. You can type it, and Claude may also reach for it on its own when your request matches what it does. Only when I type it. Claude will never run it on its own. Best for commands that change things, so nothing happens unless you ask.

How much thinking power it needs

Simple, repeated jobs run fine and cheap on a smaller model. Genuinely hard reasoning is worth a bigger one. If you are not sure, leave it on the first option.

The same one I am already using. A safe default. It matches whatever you have set for your main session. Fast and cheap. Best for simple, high-volume jobs where speed and cost matter more than depth. Balanced. A sound middle for most real work. Most capable. For the genuinely hard jobs, at a higher cost.

Your command file

This updates as you answer. Nothing here leaves your browser.

Where the file goes

The easy way, with no typing: hit Copy, then paste the whole thing to Claude and say save this as a command I can use on every project. It knows where these files live and will put it in the right place with the right name.

By hand: it is a small text file that lives in a folder called commands inside the .claude folder. For one project, that is .claude/commands in that project. To use the command everywhere, put it in .claude/commands in your home folder instead. The important part is the file name, because the file name is the command: save it as recap.md and you run it by typing /recap. The download is already named for you.

How to tell it worked

Start Claude fresh and type a slash. Your command should show up in the list. Type it and it runs the instructions you saved.

If you told it to take something to work on, type the command and then the thing, like /fix-issue 123. Whatever you type after the command lands in your instructions.

Turn a job you keep asking for into a one-word command

Your command file

Where the file goes

How to tell it worked

Get the next one