create-command

Description

Automatically invoked when user wants to create, improve, update, or review Claude Code slash commands. Use when user mentions creating custom commands, slash commands, improving command metadata, fixing command YAML frontmatter, or before creating new slash command. Triggers include create command, new command, slash command, improve command, update command, review command, fix command metadata, command not working. Ensures commands have meaningful metadata with clear trigger words explaining manual invocation, descriptive purpose, minimum 512 character descriptions, proper YAML syntax validation, correct argument handling. Analyzes existing commands to avoid duplicates, suggests improvements, validates naming, handles arguments ($ARGUMENTS, $1, $2), bash execution capabilities, file references (@ prefix), namespacing via subdirectories. Handles personal (~/.claude/commands/) and project (.claude/commands/) commands, asks about supporting files case-by-case, provides preview before creating or modifying.

Tool Access

Full access

Inherits all available tools

Supporting Files

1 file

Additional assets for this skill

Tool Access

This skill inherits all available tools. When active, it can use any tool Claude has access to.

Supporting Assets

references/claude-code-commands-guide.md

Links

GitHub Stats

0 forks

Updated 19 days ago

Related Skills

Agent Development

46.0K

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

From plugin-dev

Command Development

46.0K

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

From plugin-dev

Hook Development

46.0K

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

From plugin-dev