What if you could take any weak, vague prompt and instantly transform it into an elite, production-ready one โ with a power score, technique breakdown, and warrior rank?
That's exactly what Prompt Forge does.
๐ค The Problem
Most people use AI wrong. They type something like:
"Write me a blog post about productivity"
And wonder why the output is generic. The secret isn't the model โ it's the prompt. A better prompt unlocks dramatically better results.
But most people don't know how to write better prompts. That's the gap Prompt Forge fills.
โ๏ธ What is Prompt Forge?
Prompt Forge is a single-page web app that transforms weak prompts into elite, production-ready prompts using NVIDIA Llama 3.1 70B via the NVIDIA NIM API.
You paste a rough idea โ hit Forge It โ get back:
- A rewritten prompt (3โ8ร more detailed)
- Which of 8 prompt engineering techniques were applied
- A Power Level score from 1โ10
- A Warrior Rank (Recruit โ Bronze โ Silver โ Gold โ Legendary)
- A Warrior Analysis explaining every upgrade made ๐ Try it live โ
โจ Features
- Prompt Forging Engine โ rewrites weak prompts using Llama 3.1 70B Instruct
- 8 Technique Tags โ Context ยท Specificity ยท Constraints ยท Output Format ยท Persona ยท Examples ยท Chain-of-Thought ยท Negatives
- Power Level Meter โ 10-bar visual indicator (1โ10)
- Warrior Rank System โ gamified ranking based on power level
- Warrior Analysis Panel โ explains every improvement made
- Typewriter Animation โ forged prompt streams in dramatically
- One-click Copy โ instantly copy the result
-
Keyboard Shortcut โ
Ctrl+Enter/Cmd+Enter
- Responsive โ works on mobile and tablet
๐ ๏ธ Tech Stack
| Layer | Technology |
|---|---|
| Frontend | Vanilla HTML / CSS / JavaScript |
| Backend | Python + Flask |
| AI Model | NVIDIA Llama 3.1 70B Instruct |
| API | NVIDIA NIM API |
| Hosting | Render |
Deliberately kept the stack simple โ no React, no heavy frameworks. Just a single HTML file on the frontend and a lightweight Flask proxy on the backend.
๐ง How It Works
The architecture is straightforward:
User Input โ Flask Server โ NVIDIA NIM API โ Llama 3.1 70B โ Structured JSON โ UI
- User enters a weak prompt
- Frontend sends
POST /api/forgeto Flask - Flask forwards to NVIDIA NIM API with a system prompt instructing Llama to act as a master prompt engineer
- Model returns structured JSON:
{
"forged_prompt": "...",
"techniques_used": ["Context", "Specificity", "Persona"],
"power_level": 8,
"analysis": "Added role context, specified output format..."
}
5. Frontend renders with typewriter animation, technique tags, power meter, and warrior rank
๐ก The Key: System Prompt Engineering
The magic is in the system prompt sent to Llama 3.1 70B. It instructs the model to:
- Act as a master prompt engineer
- Identify weaknesses in the input prompt
- Apply specific prompt engineering techniques
- Return a structured JSON response with the forged prompt, techniques used, power level, and analysis The model essentially uses prompt engineering to improve prompts โ meta, but incredibly effective.
๐๏ธ Warrior Rank System
| Power Level | Rank |
|---|---|
| 1โ2 | ๐ช RECRUIT |
| 3โ4 | ๐ฅ BRONZE |
| 5โ6 | ๐ฅ SILVER |
| 7โ8 | ๐ฅ GOLD |
| 9โ10 | ๐ LEGENDARY |
๐ Run It Yourself
git clone https://github.com/Divyansh0208/Prompt_Forge.git
cd Prompt_Forge
pip install flask python-dotenv requests
cp .env.example .env
# Add your NVIDIA API key to .env
python server.py
Get a free NVIDIA API key at build.nvidia.com.
๐ Links
- ๐ Live Demo: prompt-forge-o970.onrender.com
- ๐ป GitHub: github.com/Divyansh0208/Prompt_Forge
Built for Google Prompt Wars 2026. Try forging your weakest prompt and see what rank you earn โ๏ธ













