Slash Commands | Claude Code Recap Card M09

CC 2.1.3: Skills use .claude/skills/<name>/SKILL.md; set disable-model-invocation: true for manual invocation only. Legacy .claude/commands/*.md files remain supported. The /name syntax and behavior are identical.

Principle

A slash command is a Markdown file that defines a workflow. Claude executes it as if it had received that text as a prompt, with the ability to pass dynamic arguments.

File locations

.claude/skills/             # Project skills
├── commit/SKILL.md         → /commit
├── review-pr/SKILL.md      → /review-pr
└── deploy/SKILL.md         → /deploy

~/.claude/skills/           # Personal skills
├── release/SKILL.md        → /release
└── sync/SKILL.md           → /sync

Global commands are available in all sessions, regardless of the project.

Invocation and arguments

/commit                    # No argument
/deploy production    # Positional argument
/release minor             # Version bump

In the Markdown file, arguments are accessible via variables:

Deploy to environment: $ARGUMENTS[0]
With strategy: $ARGUMENTS[1]

If no argument provided: use "staging" by default.

The $0, $1 syntax is equivalent to $ARGUMENTS[0], $ARGUMENTS[1]. The old dot notation ($ARGUMENTS.0) is deprecated since v2.1.19.

Recommended structure

# Command Name

## Objective
What this command does in one sentence.

## Process
1. **Step 1** — detailed instructions
2. **Step 2** — detailed instructions
3. **Step 3** — detailed instructions

## Arguments
- $0: target environment (default: staging)

## Output format
Description of the expected result.

Recent native commands

These two are built-in commands. /simplify, /batch, /loop and /debug are bundled skills that work like your own.

Command	Usage
`/goal [condition]`	Autonomous multi-turn mode: Claude works until the condition is met, with a live elapsed/turns/tokens overlay
`/scroll-speed`	Interactive slider to tune mouse wheel scroll speed with live preview

Useful commands to create

Command	Usage
`/commit`	Automatic conventional commit
`/review-pr`	PR review against project criteria
`/release [patch	minor
`/sync`	Multi-file consistency check
`/security-check`	Quick config scan

Command vs skill vs agent

Mechanism	When to use
Command	One-off workflow, procedure to follow
Skill	Reusable knowledge + embedded resources
Agent	Recurring specialist with own memory

A skill directory can include additional reference files and scripts, whether invoked by the user or model. Agent memory is a separate persistent mechanism.

Practical tips

One command, one responsibility. As soon as a command does two distinct things, split it. Name with an action verb first (commit, release, sync) so that the intent is immediately readable in the list of available commands.