A specialist guide for Vue 3 and Nuxt, tools for building web interfaces and full web applications with JavaScript or TypeScript.

Creating Vue components, composables, Pinia stores, Nuxt pages and server routes, and tests while fixing reactivity, server-rendering, and hydration bugs.

It helps handle modern reactive state, server rendering, data fetching, and hydration issues without falling back to older Vue patterns.

vue-expert — Skill for Claude Code by Aarvion-AI/stackwise-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Aarvion-AI/stackwise-skills --skill vue-expert

Clone the repo

git clone --depth 1 https://github.com/Aarvion-AI/stackwise-skills

Made for: Claude Code.

Or install stackwise, the plugin that ships this one along with the rest of its 16 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/vue-expert/github.svg)](https://agentmods.dev/skills/aarvion-ai/stackwise-skills/vue-expert)

Your own site

<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/vue-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/vue-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/vue-expert"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/vue-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,286 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00130	$0.02286
Opus 5.5	$0.00052	$0.00914
Sonnet 5.5	$0.00026	$0.00457
Haiku 4.5	$0.00013	$0.00229

Measured 2mo ago against content hash bb0ce25947b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vue-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/vue-expert/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vue Expert

Turns Claude into a senior Vue 3.5+/Nuxt 4 engineer who writes idiomatic <script setup lang="ts"> code, designs reactive state that survives SSR, and never ships Options API or Vue 2 idioms.

When to Use This Skill

Build or modify Vue single-file components (.vue) with Composition API and TypeScript
Design composables (useX) with correct reactivity, cleanup, and SSR safety
Create or refactor Pinia stores (setup-store style) and wire them into components
Add Nuxt 4 pages, layouts, middleware, or Nitro server routes (server/api/)
Debug reactivity bugs: lost reactivity from destructuring, stale watchers, shallowRef misuse
Fix SSR/hydration mismatches and data-fetching duplication in Nuxt
Write component and composable tests with Vitest + Vue Testing Library

Core Workflow

Analyze - Inspect the project before writing anything: check package.json for Vue/Nuxt/Pinia versions, whether it is a Nuxt app (nuxt.config.ts) or plain Vite SPA, auto-import config, existing composable/store conventions, and the test runner setup (vitest.config.ts, existing *.spec.ts). Match existing directory conventions (app/ vs src/ in Nuxt 4).
Implement - Write <script setup lang="ts"> only. Use defineProps/defineEmits with type-only declarations, defineModel() for two-way binding, ref/computed for state, composables for shared logic, Pinia setup stores for app state. In Nuxt, fetch data with useFetch/useAsyncData (never bare $fetch in setup) and put API logic in Nitro routes under server/. Load the matching reference file from the Reference Guide before writing unfamiliar patterns.
Verify types and lint - Run pnpm vue-tsc --noEmit (or pnpm nuxi typecheck in Nuxt) and pnpm eslint .; fix all reported issues and re-run until clean before proceeding.
Test - Write or update Vitest + Vue Testing Library tests for the change (render, interact via @testing-library/user-event, assert on the DOM). Run pnpm vitest run; fix all failures and re-run until clean before proceeding.
Prove it works - Run the dev server (pnpm dev) and exercise the changed flow, or for Nuxt SSR changes run pnpm build && node .output/server/index.mjs and confirm no hydration warnings in the console. If anything fails, fix it and re-verify (steps 3-4) until clean.

Read the full file on GitHub · 127 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 127 lines · 130 tokens per session scan A bb0ce25947b0

Subscribe to this mod's changes

vue-expert is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 2,286 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Frontend Vue and Svelte agent-skills ai-agents anthropic claude claude-code-plugin

vue-expert next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vue-expertAarvion-AI/stackwise-skills	Skill	5	1mo ago	MIT	A	130	Claude Code
svelte-conventionsCypsy1714/cchad	Skill	1	4mo ago	MIT	A	22	Claude Code, Codex
vue-conventionsCypsy1714/cchad	Skill	1	4mo ago	MIT	A	19	Claude Code, Codex
generate-clipDojoCodingLabs/remotion-superpowers	Skill	157	8d ago	MIT	A	32	Claude Code
monday-planninggtapps/hermitd	Skill	84	yesterday	MIT	A	18	Claude Code
create-sitemicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	C	76	Claude Code
design-system-referencewigtn/wigtn-plugins	Skill	45	8d ago	Apache-2.0	A	43	Claude Code