Skills Explorer Add Skills

nuxt

An agent skill by antfu, from antfu/skills. Tags: development, routing, ssr, vue, web.

What it does

Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing. Use when working with Nuxt apps, server routes, useFetch, middleware, or hybrid rendering.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add antfu/skills --skill nuxt

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/antfu/skills
cp -r skills/skills/nuxt ~/.claude/skills/nuxt

Safety box score

Grade C, moderate risk: 42 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only Nuxt skill: it teaches the agent to run Nuxt CLI commands, edit app/server files, and deploy to external hosts. The main risks are external command execution, global CLI installs, and publishing/build actions; there are no shipped scripts or opaque binaries in the skill itself.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)The skill is built around shell workflows like `npx nuxi@latest init`, `npx nuxt build`, and `pnpm install`, so using it can lead the agent to run external CLI commands.
Network access2 (moderate)It references remote package and repo fetches (`npx nuxi@latest`, `github:username/repo#v1.0`, `npm i -g vercel`) and even `--tunnel`/deploy flows, so network access is part of the skill's normal reach.
Filesystem reach1 (low)The docs steer the agent to create and clean project files under `app/`, `server/`, `.nuxt`, `.output`, and `node_modules/.cache`, but not outside the project tree.
Secrets & credentials2 (moderate)Secret-bearing settings are a core topic here: `runtimeConfig.apiSecret`, `.env`, `NUXT_API_SECRET`, `NUXT_APP_SECRET`, and `process.env.JWT_SECRET` are all shown or named in the shipped docs.
Privilege & persistence2 (moderate)The deployment guidance recommends global installs such as `npm i -g vercel` and `npm i -g netlify-cli`, which affects the user's global tooling environment.
Instruction hijack surface0 (none)I found no prompt-injection text, hidden instructions, or requests to ignore higher-priority policy in the shipped files.
Irreversible actions2 (moderate)The deployment examples include publish actions like `vercel` and `netlify deploy --prod`, so the skill can drive external side effects if the agent follows it.
Transparency0 (none)All files are plain readable Markdown and code snippets; I found no binaries, minified blobs, or decoded-at-runtime content.

Before installing

Rated 2026-10-20 by an automated review of 20 files from the skill's repository.

Source

Repository
antfu/skills (all skills from this repository)
Path
skills/nuxt/SKILL.md
Branch
main
Updated
2026-09-22