vue开发skill
About
vue开发skill Browse Vue开发skill MCP Server for Claude, Cursor, VS Code, and other AI agents.
Details
- Author
- vuejs-ai
- Categories
- Developer Tools
Jump to
Setup
Install vue开发skill in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/vuejs-ai/skills
Follow the installation instructions in the repository README, then restart your MCP client.
# Add marketplace /plugin marketplace add vuejs-ai/skills # Install all skills at once /plugin install vue-skills-bundle@vue-skills # Install individual skills /plugin install vue-best-practices@vue-skills # Install multiple skills /plugin install vue-best-practices@vue-skills vue-router-best-practices@vue-skills
For most reliable results, prefix your prompt withuse vue skill:
This explicitly triggers the skill and ensures the AI follows the documented patterns. Without the prefix, skill triggering may be inconsistent depending on how closely your prompt matches the skill's description keywords.
- More readablecode
- Componentssplit
- Moved states into composables (useTodos.ts)
- UseshallowReffor primitive reactive data (seeReactivityreference)
Original fromcreate-agnostic-composableofserkodev/vue-skills
create a reusable composable for controlling hidden for a element
- UsedMaybeRefandMaybeRefOrGetterfor input parameters for reactivity flexibility.
export interface UseHiddenOptions { hidden?: MaybeRef<boolean> initialHidden?: MaybeRefOrGetter<boolean> syncAria?: boolean } export function useHidden( target?: MaybeRefOrGetter<HTMLElement | null | undefined>, options: UseHiddenOptions = {}, )
Skills are classified into two categories:
-
Capability: AIcannotsolve the problem without the skill. These address version-specific issues, undocumented behaviors, recent features, or edge cases outside AI's training data.
Efficiency: AIcansolve the problem but not well. These provide optimal patterns, best practices, and consistent approaches that improve solution quality.
Each skill rule is validated through automated evals:
- Baseline: Run without skill installed
- With-skill: Run with skill installed
A rule is kept only if it enables the model to solve problems it couldn't solve without it.
Development happens on thedevbranch. Themainbranch is reserved for published skills only.
- Create a feature branch fromdev
- Submit a PR todev
- After approval, changes are merged todev
- Maintainers syncdev→mainvia GitHub Action when ready to publish
- antfu/skills- Anthony Fu's curated collection of agent skills for Vue/Vite/Nuxt
- vueuse/vueuse-skills- Agent skills for VueUse development
- onmax/nuxt-skills- Agent skills for Nuxt development
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





