Slash Command Creator

Create slash commands that users explicitly invoke with /command-name.

Command vs Skill

File Structure

.claude/
└── commands/
    ├── my-command.md
    └── subdir/
        └── nested-command.md

Creation Process

1. Initialize

Run the init script to create proper structure:

python3 scripts/init_command.py <command-name>

Options:

• --path, -p: Output directory (default: .claude/commands)
• --no-args: Create without argument template

2. Edit the Command

Update the generated file with your instructions.

3. Test

Restart Claude Code, then run /<command-name>.

Command Template

---
name: command-name
description: Brief description of what this command does
arguments:
  - name: required_arg
    description: Something required
    required: true
  - name: optional_arg
    description: Something optional
    required: false
---

# Command Title

[What this command does]

## Process

### 1. [Step Name]
[Instructions with code examples]

### 2. [Step Name]
[Instructions]

## Example Usage

/command-name value1 value2

YAML Frontmatter

Required Fields

Optional Fields

Arguments

Define arguments as array:

arguments:
  - name: issue-id
    description: GitHub issue number
    required: true
  - name: branch
    description: Branch name (default: main)
    required: false

Accessing Arguments

Example: /deploy app prod → $1=app, $2=prod

Body Guidelines

Do:

• Use imperative form ("Run" not "You should run")
• Provide concrete code examples
• Break into numbered steps
• Show example usage

Don't:

• Include "When to use" (goes in description)
• Be vague about commands
• Make it too long

Special Features

Bash Execution

!npm run build
!python scripts/process.py

File References

Review this:
@src/index.ts

Validation Checklist

• Name matches filename (kebab-case)
• Description is clear and actionable
• Arguments have descriptions and required flags
• Body uses imperative form
• Includes example usage