Command Development

Create Claude Code slash commands with Markdown, YAML frontmatter, and argument handling.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/stellarone/evaluate --skill command-development-stellarone
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Command Development
Source: https://github.com/stellarone/evaluate/tree/main/.agents/skills/command-development
Command: npx skills add https://github.com/stellarone/evaluate --skill command-development-stellarone

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Command Development helps you create reliable, discoverable Claude Code slash commands by teaching the correct file structure, YAML frontmatter configuration, argument handling, file references, and safe bash execution patterns.

Core Features & Use Cases

  • Slash command authoring: Write commands as Markdown instructions for Claude, not user-facing explanations.
  • Configurable frontmatter: Use fields like description, allowed-tools, model, and disable-model-invocation to control behavior and tool permissions.
  • Dynamic command inputs: Build commands that accept $1/$2 positional arguments and $ARGUMENTS, and load context from files via @ syntax.
  • Operational best practices: Add validation, error handling, organization/namespacing, and guidance on interactive flows with AskUserQuestion.

Quick Start

Ask an AI: "Using the Command Development skill, write a Claude Code slash command named /review-pr that accepts a PR number, reads changed files via file references or bash where needed, and outputs a structured review checklist with clear next actions."

Frequently Asked Questions about Command Development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create Claude Code slash commands with YAML frontmatter and dynamic arguments?

To create Claude Code slash commands, you write Markdown instruction files with YAML frontmatter configuring fields like description and allowed-tools, then use positional arguments like $1 and $ARGUMENTS to accept dynamic inputs at runtime.

What is the correct file structure for building reusable slash commands in Claude Code?

Building reusable slash commands requires writing Markdown instruction files for Claude rather than user-facing explanations, structured with YAML frontmatter to control behavior, tool permissions, and model invocation settings.

How do I use file references and bash execution in Claude Code slash commands?

You can load context from files using the @ syntax within command instructions, and execute bash context gathering by configuring the allowed-tools constraint in YAML frontmatter to safely manage execution permissions.

Can I use interactive workflows with AskUserQuestion in custom Claude Code commands?

Yes, custom Claude Code commands can guide interactive workflows by implementing AskUserQuestion behavior, allowing the command to prompt users for required input when dynamic arguments are not provided at invocation.

What are the limitations when configuring tooling permissions with allowed-tools in slash commands?

The allowed-tools constraint in YAML frontmatter governs safe bash execution and tool access, meaning commands are restricted to only the explicitly permitted tools, preventing unauthorized filesystem or system access during dynamic argument processing.

Does Claude Code slash command development support namespacing and argument hints?

Yes, slash command development supports namespacing and organization patterns for discoverability, and you can document expected inputs using the argument-hint field to help users understand required positional arguments.