Create a new Claude Code slash command with proper YAML frontmatter structure. Use when the user wants to add a custom slash command to a plugin. Handles command file creation with description, argument hints, allowed tools, and all advanced features.
Create new Claude Code slash commands with proper YAML frontmatter structure. Use when users want to add custom slash commands to plugins or projects. Handles command file creation with description, argument hints, allowed tools, and advanced features like bash execution and file references.
/plugin marketplace add jpoutrin/product-forge/plugin install claude-code-dev@product-forge-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Create new Claude Code slash commands with proper configuration and advanced features.
Commands stored in your repository and shared with your team.
Location: .claude/commands/ or plugins/<plugin>/commands/
Shows "(project)" in /help.
Commands available across all your projects.
Location: ~/.claude/commands/
Shows "(user)" in /help.
Commands are markdown files with YAML frontmatter:
---
description: Short description shown in /help
argument-hint: <required-arg> [optional-arg]
---
# Command Name
Instructions for Claude when this command is invoked...
| Field | Purpose | Default |
|---|---|---|
description | Brief description of the command | Uses first line from prompt |
argument-hint | Arguments shown in autocomplete | None |
allowed-tools | List of tools the command can use | Inherits from conversation |
model | Specific model string | Inherits from conversation |
disable-model-invocation | Prevent SlashCommand tool from calling | false |
$ARGUMENTSCaptures all arguments passed to the command:
---
description: Fix a GitHub issue
argument-hint: <issue-number> [priority]
---
Fix issue #$ARGUMENTS following our coding standards.
# Usage: /fix-issue 123 high-priority
# $ARGUMENTS becomes: "123 high-priority"
$1, $2, etc.Access specific arguments individually:
---
description: Review pull request
argument-hint: <pr-number> <priority> <assignee>
---
Review PR #$1 with priority $2 and assign to $3.
Focus on security, performance, and code style.
# Usage: /review-pr 456 high alice
# $1 = "456", $2 = "high", $3 = "alice"
Execute bash commands before the slash command runs using the ! prefix.
IMPORTANT: You MUST include allowed-tools with the Bash tool.
---
allowed-tools: Bash(git add:*), Bash(git status:*), Bash(git commit:*)
description: Create a git commit
---
## Context
- Current git status: !`git status`
- Current git diff: !`git diff HEAD`
- Current branch: !`git branch --show-current`
- Recent commits: !`git log --oneline -10`
## Your task
Based on the above changes, create a single git commit.
Include file contents using the @ prefix:
---
description: Review implementation
---
# Reference a specific file
Review the implementation in @src/utils/helpers.js
# Reference multiple files
Compare @src/old-version.js with @src/new-version.js
Organize commands in subdirectories. The subdirectory appears in the description but not the command name.
.claude/commands/
├── frontend/
│ └── component.md # Creates /component (project:frontend)
└── backend/
└── api.md # Creates /api (project:backend)
| Syntax | Meaning |
|---|---|
<name> | Required argument |
[name] | Optional argument |
[--flag] | Optional flag |
[--option <value>] | Optional flag with value |
"" or omit | No arguments |
---
description: Show project status overview
---
Show a summary of the current project status including:
- Git branch and recent commits
- Open issues and PRs
- Build status
---
allowed-tools: Bash(npm:*), Bash(yarn:*)
description: Run tests with coverage
argument-hint: [--watch] [--coverage]
---
Run the test suite with the following options:
- If --watch is passed, run in watch mode
- If --coverage is passed, generate coverage report
Use npm or yarn based on the lock file present.
---
allowed-tools: Bash(git add:*), Bash(git status:*), Bash(git commit:*)
description: Create a conventional commit
argument-hint: [message]
---
## Context
- Current status: !`git status --short`
- Staged changes: !`git diff --cached --stat`
- Recent commits: !`git log --oneline -5`
## Task
Create a git commit following conventional commit format:
- type(scope): description
- Types: feat, fix, docs, style, refactor, test, chore
If $ARGUMENTS is provided, use it as the commit message.
Otherwise, analyze the changes and generate an appropriate message.
---
allowed-tools: Bash(docker:*), Bash(kubectl:*)
description: Deploy to environment
argument-hint: <environment> [--dry-run]
model: claude-sonnet-4-20250514
---
Deploy to $1 environment.
## Pre-flight checks
- Verify current branch: !`git branch --show-current`
- Check for uncommitted changes: !`git status --porcelain`
## Process
1. Build Docker image
2. Push to registry
3. Update Kubernetes deployment
4. Verify rollout status
If --dry-run is in $ARGUMENTS, only show what would be done.
---
description: Review code changes
argument-hint: [file-path]
---
Review the code for:
- Security vulnerabilities
- Performance issues
- Code style violations
- Best practices
If a file path is provided ($1), focus on that file.
Otherwise, review all changed files:
!`git diff --name-only HEAD~1`
Reference style guide: @.claude/STYLE_GUIDE.md
Include extended thinking keywords to trigger deeper analysis:
---
description: Analyze architecture deeply
---
Think step by step about the architecture of this codebase.
Consider:
- Design patterns used
- Potential improvements
- Scalability concerns
For commands to be invocable by Claude via the SlashCommand tool:
description frontmatter fielddisable-model-invocation: true to prevent automatic invocation/compact) are NOT supportedSlashCommand:/commit # Exact match only
SlashCommand:/review-pr:* # Prefix match with any arguments
| Type | Location |
|---|---|
| Plugin commands | plugins/<plugin>/commands/<name>.md |
| Project commands | .claude/commands/<name>.md |
| Personal commands | ~/.claude/commands/<name>.md |
The filename (without .md) becomes the slash command name.
| Aspect | Slash Commands | Skills |
|---|---|---|
| Complexity | Simple prompts | Complex capabilities |
| Structure | Single .md file | Directory with SKILL.md + resources |
| Discovery | Explicit (/command) | Automatic (context-based) |
| Files | One file only | Multiple files, scripts, templates |
Use slash commands when:
Use Skills when:
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.