Command Development

Create reusable Claude Code slash commands with Markdown, frontmatter, args, and bash integration.

1|Updated May 4, 2026
One-click install
npx skills add https://github.com/open-session/os_design_system --skill command-development-open-session
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Command Development
Source: https://github.com/open-session/os_design_system/tree/main/.claude/plugins/plugin-dev/skills/command-development
Command: npx skills add https://github.com/open-session/os_design_system --skill command-development-open-session

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you design clear, reusable Claude Code slash commands that turn repeated workflows into reliable, shareable prompts. It reduces confusion around command format, configuration, and execution by showing how to structure commands the way Claude expects them.

Core Features & Use Cases

  • Command File Structure: Define Markdown commands with the right frontmatter and prompt body so they appear correctly in Claude Code.
  • Arguments and References: Use positional arguments, argument hints, file references, and bash output to make commands flexible and context-aware.
  • Plugin-Ready Patterns: Organize commands for teams and plugins, validate inputs, and integrate with scripts, skills, agents, and hooks.
  • Use Case: A team can create a repeatable review command that loads repository context, checks changed files, and produces consistent feedback without rewriting the workflow each time.

Quick Start

Create a Markdown command with a clear description and then write direct instructions that tell Claude exactly what action to perform.

Frequently Asked Questions about Command Development

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

FAQPage Schema
How do I create reusable slash commands in Claude Code?

Create reusable Claude Code slash commands by authoring Markdown files with valid YAML frontmatter and direct prompt instructions. This standardizes command structure so Claude interprets arguments, file references, and execution rules correctly.

What is frontmatter and how does it structure prompt engineering in Claude Code commands?

Frontmatter is YAML metadata at the top of a Markdown command file that defines configuration for prompt engineering. It standardizes argument hints, tool restrictions, and resource validation so commands execute reliably without ambiguity.

How do I pass arguments and file references to a Claude Code plugin command?

Pass arguments and file references to a Claude Code plugin command using positional arguments and argument hints defined in the frontmatter. The command body can then reference these inputs to load context-aware bash output or repository files dynamically.

Can I package interactive workflows and inline bash execution into a single Claude Code command?

Yes, you can package interactive workflows and inline bash execution into a single Claude Code command by structuring the Markdown prompt body with direct instructions. This allows the command to run scripts, validate inputs, and generate consistent feedback automatically.

What are the limitations when defining tool restrictions in Claude Code command frontmatter?

Limitations when defining tool restrictions in Claude Code command frontmatter include the need for careful validation to avoid error-prone execution. If tool permissions or file resource paths are not explicitly restricted, the command may fail or behave unpredictably.