Author custom Claude Code slash commands as reusable Markdown prompt templates. Covers frontmatter configuration, argument handling, variable substitution, and workflow automation patterns. Invoke when designing new commands, debugging command syntax, or converting repetitive prompts into reusable shortcuts.
Creates reusable Claude Code slash commands from Markdown templates to automate repetitive workflows.
npx claudepluginhub aeyeops/aeo-skill-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/examples.mdreferences/patterns.mdreferences/template.mdCreate effective Claude Code slash commands - reusable prompt templates stored as Markdown files.
| Scope | Location | Label in /help |
|---|---|---|
| Project | .claude/commands/*.md | (project) |
| Personal | ~/.claude/commands/*.md | (user) |
---
description: Brief description shown in /help
argument-hint: <required> [optional]
allowed-tools: Bash(git *), Read, Edit
model: claude-sonnet-4-20250514
disable-model-invocation: false
---
Your prompt template here with $ARGUMENTS or $1, $2, etc.
| Variable | Description | Example |
|---|---|---|
$ARGUMENTS | All args as single string | /cmd foo bar -> "foo bar" |
$1, $2... | Positional args | /cmd foo bar -> $1="foo", $2="bar" |
@path/file | Include file contents | Review @src/main.py |
`!command` | Execute bash, include output | `!git status` |
| Field | Purpose | Default |
|---|---|---|
description | Shown in /help, enables discoverability | First line of prompt |
argument-hint | Shows in autocomplete | None |
allowed-tools | Restrict tool access | Inherits from conversation |
model | Override model | Inherits from conversation |
disable-model-invocation | Prevent auto-invocation | false |
$ARGUMENTS for flexibilityUse slash commands for:
Use Skills instead for:
/review-pr not /rpConsult these resources when creating slash commands:
examples.md - Read when you need complete working examples or want to show the user reference implementations. Covers git workflows, code review, documentation, testing, scaffolding, and utilities.
patterns.md - Read when implementing specific features: variable handling, file inclusion (@path), bash execution (`!cmd`), tool restrictions, multi-step workflows, or output formatting.
template.md - Starting template for new commands. Copy and customize the structure.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
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.