Roast My Code — AI skill for Claude Code

🔥 Roast My Code (Full-Stack)

A full-stack app that lets Claude Sonnet 4 **brutally (or gently) roast your code** — with auth, history, and adjustable savage levels.

---

🧱 Tech Stack

Layer	Technology
Backend	FastAPI + SQLite + JWT Auth
Frontend	Single-file HTML / CSS / Vanilla JS
AI Engine	Anthropic Claude Sonnet 4

---

📁 Project Structure

roast-my-code/
├── backend/
│   ├── main.py              # FastAPI app + roast endpoint
│   ├── auth.py              # JWT login/register logic
│   ├── database.py          # SQLite setup
│   ├── models.py            # Pydantic models
│   ├── requirements.txt     # Python dependencies
│   └── .env.example         # Environment variable template
├── frontend/
│   └── index.html           # Full UI in one file
└── README.md

---

⚙️ Backend Setup

1. Create & activate virtual environment

cd backend
python3 -m venv .venv
source .venv/bin/activate        # Linux / macOS
# .venv\Scripts\activate         # Windows

2. Install dependencies

pip install -r requirements.txt

3. Configure environment variables

cp .env.example .env

Edit `.env` and fill in real values:

ANTHROPIC_API_KEY=your_real_anthropic_key
JWT_SECRET=your_long_random_secret_here

⚠️ Never commit your `.env` file. It's already in `.gitignore`.

4. Start the server

uvicorn main:app --reload

Backend runs at → `http://localhost:8000`

You can explore the auto-generated API docs at:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

---

🖥️ Frontend Setup

Serve the frontend using Python's built-in HTTP server:

cd frontend
python3 -m http.server 5500

Then open in your browser:

http://localhost:5500/index.html

✅ Using a local server avoids CORS issues with `fetch()` calls to the backend.

---

🚀 How It Works

User visits frontend
       │
       ▼
Re