command-authoring

Create and refactor Claude Code commands with consistent frontmatter and bounded tool usage.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/ririnto/sinon --skill command-authoring-ririnto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: command-authoring
Source: https://github.com/ririnto/sinon/tree/main/plugins/agent-capability-kit/skills/command-authoring
Command: npx skills add https://github.com/ririnto/sinon --skill command-authoring-ririnto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

This Skill helps teams author or refactor Claude Code commands and prompt files with clear arguments, frontmatter, reusable prompt structure, and bounded tool expectations for offline use.

Core Features & Use Cases

  • Standardized command templates that enforce consistent frontmatter and structure.
  • Safe offline authoring that designs commands to be executable without external docs.
  • Review passes to audit existing commands/prompts for clarity, safety, and correctness.
  • Use cases include plugin development, agent capability authoring, and internal tooling for AI-assisted command generation.

Quick Start

Draft or review one Claude Code command file under commands/*.md offline.

Frequently Asked Questions about command-authoring

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

FAQPage Schema
How do I create Claude Code commands with consistent frontmatter and structure?

You refactor Claude Code prompts by running review passes that audit existing command files for clarity, safety, and correctness, then enforcing minimal frontmatter, explicit argument handling, and bounded tool usage to achieve a reusable prompt structure.

What is the best way to structure prompt files for plugin development toolkits?

The best way to structure prompt files for plugin development is to use standardized command templates that enforce minimal frontmatter, reusable prompt structures, and bounded tool expectations, ensuring rigorous command architecture and clear argument handling.

How do I audit existing Claude Code commands for clarity and safety?

To audit existing Claude Code commands for clarity and safety, run review passes that check for consistent frontmatter, explicit argument handling, bounded tool usage, and predictable interfaces to ensure correct offline execution.

When do I need to use bounded tool usage in Claude Code command generation?

You need bounded tool usage in Claude Code command generation when authoring offline commands for plugin development or internal toolkits, ensuring predictable tool interfaces and safe execution without external dependencies.