# Acme Web App

A Next.js dashboard for the Acme analytics product. Server components by default, client components only when interactivity is required.

## Project

- Stack: Next.js 14, TypeScript, Tailwind CSS, Postgres, Prisma
- Package manager: pnpm

## Commands

- Install: `pnpm install`
- Dev: `pnpm dev`
- Build: `pnpm build`
- Test: `pnpm test`
- Lint: `pnpm lint`

## Code conventions

- Use TypeScript strict mode
- Prefer function components and hooks
- Keep components under 200 lines
- Colocate tests next to source files

## Always do

- Run the linter before committing
- Write tests for new business logic
- Use the existing design tokens

## Never do

- Never commit secrets or .env files
- Never edit generated files by hand
- Never introduce a new dependency without checking for an existing one

How the CLAUDE.md generator works

A CLAUDE.md file is the memory Claude Code reads at the start of every session. It tells the assistant what your project is, which commands to run, and which conventions to follow, so it stops guessing and starts matching your codebase. This generator turns a short form into a concise, sectioned file that follows Anthropic best practices: keep it short, use imperative instructions, and group guidance into clear headings.

Type into any field and the preview updates live. Multi-line fields such as conventions, always do, and never do become bullet lists, while your build, test, and lint commands are formatted as inline code so Claude can run them verbatim. When you are happy with the result, copy it to the clipboard or download a ready-to-commit CLAUDE.md, then place it in your repository root.

This complements Claude Code's built-in /init command rather than replacing it. The /init command scans your repository and drafts a CLAUDE.md automatically, which is great for existing codebases. This generator is handy when you want to hand-craft the file up front, start a new project before there is code to scan, or quickly standardize CLAUDE.md files across several repositories.

Frequently asked questions

What is a CLAUDE.md file?

It is a markdown file in your project that Claude Code automatically reads for context at the start of a session. It captures the project overview, key commands, code conventions, and any hard rules, so the assistant produces work that fits your codebase without repeated explanation.

Where should I put the CLAUDE.md file?

Put the main file in your repository root so it applies to the whole project. You can also add more focused CLAUDE.md files inside subdirectories, and Claude Code will layer that guidance when it works in those folders. There is also a user-level file for preferences that apply across all of your projects.

How is this different from the /init command?

The /init command inside Claude Code inspects your existing repository and drafts a CLAUDE.md for you. This generator is a manual, form-driven alternative that is useful before there is code to scan, when you want tight control over the wording, or when you are creating consistent files across many repositories. The two work well together.

What makes a good CLAUDE.md?

Keep it concise and specific. Favor short, imperative instructions, list the exact commands you want run, and state the rules that matter most, especially anything the assistant should never do. Avoid dumping long documentation into it, since a focused file is easier for the model to follow than a sprawling one.

Does this tool send my data anywhere?

No. Everything runs in your browser. The generator builds the markdown locally, and nothing you type is sent to a server, so you can safely draft internal project details before copying or downloading the file.