Creating custom Vue composables with proper patterns. Use when building reusable stateful logic, shared state management, or encapsulating feature-specific behavior.
/plugin marketplace add leeovery/claude-nuxt/plugin install leeovery-claude-nuxt@leeovery/claude-nuxtThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/composables.mdCreating reusable stateful logic via Vue Composition API.
composables.md - Patterns, naming, state management, best practices
State defined outside function persists across all callers:
// app/composables/useUser.ts
let user = ref<User>() // Singleton - shared across app
export default function useUser() {
const setUser = (data: BaseEntity) => {
user.value = User.hydrate(data)
}
const clearUser = () => { user.value = undefined }
return { user, setUser, clearUser }
}
State defined inside function - new instance per call:
// app/composables/useCounter.ts
export default function useCounter(initial = 0) {
const count = ref(initial) // Fresh per call
const increment = () => count.value++
const decrement = () => count.value--
return { count, increment, decrement }
}
| Convention | Example |
|---|---|
| File name | useUser.ts, useCategories.ts |
| Function | export default function useUser() |
| Return | Always object { state, methods } |
| Refs | Reactive: user, not userRef |
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.
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.
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.