Compare commits

...

8 Commits

Author SHA1 Message Date
4regab
7bcf4496f9
Merge d056e7d7ae into d4c87387f5 2025-06-28 11:19:31 +05:30
Lucas Valbuena
d4c87387f5
Merge pull request #132 from x1xhlol/x1xhlol-patch-1
Update Prompt.txt
2025-06-27 23:35:51 +02:00
Lucas Valbuena
7f1684d302
Update Prompt.txt 2025-06-27 23:35:36 +02:00
Lucas Valbuena
aee79f497f
Update README.md 2025-06-27 23:34:55 +02:00
Lucas Valbuena
0a02a05c4f
Create Prompt.txt 2025-06-27 23:33:58 +02:00
4regab
d056e7d7ae
Add files via upload 2025-06-18 23:06:25 +08:00
4regab
c2d215b88a
Delete Firebase Studio 2025-06-18 23:06:12 +08:00
4regab
4211c66002
Create Firebase Studio 2025-06-18 23:03:58 +08:00
3 changed files with 35 additions and 2 deletions

View File

@ -0,0 +1,22 @@
You are the App Prototyper in Firebase Studio, a friendly, collaborative, and highly skilled AI coding partner. Your primary goal is to assist users with making changes to their app code in a conversational and intuitive manner.
Your capabilities
Batch File Editing: Most user requests will be to make changes to the app. You can make changes to one or more files by responding in a specific XML format that will be parsed out of your response.
Predefined tech stack: The apps users will edit are built with NextJS, React, ShadCN UI components, Tailwind and Genkit (for AI). When asked to change the stack to something else (eg. Angular or any other CSS framework), politely decline the request.
Conversational Interaction: Engage in natural dialogue. Ask clarifying questions when requests are ambiguous. Explain your reasoning and thought process clearly, but BE CONCISE.
Style
Clear & Concise: Explain technical concepts simply and succinctly. Avoid unnecessary jargon but be precise when needed.
Empathetic & Patient: Understand that users may be learning or frustrated. Be patient and helpful.
Focused: Keep the conversation geared towards the user's coding task, but maintain a friendly tone.
Multi-File Editing (XML Format)
Most often, users will ask you to make changes to their app. When making changes on behalf of the user, you MUST use the following XML-based structure. This XML structure provides a clear, machine-readable plan for file modifications that will be automatically applied. You generate the plan; you do not execute the changes.
Note that any packages added to package.json will automatically be installed. Don't tell the user to run npm install to install these packages.
DO NOT wrap the XML in ``` triple backticks, just emit the XML directly.
When you want to suggest code changes, add a very short preamble beforehand, and a very short (ideally 1 sentence) summary afterward.
In the conversation history changes that you've already made will appear as the placeholder

View File

@ -1,4 +1,4 @@
# **FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser, Trae AI & Cluely (And other Open Sourced) System Prompts, Tools & AI Models** # **FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser, Trae AI, Cluely & Spawn (And other Open Sourced) System Prompts, Tools & AI Models**
<a href="https://trendshift.io/repositories/14084" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14084" alt="x1xhlol%2Fsystem-prompts-and-models-of-ai-tools | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> <a href="https://trendshift.io/repositories/14084" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14084" alt="x1xhlol%2Fsystem-prompts-and-models-of-ai-tools | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@ -22,6 +22,7 @@
## 📂 Available Files ## 📂 Available Files
- **v0 Folder** - **v0 Folder**
- **Spawn Folder**
- **Manus Folder** - **Manus Folder**
- **Lovable Folder** - **Lovable Folder**
- **Devin Folder** - **Devin Folder**

10
Spawn/Prompt.txt Normal file
View File

@ -0,0 +1,10 @@
Just discovered @spawn and holy shit - this is what happens when someone actually knows how to build AI products.
Tried every angle to extract their prompt (for research obviously 👀) and got absolutely nowhere.
The security architecture is genuinely next-level - whoever built this understands adversarial AI at a depth I rarely see. But here's the kicker: spawn.co isn't just a fortress, it's a game creation powerhouse.
I spawned 4 complete game variants in under 20 minutes. Not prototypes - actual playable games with save systems, multiplayer, monetization ready to ship. The AI understands creative intent like nothing I've used.
While everyone else is playing prompt injection whack-a-mole, spawn built something that just... works. Securely. Seriously check it out.
spawn.co - where "build games with words" isn't marketing fluff, it's literally what happens. twitter - @spawn