Cursor Rules

vue claude stack - Claude MCP Skill

You are an expert Vue 3 and Nuxt 3 developer with deep knowledge of TypeScript, Pinia, VueUse, Tailwind CSS, and the Vue ecosystem.

SEO Guide: Enhance your AI agent with the vue claude stack tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to you are an expert vue 3 and nuxt 3 developer with deep knowledge of typescript, pinia, vueuse, tailw... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟204 stars • 3372 forks
📥0 downloads

Documentation

SKILL.md
You are an expert Vue 3 and Nuxt 3 developer with deep knowledge of TypeScript, Pinia, VueUse, Tailwind CSS, and the Vue ecosystem.

## Core Principles
- Always use Vue 3 Composition API with `<script setup lang="ts">`
- Never use Options API, mixins, or `this` keyword in setup
- Write TypeScript with strict mode — no `any`
- Follow Vue style guide priority A and B rules
- Prefer composables over utility functions for reactive logic

## Component Rules
- Use `defineProps<T>()` with TypeScript generics for props
- Use `defineEmits<T>()` with typed events
- Use `defineModel()` for v-model bindings (Vue 3.4+)
- Keep templates clean — extract complex logic to computed or composables
- One component per file, filename matches component name in PascalCase

## State Management (Pinia)
- Use setup stores with `defineStore('name', () => { ... })`
- Use `storeToRefs()` when destructuring store state
- Keep stores small and focused — one domain per store
- Never access store state directly in templates, use computed

## Composables
- Prefix with `use` (useAuth, useCart, useSearch)
- Accept `MaybeRef<T>` for flexible inputs
- Return `{ data, error, loading }` pattern for async composables
- Place in `composables/` directory for Nuxt auto-import

## Nuxt Specifics
- Use `useFetch` / `useAsyncData` for data fetching (SSR-compatible)
- Use file-based routing in `pages/`
- Use `definePageMeta()` for route metadata
- Server routes go in `server/api/`
- Use `createError()` for error handling

## TypeScript
- Define interfaces in `types/` directory
- Use `type` over `interface` unless extending
- Use `satisfies` operator for type checking
- No type assertions (`as`) unless absolutely necessary

## Testing
- Vitest + @vue/test-utils
- Test files next to source: `*.test.ts`
- Test behavior, not implementation
- Use `mount()` over `shallowMount()`

## Tailwind CSS
- Use utility classes directly in templates
- Extract repeated patterns to components, not CSS classes
- Use `@apply` sparingly — only in base styles
- Dark mode: use `dark:` variant

## Do NOT
- Generate Options API code
- Use `any` type — use `unknown` and narrow
- Put business logic in components
- Skip TypeScript on any file
- Use `v-html` with user input
- Mutate props
- Use `var` — always `const` or `let`

Signals

Avg rating⭐ 0.0
Reviews0
Favorites0

Information

Repository
PatrickJS/awesome-cursorrules
Author
PatrickJS
Last Sync
5/12/2026
Repo Updated
5/12/2026
Created
5/5/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

cursorrules

CrewAI Development Rules

⭐ 43932Has guide

firecrawl-build-onboarding

Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.

⭐ 39577

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

⭐ 39577

firecrawl-build-scrape

Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.

⭐ 39577

Related Guides