nuxt-skill-hub
Install one skill or module. Your agent gets Nuxt best practices, module APIs, and project-specific guidance before it changes your code.
Works with your AI agent
How it works
nuxt-{package.name}Doctor
Doctor scans your project before review and flags framework bugs agents often miss.
SSR drift
public config
report ready
$pnpm dlx vite-doctor . --rules nuxt/hydration
loaded
nuxt.config.ts
scanned
38 Vue components
matched
15 Nuxt rules
nuxt/hydration/no-client-conditional-in-template
app/components/UserMenu.vue:18:5
Browser-only state changes the server-rendered markup.
nuxt/runtime/no-secret-in-public-config
nuxt.config.ts:42:13
Move private keys out of public runtime config.
suggested agent action
Apply the narrow fix, rerun Doctor, then discharge the PR with the report attached.
What's inside
General agents can write Vue, but they still miss Nuxt conventions, module APIs, and common pitfalls. Skills package that context into files your agent can read before it edits code.
Keeps agents aligned with your Nuxt version and installed modules before they dive deeper
Focused Nuxt packs help agents pick the right framework API before they fall back to generic Vue patterns
A sibling Vue skill covers SFC structure, reactivity, props/emits, and composables after the Nuxt decision is settled
Data fetching, hydration safety, runtime config, Nitro, and request boundaries where Nuxt-specific mistakes compound quickly
Each module adds scoped guidance on top of the Nuxt packs instead of replacing broad framework rules
When a module lacks a shipped skill, generated wrappers route agents to official docs and repo links
Playground
Toggle modules to see how the skill changes as your stack changes.
Modules
2 activeModule authoring
Add module author guidance to the preview.
Use this skill to make the Nuxt ownership decision first, then route to the smallest relevant Nuxt, Vue, or module guide.
Load one matching guide first. Open more guides only when the first guide points you there or the task clearly crosses boundaries.
| Task shape or symptom | Open first |
|---|---|
| SSR, initial page load, route params, or data fetched for first render | Data Fetching and SSR |
Hydration warnings, ClientOnly, browser-only APIs, time/randomness, or SSR/CSR mismatch | Hydration and SSR Consistency |
| Page options, middleware, layout selection, title, meta tags, canonical URLs, or OG data | Page Meta, Head, and Layout |
nuxt.config.*, runtimeConfig, env wiring, or public/private config exposure | Server Routes and Runtime Config |
server/api/**, server/routes/**, defineEventHandler, route rules, caching, or Nitro plugins | Nitro and h3 Server Patterns |
| Plugins, injections, app boot logic, or global runtime initialization | Plugins and Runtime Boot |
| Secrets, privileged API calls, request isolation, or server/client boundary confusion | Architecture Boundaries |
| Performance regressions, rendering strategy, lazy loading, or payload/bundle cost | Performance and Rendering |
| Upgrades, deprecations, compatibility fixes, or version-boundary work | Migrations and Compatibility |
| A generic Vue or raw HTML fix looks plausible | Abstraction Disambiguation |
| The remaining work is mostly components, composables, reactivity, props/emits, or SFC structure | Vue Best Practices |
Global/local errors, clearError, showError, or recovery flows | Error Surfaces and Recovery |
clearError is not behaving as expected" → Error Surfaces and RecoveryModule guidance exists for installed packages. Keep it scoped to module-owned APIs, config, runtime behavior, plugins, composables, components, hooks, and owned files.
For multi-surface changes or final verification, open Verification and Finish.
Generated by nuxt-skill-hub. Do not edit this file manually.
Configuration
Most projects work with the defaults. Configure skillHub in nuxt.config.ts when you need a custom skill name, explicit agent targets, extra module-author guidance, a different generation policy, or remote lookup control.
autoCustom skill name. Defaults to nuxt-{package.name}.[]Optional explicit agent targets. Leave empty to auto-detect installed agents.falseAdds module-author guidance on top of the default Nuxt app skill.prepareControls when the full generated skill tree is refreshed inside Nuxt buildDir.enabledControls remote module skill lookup, concurrency, cache refresh, timing logs, timeout, and .well-known context budgets.export default defineNuxtConfig({ modules: ['nuxt-skill-hub'], skillHub: { targets: ['claude-code'], generationMode: 'prepare', remote: { refresh: false, timeoutMs: 1500, concurrency: 8, githubHeuristics: false, timings: false, }, } })
Pipeline
On every nuxi prepare, nuxt-skill-hub scans your project, resolves the best available sources, and writes agent-ready files.
Find agent folders
Claude, Cursor, Gemini, and Codex targets
Read your stack
Nuxt modules, layers, and extra packages
Check .well-known paths
Standard discovery for docs-published skills
Prefer packaged skills
Use skill files shipped with the package
Fall back to GitHub
Load the module repository when needed
Use curated mappings
Last-resort community skill map
Write agent-ready files
One entry skill plus module guidance per agent