Claude Code Custom Commands Generator
Answer 7 quick questions and get a custom Claude Code slash command with valid frontmatter, ready to drop into .claude/commands/.
Question 1 of 7
What do you want to type to run it?
Lowercase letters, numbers, and hyphens only - this becomes both the file name and the command. We'll clean it up automatically.
/my-command
7 quick questions - free, no sign-up, nothing leaves your browser
FAQ
What is a custom Claude Code command?
A markdown file that turns a prompt you use often into something you type as /your-command-name. Claude Code reads the file's YAML frontmatter to decide things like whether it can trigger the command on its own, then runs the markdown body below it as the prompt, with any typed arguments substituted in.
Where do I save the generated command file?
.claude/commands/<name>.md for a command shared with your team (commit it to the repo), or ~/.claude/commands/<name>.md for a personal one that applies to every project on your machine but isn't shared. The generator shows the exact path for whichever scope you picked.
What do $ARGUMENTS and $1 mean in a command file?
$ARGUMENTS expands to everything typed after the command name, as one string. $1 and $2 are shorthand for the first and second word on their own, so you can address them separately - wrap a multi-word value in quotes to keep it as a single argument. This generator scans your prompt for whichever ones you used and writes a matching argument-hint automatically.
Are custom commands the same thing as skills?
Custom commands now run under the hood as part of Claude Code's skills system, and a skill folder supports a few extra features a plain command file doesn't. But a file at .claude/commands/your-command.md still works exactly as it always has, and that's the simpler format most people mean by "a custom command" - which is what this generator produces.
Is this Claude Code commands generator free?
Yes - free, no sign-up, and nothing you type leaves your browser; the file is assembled locally. ClockedCode separately sells a complete done-for-you Claude Code setup, but the generator itself is not gated.
This generator builds a custom Claude Code slash command: a .md file that turns a prompt you use often into something you type as /your-command-name. Seven questions, mostly click-only, and the two free-text ones (the command name and the prompt itself) come with a live preview and default text so you always end up with something that works, even if you skip straight through.
The frontmatter is where hand-written commands usually go wrong, because half the fields are easy to guess incorrectly and the other half most people don't know exist. This generator only writes the fields your answers actually call for: a description (always, since that's what tells Claude when to reach for the command on its own), disable-model-invocation when you want it to run only when you type it, allowed-tools when you picked specific tools it can use without asking, and model when you want it pinned to a tier. It also reads your prompt for $ARGUMENTS, $1, or $2 and writes a matching argument-hint automatically - most guides skip this field entirely, and it's the one that makes your command autocomplete correctly.
$ARGUMENTS is everything typed after the command name; $1 and $2 (shorthand for the first and second word on their own) let you address individual arguments separately, and wrapping a multi-word value in quotes keeps it as one argument instead of splitting on the space. Worth knowing if you've read an older writeup on this: custom commands now live under the hood as part of Claude Code's skills system, but a file at .claude/commands/your-command.md still works exactly the way it always has - that's the format this generator produces, because it's still what most people mean by "a custom command."
The recommended path is the paste prompt: it tells Claude Code to check whether the target file already exists before writing it, confirm every frontmatter field is supported by the version you're running, and hand you the exact command to try once it's saved. That verification step is the part a copy-pasted gist can't do for you.
Once you have a command that runs on your terms, the next thing worth locking down is what Claude does without being asked - the Claude Code hooks guide covers the lifecycle events that fire automatically, and the CLAUDE.md generator builds the instruction file that shapes everything in between.
I run Claude Code daily and this generator writes the same frontmatter conventions my own commands use. If you want the finished version of the whole idea - a tuned CLAUDE.md, a tuned settings.json, and the full vetted tool stack, installed in one paste - that is what ClockedCode is. The link is at the bottom of this page.
By Neo Zino - builder of ClockedCodeOther free tools
Statusline Generator
Toggle the segments you want, watch the exact statusline render live, then copy the tested script and settings.json block.
Try toolConfig generatorsettings.json Generator
Pick permission rules, hook presets, env vars, and a model override one step at a time, then copy or download the finished settings.json.
Try toolConfig generatorCLAUDE.md Generator
Answer 7 quick questions, get a tuned CLAUDE.md for your project in 30 seconds.
Try toolTemplate libraryClaude Code Templates
A curated library of copy-paste Claude Code templates: subagents, hooks, slash commands, settings, and CLAUDE.md starters, each one explained and pulled from a setup that gets used every day.
Try toolToken scannerUsageCut
Scan your Claude Code setup in 30 seconds and see exactly what is burning your tokens - bloated context, heavy MCP servers, and settings quietly draining your usage limits.
Try tool