Command Development

anthropics/claude-plugins-officialOfficial

If you're building custom workflows in Claude Code, this is your reference for creating slash commands with the `.claude/commands/` directory structure. It covers YAML frontmatter options like model selection and tool permissions, dynamic argument substitution with $1, $2, and $ARGUMENTS, file references using @ syntax, and inline bash execution for pulling in context like git status. The critical insight here is that commands are instructions for Claude, not messages to users, so write them as directives about what to do. Worth noting this is the legacy format, the newer `.claude/skills/` approach is preferred for new work, but both load identically so existing commands keep working.

skills.sh installs: 7.4K
GitHub stars: 46.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/claude-plugins-official --skill command-development --agent claude-code

Installs into .claude/skills of the current project.

Files

Command Development for Claude Code

Note: The .claude/commands/ directory is a legacy format. For new skills, use the .claude/skills/<name>/SKILL.md directory format. Both are loaded identically — the only difference is file layout. See the skill-development skill for the preferred format.

Overview

Slash commands are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Understanding command structure, frontmatter options, and dynamic features enables creating powerful, reusable workflows.

Key concepts: