What it is
Command Development is a skill in Claude Code's plugin-dev plugin. It gives comprehensive guidance on creating slash commands, which are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Claude Code activates it when a user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", or "organize commands". It also activates for questions about command frontmatter, file references, bash execution in commands, interactive commands or AskUserQuestion, and command development best practices.
The core idea is that commands are instructions FOR Claude, not messages to the user. When a user invokes /command-name, the command content becomes Claude's instructions. Commands can live in three places:
- .claude/commands/ for project commands, shown as "(project)" in /help
- ~/.claude/commands/ for personal commands, shown as "(user)"
- plugin-name/commands/ for plugin commands, shown as "(plugin-name)"
Commands are .md files with optional YAML frontmatter. The supported fields are description, allowed-tools, model (sonnet, opus, haiku), argument-hint and disable-model-invocation. Commands can use dynamic arguments ($ARGUMENTS for all arguments as one string, and $1, $2, $3 for positional ones), include file contents with @path, and execute bash inline with the !` syntax. They can be organized flat or namespaced in subdirectories.
For plugins, the skill covers:
- the ${CLAUDE_PLUGIN_ROOT} environment variable, which resolves to the plugin's absolute path
- automatic command discovery from commands/
- configuration, template and multi-script patterns
- integration with plugin agents, skills and hooks
- validation patterns for arguments, file existence, plugin resources and error handling
The skill uses progressive disclosure. SKILL.md (~2,470 words) holds the core concepts. Reference files hold detailed specifications, including frontmatter-reference.md and plugin-features-reference.md. Example files (simple-commands.md and plugin-commands.md) hold complete working commands. Claude loads the references and examples as needed.
Who it's for
- Claude Code users who want to create custom slash commands
- Teams sharing project-specific workflows via .claude/commands/
- Plugin developers bundling commands with their Claude Code plugins
- Developers integrating commands with plugin agents, skills, and hooks
Requirements
Requirements
- Claude Code
- Part of the plugin-dev plugin in the anthropics/claude-code repository
- Plugin-specific features (${CLAUDE_PLUGIN_ROOT}, plugin command organization) apply to commands bundled in a plugin's commands/ directory
هاي سكيل لـ Claude Code بتساعدك تعمل slash commands خاصة فيك. بتشرحلك شكل الملف والـ frontmatter والـ arguments، وكيف تربط الأوامر مع ملفات وأوامر bash ومكوّنات البلَغِن.
Examples
Command using $ARGUMENTS
markdown---
description: Fix issue by number
argument-hint: [issue-number]
---
Fix issue #$ARGUMENTS following our coding standards and best practices.What it does: Captures all arguments as a single string. Invoking /fix-issue 123 expands to "Fix issue #123 following our coding standards...".
Invoking a command with positional arguments
Prompt> /review-pr 123 high aliceExpected output: With a command using $1, $2, $3, this expands to "Review pull request #123 with priority level high. After review, assign to alice for follow-up."
Command with bash execution
markdown---
description: Show Git status
allowed-tools: Bash(git:*)
---
Current status: !`git status`
Recent commits: !`git log --oneline -5`What it does: Runs git commands inline and includes their output as context. allowed-tools restricts Bash to git commands only.
Plugin command using ${CLAUDE_PLUGIN_ROOT}
markdown---
description: Analyze using plugin script
allowed-tools: Bash(node:*)
---
Run analysis: !`node ${CLAUDE_PLUGIN_ROOT}/scripts/analyze.js $1`
Review results and report findings.What it does: Executes a script bundled with the plugin using a portable path. This avoids hardcoded paths across installations.
Related
Skill internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident rep
Skill skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better t
Skill Agent Development
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
Skill Skill Development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Skill Writing Hookify Rules
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Skill access
Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.