Command Development FAQs

Question 1

What is the difference between project and personal commands?

Accepted Answer

Project commands are stored in `.claude/commands/` and are shared with your team via the repository. Personal commands reside in `~/.claude/commands/` and are available to you across all projects on your local machine.

Question 2

What does the Command Development skill do?

Accepted Answer

This skill provides the framework and best practices for building custom slash commands within Claude Code. It covers how to use YAML frontmatter for configuration, handle dynamic arguments like $1 and $ARGUMENTS, and incorporate file references using the @ syntax.

Question 3

How does this skill improve my AI coding workflow?

Accepted Answer

It transforms Claude Code into a personalized CLI by allowing you to define reusable, consistent instructions. This reduces prompt engineering time and ensures that Claude consistently follows your project's specific standards and logic.

Question 4

When should I use this skill?

Accepted Answer

Use this skill whenever you want to automate repetitive workflows, standardize team prompts, or create complex instructions that require specific tool access, model selection, or real-time repository context through bash execution.

Question 5

What is the golden rule for writing slash commands?

Accepted Answer

Commands are instructions FOR Claude, not messages FOR the user. You should write command content as direct instructions telling the AI what to do (e.g., 'Review this code...') rather than descriptive text for the human operator.

Command Development

Command Development

概要

主な機能

ユースケース

概要

主な機能

ユースケース