🎯

command-development

🎯Skill

from s-hiraoku/claude-code-harnesses-factory

VibeIndex|
What it does

Guides creating slash commands for Claude Code as reusable Markdown-based prompts with configurable YAML settings for custom command workflows.

πŸ“¦

Part of

s-hiraoku/claude-code-harnesses-factory(9 items)

command-development

Installation

Add MarketplaceAdd marketplace to Claude Code
/plugin marketplace add s-hiraoku/harnesses-factory
Claude CodeAdd plugin in Claude Code
/plugin search
Install PluginInstall plugin from marketplace
/plugin install cc-version-updater
Install PluginInstall plugin from marketplace
/plugin install cc-version-updater@s-hiraoku/harnesses-factory
πŸ“– Extracted from docs: s-hiraoku/claude-code-harnesses-factory
1Installs
-
AddedFeb 4, 2026

Skill Details

SKILL.md

This skill guides creating slash commands for Claude Codeβ€”reusable Markdown-based prompts with YAML configuration. Use when building custom commands, designing command workflows, or extending Claude Code functionality.

Overview

# Command Development

Overview

Commands are reusable prompts defined as Markdown files with optional YAML frontmatter.

Critical: Commands are instructions FOR Claude, not messages TO users.

Command File Structure

```markdown

---

description: Brief help text shown in /help

allowed-tools: Bash(git:*), Read

model: sonnet

argument-hint: [file-path] [options]

---

Instructions for Claude here.

Analyze the file at $1 and provide...

```

File Locations

| Location | Scope |

|----------|-------|

| .claude/commands/ | Project (shared via git) |

| ~/.claude/commands/ | Personal (all projects) |

| plugin/commands/ | Plugin distribution |

Frontmatter Fields

| Field | Purpose |

|-------|---------|

| description | Help text for /help command |

| allowed-tools | Restrict tool access (e.g., Bash(git:*)) |

| model | Specify model: haiku, sonnet, opus |

| argument-hint | Document expected arguments |

| disable-model-invocation | Prevent programmatic calls |

Dynamic Features

Arguments

```markdown

# All arguments as single string

Process: $ARGUMENTS

# Positional arguments

File: $1

Options: $2

Mode: $3

```

File References

```markdown

# Include file contents

Review this code: @src/main.ts

# Argument-based reference

Analyze: @$1

```

Inline Bash Execution

```markdown

# Current context

Current branch: !git branch --show-current

Recent commits: !git log --oneline -5

```

Naming Conventions

Use verb-noun format:

  • review-pr.md
  • generate-tests.md
  • fix-issue.md

Organization

```

.claude/commands/

β”œβ”€β”€ review-pr.md # Flat for <15 commands

β”œβ”€β”€ git/ # Namespaced for 15+

β”‚ β”œβ”€β”€ commit.md # Becomes /git-commit

β”‚ └── push.md # Becomes /git-push

└── testing/

└── run-tests.md # Becomes /testing-run-tests

```

Best Practices

  1. Single responsibility - One task per command
  2. Document arguments - Always use argument-hint
  3. Validate inputs - Check before processing
  4. Restrict tools - Use allowed-tools appropriately
  5. Clear naming - Verb-noun format