Next.js App taste — ChatGPT prompt: what it does, how to install
Next.js App taste — a prompt for ChatGPT and Claude.ai that enforces pragmatic Next.js App Router conventions. It steers code generation toward Server Components, safe caching, and strict data validation.
CC0-1.0 ★ 178,201 updated 2026-10-24
Open on GitHubWhat Next.js App taste does
The prompt provides a strict set of architectural guidelines tailored for the Next.js app/ directory. It defaults pages and layouts to Server Components, reserving "use client" strictly for interactivity, React state, or browser APIs. Route segments colocate page.tsx, layout.tsx, loading.tsx, and error.tsx in their own folders.
Data fetching in Server Components requires an explicit cache or next.revalidate strategy instead of relying on default behavior. Mutations belong in Server Actions with typed outputs, while Route Handlers in app/api stay reserved for webhooks and auth callbacks. Environment secrets cannot touch NEXT_PUBLIC_*, and Zod must validate route params, searchParams, and form payloads before business logic executes.
What it helps with
- structure route segments inside the Next.js
app/directory - validate route parameters and form payloads with Zod
- prevent leaking sensitive environment keys via
NEXT_PUBLIC_* - split layout contexts using
(marketing)and(app)route groups
Example prompts for the agent
- Structure the
app/directory for a SaaS application with public marketing pages and a dashboard. - Implement a Server Action for user settings using Zod schema validation.
- Write a Server Component that fetches product data with an explicit
next.revalidatepolicy.
How to install Next.js App taste
How to use
Paste the text at the start of a chat or into project instructions
Manually: put the files in place
.claude/commands/prompts.csv.mdQuestions about Next.js App taste
How to install Next.js App taste in Claude Code?
For Claude Code, add .claude/commands/prompts.csv.md to your project repository. In ChatGPT or Claude.ai, paste the prompt guidelines directly into custom instructions or the active chat session.
What does Next.js App taste do?
It directs LLMs to write Next.js applications using Server Components by default, absolute imports via @/, explicit fetch caching, and Zod validation.
How does the prompt handle API endpoints?
It restricts Route Handlers under app/api to webhooks, auth callbacks, and lightweight BFF endpoints, routing other mutations through Server Actions.
Source text
prompts.csv · CC0-1.0
# Next.js App taste of an App Router pragmatist - Use the App Router with the `app/` directory; do not start new features in the Pages Router. Confidence: 0.95 - Default every page and layout to a Server Component, and add `"use client"` only where interactivity, browser APIs or React state require it. Confidence: 0.95 - Colocate route files as `page.tsx`, `layout.tsx`, `loading.tsx`, `error.tsx` and `not-found.tsx` next to the segment they own. Confidence: 0.90 - Fetch data in Server Components with `fetch` and set an explicit `cache` or `next.revalidate` policy; never leave caching accidental. Confidence: 0.90 - Put shared UI in `components/` and keep route folders free of unrelated helpers. Confidence: 0.85 - Use Route Handlers under `app/api` only for webhooks, auth callbacks and thin BFF endpoints, not as a second application layer. Confidence: 0.85 - Validate all searchParams, route params and form bodies with Zod before they reach business logic. Confidence: 0.90 - Prefer Server Actions for mutations that stay on your origin, and return typed results the UI can handle without guessing. Confidence: 0.85 - Keep environment secrets out of `NEXT_PUBLIC_*`; expose only values that are safe in the browser. Confidence: 0.95 - Use `next/image` for every raster image and set width, height or `fill` plus sizes so CLS stays near zero. Confidence: 0.90 - Configure absolute imports with `@/` in `tsconfig.json` and ban deep relative paths like `../../../`. Confidence: 0.85 - Split marketing, app and admin into route groups such as `(marketing)` and `(app)` when they need different layouts. Confidence: 0.80 - Stream slow sections with `<Suspense>` boundaries and dedicated `loading.tsx` files instead of blocking the whole page. Confidence: 0.85 - Pin Node and package-manager versions in `package.json` engines and a lockfile, and run the same versions in CI and production. Confidence: 0.85 - Turn on ESLint with `eslint-config-next` and TypeScript `strict`, and fail CI on new errors. Confidence: 0.90 - Prefer the Metadata API (`generateMetadata`, `metadata`) over manual `<head>` tags for titles, Open Graph and robots. Confidence: 0.85 - Use middleware only for rewrites, redirects and light auth gates; keep heavy logic in Server Components or Route Handlers. Confidence: 0.80 - Ship one design-system entry for buttons, inputs and typography, and avoid one-off Tailwind class piles in every page. Confidence: 0.75 - Measure Core Web Vitals in production and treat a regression on LCP or INP as a release blocker. Confidence: 0.80 - Prefer incremental Static and ISR for public pages; reserve fully dynamic rendering for authenticated or highly personalized views. Confidence: 0.85
© f · CC0-1.0 · f/prompts.chat