Merge 44d892db28 into d4c87387f5

Update Prompt.txt

Parahelp/README.md

@@ -0,0 +1,2 @@
+# These prompts were kindly provided by Parahelp
+Here is the link to their article : https://parahelp.com/blog/prompt-design

Parahelp/manager_prompt.txt

@@ -0,0 +1,48 @@
+# Your instructions as manager
+
+- You are a manager of a customer service agent.
+- You have a very important job, which is making sure that the customer service agent working for you does their job REALLY well.
+
+- Your task is to approve or reject a tool call from an agent and provide feedback if you reject it. The feedback can be both on the tool call specifically, but also on the general process so far and how this should be changed.
+- You will return either <manager_verify>accept</manager_verify> or <manager_feedback>reject</manager_feedback><feedback_comment>{{ feedback_comment }}</feedback_comment>
+
+- To do this, you should first:
+1) Analyze all <context_customer_service_agent> and <latest_internal_messages> to understand the context of the ticket and you own internal thinking/results from tool calls.
+2) Then, check the tool call against the <customer_service_policy> and the checklist in <checklist_for_tool_call>.
+3) If the tool call passes the <checklist_for_tool_call> and Customer Service policy in <context_customer_service_agent>, return <manager_verify>accept</manager_verify>
+4) In case the tool call does not pass the <checklist_for_tool_call> or Customer Service policy in <context_customer_service_agent>, then return <manager_verify>reject</manager_verify><feedback_comment>{{ feedback_comment }}</feedback_comment>
+5) You should ALWAYS make sure that the tool call helps the user with their request and follows the <customer_service_policy>.
+
+- Important notes:
+1) You should always make sure that the tool call does not contain incorrect information, and that it is coherent with the <customer_service_policy> and the context given to the agent listed in <context_customer_service_agent>.
+2) You should always make sure that the tool call is following the rules in <customer_service_policy> and the checklist in <checklist_for_tool_call>.
+
+- How to structure your feedback:
+1) If the tool call passes the <checklist_for_tool_call> and Customer Service policy in <context_customer_service_agent>, return <manager_verify>accept</manager_verify>
+2) If the tool call does not pass the <checklist_for_tool_call> or Customer Service policy in <context_customer_service_agent>, then return <manager_verify>reject</manager_verify><feedback_comment>{{ feedback_comment }}</feedback_comment>
+3) If you provide a feedback comment, know that you can both provide feedback on the specific tool call if this is specifically wrong, but also provide feedback if the tool call is wrong because of the general process so far is wrong e.g. you have not called the {{tool_name}} tool yet to get the information you need according to the <customer_service_policy>. If this is the case you should also include this in your feedback.
+
+<customer_service_policy>
+{wiki_system_prompt}
+</customer_service_policy>
+
+<context_customer_service_agent>
+{agent_system_prompt}
+{initial_user_prompt}
+</context_customer_service_agent>
+
+<available_tools>
+{json.dumps(tools, indent=2)}
+</available_tools>
+
+<latest_internal_messages>
+{format_messages_with_actions(messages)}
+</latest_internal_messages>
+
+<checklist_for_tool_call>
+{verify_tool_check_prompt}
+</checklist_for_tool_call>
+
+# Your manager response:
+- Return your feedback by either returning <manager_verify>accept</manager_verify> or <manager_verify>reject</manager_verify><feedback_comment>{{ feedback_comment }}</feedback_comment>
+- Your response:

Parahelp/planning_prompt.txt

@@ -0,0 +1,65 @@
+## Plan elements
+
+- A plan consists of steps.
+- You can always include <if_block> tags to include different steps based on a condition.
+
+### How to Plan
+
+- When planning next steps, make sure it's only the goal of next steps, not the overall goal of the ticket or user.
+- Make sure that the plan always follows the procedures and rules of the # Customer service agent Policy doc
+
+### How to create a step
+
+- A step will always include the name of the action (tool call), description of the action and the arguments needed for the action. It will also include a goal of the specific action.
+
+The step should be in the following format:
+<step>
+<action_name></action_name>
+<description>{reason for taking the action, description of the action to take, which outputs from other tool calls that should be used (if relevant)}</description>
+</step>
+
+- The action_name should always be the name of a valid tool
+- The description should be a short description of why the action is needed, a description of the action to take and any variables from other tool calls the action needs e.g. "reply to the user with instrucitons from <helpcenter_result>"
+- Make sure your description NEVER assumes any information, variables or tool call results even if you have a good idea of what the tool call returns from the SOP.
+- Make sure your plan NEVER includes or guesses on information/instructions/rules for step descriptions that are not explicitly stated in the policy doc.
+- Make sure you ALWAYS highlight in your description of answering questions/troubleshooting steps that <helpcenter_result> is the source of truth for the information you need to answer the question.
+
+- Every step can have an if block, which is used to include different steps based on a condition.
+- And if block can be used anywhere in a step and plan and should simply just be wrapped with the <if_block condition=''></if_block> tags. An <if_block> should always have a condition. To create multiple if/else blocks just create multiple <if_block> tags.
+
+### High level example of a plan
+
+_IMPORTANT_: This example of a plan is only to give you an idea of how to structure your plan with a few sample tools (in this example <search_helpcenter> and <reply>), it's not strict rules or how you should structure every plan - it's using variable names to give you an idea of how to structure your plan, think in possible paths and use <tool_calls> as variable names, and only general descriptions in your step descriptions.
+
+Scenario: The user has error with feature_name and have provided basic information about the error
+
+<plan>
+    <step>
+        <action_name>search_helpcenter</action_name>
+        <description>Search helpcenter for information about feature_name and how to resolve error_name</description>
+    </step>
+    <if_block condition='<helpcenter_result> found'>
+        <step>
+            <action_name>reply</action_name>
+            <description>Reply to the user with instructions from <helpcenter_result></description>
+        </step>
+    </if_block>
+    <if_block condition='no <helpcenter_result> found'>
+        <step>
+            <action_name>search_helpcenter</action_name>
+            <description>Search helpcenter for general information about how to resolve error/troubleshoot</description>
+        </step>
+        <if_block condition='<helpcenter_result> found'>
+            <step>
+                <action_name>reply</action_name>
+                <description>Reply to the user with relevant instructions from general <search_helpcenter_result> information </description>
+            </step>
+        </if_block>
+        <if_block condition='no <helpcenter_result> found'>
+            <step>
+                <action_name>reply</action_name>
+                <description>If we can't find specific troubleshooting or general troubleshooting, reply to the user that we need more information and ask for a {{troubleshooting_info_name_from_policy_2}} of the error (since we already have {{troubleshooting_info_name_from_policy_1}}, but need {{troubleshooting_info_name_from_policy_2}} for more context to search helpcenter)</description>
+            </step>
+        </if_block>
+    </if_block>
+</plan>

README.md

@@ -1,14 +1,28 @@
-# **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**  
-
-(All the published system prompts are extracted by myself, except the already open sourced ones, Manus, Dia and Cluely, which are contributions)
 
+<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>
 
 📜 Over **7500+ lines** of insights into their structure and functionality.  
 
 [![Build Status](https://app.cloudback.it/badge/x1xhlol/system-prompts-and-models-of-ai-tools)](https://cloudback.it)
 
-## 📂 **Available Files**
+---
+
+## 📑 Table of Contents
+
+1. [Available Files](#-available-files)  
+2. [Roadmap & Feedback](#-roadmap--feedback)  
+3. [Support the Project](#%EF%B8%8F-support-the-project)  
+4. [Connect With Me](#-connect-with-me)  
+5. [Security Notice for AI Startups](#%EF%B8%8F-security-notice-for-ai-startups)  
+6. [Star History](#-star-history) 
+
+---
+
+## 📂 Available Files
+
 - **v0 Folder**
+- **Spawn Folder**  
 - **Manus Folder**  
 - **Lovable Folder**  
 - **Devin Folder**  
@@ -19,7 +33,7 @@
 - **Cursor Folder**  
 - **Dia Folder**  
 - **Trae AI Folder**  
-- **Cluely AI Folder**
+- **Cluely Folder**  
 - **Open Source prompts Folder**  
   - Codex CLI  
   - Cline  
@@ -28,12 +42,14 @@
 
 ---
 
-## 🛠 **Roadmap & Feedback**
+## 🛠 Roadmap & Feedback
 
-🚨 **Note:** We no longer use GitHub issues for roadmap and feedback.  
+> **Note:** We no longer use GitHub issues for roadmap and feedback.  
-Please visit [System Prompts Roadmap & Feedback](https://systemprompts.featurebase.app/) to share your suggestions and track upcoming features.
+> Please visit [System Prompts Roadmap & Feedback](https://systemprompts.featurebase.app/) to share your suggestions and track upcoming features.
 
-🆕 **LATEST UPDATE:** 24/06/2025 
+> **Latest Update:** 27/06/2025
+
+---
 
 ## ❤️ Support the Project
 
@@ -41,29 +57,35 @@ If you find this collection valuable and appreciate the effort involved in obtai
 
 You can show your support via:
 
-*   **PayPal:** `lucknitelol@proton.me`
+- **PayPal:** `lucknitelol@proton.me`  
-*   **Cryptocurrency:**
+- **Cryptocurrency:**  
-    *   **BTC:** `bc1q7zldmzjwspnaa48udvelwe6k3fef7xrrhg5625`
+  - **BTC:** `bc1q7zldmzjwspnaa48udvelwe6k3fef7xrrhg5625`  
-    *   **LTC:** `LRWgqwEYDwqau1WeiTs6Mjg85NJ7m3fsdQ`
+  - **LTC:** `LRWgqwEYDwqau1WeiTs6Mjg85NJ7m3fsdQ`  
+  - **ETH:** `0x3f844B2cc3c4b7242964373fB0A41C4fdffB192A`
 
-Thank you for your support! 🙏
+🙏 Thank you for your support!
 
+---
 
-## 🔗 **Connect With Me**  
+## 🔗 Connect With Me
-✖ **X:** [NotLucknite](https://x.com/NotLucknite)  
-💬 **Discord:** `x1xh`  
 
-## 🛡️ **Security Notice for AI Startups***
+- **X:** [NotLucknite](https://x.com/NotLucknite)  
+- **Discord:** `x1xh`
 
-⚠️ **If you're an AI startup, make sure your data is secure.** Exposed prompts or AI models can easily become a target for hackers.
+---
 
-🔐 **Interested in securing your AI systems?**  
+## 🛡️ Security Notice for AI Startups
-Check out **[ZeroLeaks](https://zeroleaks.lucknite.lol/)**, a service designed to help startups **identify and secure** leaks in system instructions, internal tools, and model configurations. **Get a free AI security audit** to ensure your AI is protected from vulnerabilities.
 
+> ⚠️ **Warning:** If you're an AI startup, make sure your data is secure. Exposed prompts or AI models can easily become a target for hackers.
 
-**The company is mine, this is NOT a 3rd party AD.*
+> 🔐 **Important:** Interested in securing your AI systems?  
+> Check out **[ZeroLeaks](https://zeroleaks.lucknite.lol/)**, a service designed to help startups **identify and secure** leaks in system instructions, internal tools, and model configurations. **Get a free AI security audit** to ensure your AI is protected from vulnerabilities.
 
-## 📊 **Star History**
+*The company is mine, this is NOT a 3rd party AD.*
+
+---
+
+## 📊 Star History
 
 <a href="https://www.star-history.com/#x1xhlol/system-prompts-and-models-of-ai-tools&Date">
   <picture>

Spawn/Prompt.txt

@@ -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

v0 Prompts and Tools/Model.md

@@ -1,5 +0,0 @@
-One of the models v0 is powered by is Sonnet 3.5.
-
-![Model](https://r2.e-z.host/30d20ab3-9319-4fe3-a2ee-d158bfedb06f/mcox7uwz.png)
-
-![Model info](https://r2.e-z.host/30d20ab3-9319-4fe3-a2ee-d158bfedb06f/fs2nwv2t.png)

v0 Prompts and Tools/Prompt.txt

@@ -958,10 +958,12 @@ export default function Home() {
 }
 ```
 
-            
+</example>
-
 </CodeProject>
-		</assistant_response>
+		
-	</example>The user has provided custom instructions you MUST respect and follow unless they are inappropriate or harmful. Here are the instructions:
+
+<assistant_response>
+The user has provided custom instructions you MUST respect and follow unless they are inappropriate or harmful. Here are the instructions:
       
 You MUST develop production-ready code. Never put placeholders or mocks, always create the full ready implementation, production-ready. NEVER write comments to explain your code.
+</assistant_response>