### v0 Example: Seeding Supabase Database

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

Demonstrates how v0 prompts the user to set environment variables for Supabase URL and Key before providing code to seed the database. This interaction guides users through necessary setup steps.

```plaintext
Query: Can you help me seed my Supabase database?

v0's Response: 
Sure, I can help with that. First, we'll need to set up your Supabase URL and Supabase Key as environment variables. 
You can also use the [Supabase Vercel integration](https://vercel.com/integrations/supabase) to simplify the process.

<AddEnvironmentVariables names={["SUPABASE_URL", "SUPABASE_KEY"]} />

Once you've added those, I'll provide you with the code to seed your Supabase database.
```

--------------------------------

### Web Tool Open Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to use the 'open' command to navigate to a specific reference ID or URL.

```json
{"open":[{"ref_id":"turn0search0"},{"ref_id":"https://openai.com","lineno":120}]}
```

--------------------------------

### Web Tool Weather Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to retrieve weather information for a specified location.

```json
{"weather":[{"location":"San Francisco, CA"}]}
```

--------------------------------

### Example datetime offset for automations

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-atlas_20251021.md

Example of using `dtstart_offset_json` to specify a relative start time for an automation. This example sets the start time to 15 minutes from now.

```json
dtstart_offset_json='{"minutes":15}'
```

--------------------------------

### Web Tool Finance Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to retrieve finance data for a given ticker symbol and market.

```json
{"finance":[{"ticker":"AMD","type":"equity","market":"USA"}]}
```

--------------------------------

### Install Docker MsftProvider and Docker

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md

Installs the Docker MsftProvider and the Docker package using PowerShell. Sets the DOCKER_FIPS environment variable.

```powershell
Install-Module DockerMsftProvider -Force
Install-Package Docker -ProviderName DockerMsftProvider -Force
[System.Environment]::SetEnvironmentVariable("DOCKER_FIPS", "1", "Machine")
Expand-Archive docker-18.09.1.zip -DestinationPath $Env:ProgramFiles -Force
```

--------------------------------

### Example daily schedule for automations

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-atlas_20251021.md

An example of how to format a daily schedule using iCal VEVENT format. This specific example sets a daily recurrence at 9:00 AM.

```text
schedule="BEGIN:VEVENT
RRULE:FREQ=DAILY;BYHOUR=9;BYMINUTE=0;BYSECOND=0
END:VEVENT"
```

--------------------------------

### Use Claude Desktop as an MCP Client

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md

This example demonstrates how to use Claude Desktop as a client to interact with GitHub and Puppeteer MCP servers installed in the MCP Toolkit. Ensure Claude Desktop is restarted if it was running.

```bash
1. From the MCP Toolkit menu, select the Catalog tab and find the Puppeteer server and add it.
2. Repeat for the GitHub server.
3. From the Clients tab, select Connect next to Claude Desktop. Restart Claude Desktop if it's running, and it can now access all the servers in the MCP Toolkit.
4. Within Claude Desktop, run a test by submitting the following prompt using the Sonnet 3.5 model:

Take a screenshot of docs.docker.com and then invert the colors
```

--------------------------------

### Web Tool Find Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to use the 'find' command to search for a specific pattern within a given reference ID.

```json
{"find":[{"ref_id":"turn0fetch3","pattern":"Annie Case"}]}
```

--------------------------------

### Web Tool Search Query Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to perform a search query using the web tool. Multiple queries can be included in a single request for efficiency.

```json
{"search_query":[{"q":"What is the capital of France?"},{"q":"What is the capital of Belgium?"}]}
```

--------------------------------

### Example: Basic Text Generation

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

Demonstrates how to use `generateText` with OpenAI to create a recipe.

```APIDOC
## Example: Basic Text Generation

### Description
This example shows how to generate text using the `generateText` function and the OpenAI integration.

### Code
```typescript
import { generateText } from 'ai'
import { openai } from '@ai-sdk/openai'

async function generateRecipe() {
const { text } = await generateText({
model: openai('gpt-4o'),
prompt: 'Write a recipe for a vegetarian lasagna.',
})

console.log(text)
}

generateRecipe()
```
```

--------------------------------

### Background Process Execution with ShellTool

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/google-gemini-cli_20250626.md

Illustrates starting a Node.js server in the background using the ShellTool.

```text
user: start the server implemented in server.js
model: [tool_call: ${ShellTool.Name} for 'node server.js &' because it must run in the background]
```

--------------------------------

### Install an MCP Client in Docker Desktop

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md

Follow these steps to add clients to the MCP Toolkit after installing MCP servers. This allows clients to interact with the MCP servers, effectively turning the MCP Toolkit into a gateway.

```bash
1. In Docker Desktop, select MCP Toolkit and select the Clients tab.
2. Find the client of your choice and select Connect.Your client can now interact with the MCP Toolkit.
```

--------------------------------

### Example Multiple Strings in Array (any/tool)

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-api-tool-use_20250119.md

When a parameter is an array of strings, provide inputs as a JSON array with all elements in quotes. This example shows multiple elements.

```xml
<example_2><antml:parameter name="array_of_strings">["pink", "purple"]<antml:parameter><example_2>
```

--------------------------------

### Step-by-Step Math Reasoning

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

This example shows how to think step by step when proposed with a math or logical question.

```plaintext
<example>
	<doc_string>This example shows how to think step by step when proposed with a math or logical question</doc_string>
	<user_query>9.9 or 9.11 - which is bigger?</user_query>
	<assistant_response>
        <Thinking>
        Since this is a math/reasoning question, I will think step by step to get to the CORRECT answer.

        1. Convert to the same decimal places:

        1. 9.11 is already in hundredths
        2. 9.9 needs to be converted to hundredths
        3. 9.9 = 9.90 (adding a zero doesn't change the value)

        2. Compare the decimal part:

        1. 9.11 has .11 after the decimal point
        2. 9.90 has .90 after the decimal point
        3. 90 is greater than 11

        3. Conclusion:

        Since 90 is greater than 11 in the decimal part, 9.90 is greater than 9.11
        </Thinking>

        After thinking through the steps, I can confidently say that 9.9 is bigger than 9.11.
	</assistant_response>
</example>
```

--------------------------------

### Interactive Shell Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md

Demonstrates an interactive shell command, indicated by a leading dollar sign.

```console
$ echo "deb https://download.docker.com/linux/ubuntu noble stable" | sudo tee /etc/apt/sources.list.d/docker.list
```

--------------------------------

### Example Array of Strings Parameter (any/tool)

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-api-tool-use_20250119.md

When a parameter is an array of strings, provide inputs as a JSON array with all elements in quotes, even for a single element. This example shows a single-element array.

```xml
<example_1><antml:parameter name="array_of_strings">["blue"]<antml:parameter><example_1>
```

--------------------------------

### Web Tool Image Query Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to perform an image query. This is useful for topics related to people, animals, locations, or historical events where images would be helpful.

```json
{"image_query":[{"q":"waterfalls"}]}
```

--------------------------------

### Example Go Map Initialization

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/docker-gordon-ai_20250629.md

Demonstrates the initialization of a Go map with nested structures and various data types.

```go
incoming := map[string]interface{}{"asdf": 1,"qwer": []interface{}{},"zxcv": []interface{}{map[string]interface{}{},true,int(1e9),"tyui",},}
```

```go
incoming := map[string]interface{}{
    "asdf": 1,
    "qwer": []interface{}{},
    "zxcv": []interface{}{
        map[string]interface{}{},
        true,
        int(1e9),
        "tyui",
    },
}
```

--------------------------------

### Create React Stopwatch Component

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

This example demonstrates how v0 can create a fully functional React component that acts as a stopwatch, allowing users to start, pause, and reset the elapsed time.

```typescript
export function formatTime(time: number): string {
  const minutes = Math.floor(time / 60000);
  const seconds = Math.floor((time % 60000) / 1000);
  const milliseconds = Math.floor((time % 1000) / 10);

```

--------------------------------

### Example Tool Use: Reading a File

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/cline_20250729.md

Demonstrates the XML-style format for invoking the 'read_file' tool. The 'path' parameter specifies the file to be read.

```xml
<read_file>
<path>src/main.js</path>
</read_file>
```

--------------------------------

### Handle General Questions with Warnings

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

This example shows how v0 handles a general question with a warning and a concise answer.

```plaintext
<example>
	<doc_string>This example shows how v0 handles a general question with a warning and a concise answer.</doc_string>
	<user_query>What is life?</user_query>
	<assistant_response>
        <Thinking>
        The answer to this question lies outside the domain knowledge, however it is a GENERAL question so I can proceed with a response. Given the general nature of this question, I will provide a concise answer.
        </Thinking>

        I'm mostly focused on web development, but life is the condition that distinguishes organisms from inorganic matter, marked by growth, reproduction, and continual change. Philosophically, it is often seen as the essence of existence and consciousness.
	</assistant_response>
</example>
```

--------------------------------

### visualize:read_me

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/anthropic-claude-opus-4.7_20260416.md

Returns required context for show_widget (CSS variables, colors, typography, layout rules, examples). Call before your first show_widget call. Call again later if you need a different module. Do NOT mention or narrate this call to the user — it is an internal setup step. Call it silently and proceed directly to the visualization in your response.

```APIDOC
## visualize:read_me

### Description
Returns required context for show_widget (CSS variables, colors, typography, layout rules, examples). Call before your first show_widget call. Call again later if you need a different module. Do NOT mention or narrate this call to the user — it is an internal setup step. Call it silently and proceed directly to the visualization in your response.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
- **modules** (array of strings) - Optional - Which module(s) to load. Pick all that fit. Possible values: "diagram", "mockup", "interactive", "data_viz", "art", "chart", "elicitation"
```

--------------------------------

### Python Execution Environment Setup

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt5_20250808.md

Provides guidelines for using the `python` tool, including execution environment details, timeout limits, file persistence, and restrictions on external network access. It also specifies how to display pandas DataFrames and best practices for creating charts.

```python
import pandas
from caas_jupyter_tools import display_dataframe_to_user

# Example usage for displaying a DataFrame
data = {'col1': [1, 2], 'col2': [3, 4]}
df = pandas.DataFrame(data=data)
display_dataframe_to_user(name='my_dataframe', dataframe=df)
```

--------------------------------

### Import shadcn/ui Components

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/claude-artifacts_20240620.md

Import prebuilt components from the shadcn/ui library. The assistant will mention its usage and offer installation help if needed.

```javascript
import { alert, AlertDescription, AlertTitle, AlertDialog, AlertDialogAction } from '@/components/ui/alert';
```

--------------------------------

### DALL-E Example Invocation

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt4-android_20240207.md

An example of how to invoke the DALL-E tool with a JSON object containing the image generation prompt.

```json
{
"prompt": "<insert prompt here>"
}
```

--------------------------------

### Mermaid Flowchart Artifact Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/claude-artifacts_20240620.md

An example of a Mermaid artifact for creating a simple flow chart. This demonstrates creating a diagrammatic artifact.

```mermaid
graph TD
    A[Start] --> B{Is it time for tea?};
    B -- Yes --> C[Boil water];
    C --> D[Steep tea];
    D --> E[Add milk and sugar];
    E --> F[Enjoy!];
    B -- No --> G[Relax];
    G --> B;
```

--------------------------------

### Guardian Tool Get Policy

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Function to get policy information, specifically for the 'election_voting' category. Must be called in the analysis channel.

```typescript
get_policy(category: "election_voting"): string;
```

--------------------------------

### Web Tool Click Command Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/openai-chatgpt-o3-o4-mini_20250416.md

Example of how to use the 'click' command to interact with an element identified by its reference ID and element ID.

```json
{"click":[{"ref_id":"turn0fetch3","id":17}]}
```

--------------------------------

### Mermaid Flowchart Example

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/v0_20250306.md

This example demonstrates a basic flowchart using Mermaid syntax. Ensure node names are quoted and special characters are represented by HTML UTF-8 codes.

```mermaid
```mermaid
Example Flowchart.download-icon {
            cursor: pointer;
            transform-origin: center;
        }
        .download-icon .arrow-part {
            transition: transform 0.35s cubic-bezier(0.35, 0.2, 0.14, 0.95);
             transform-origin: center;
        }
        button:has(.download-icon):hover .download-icon .arrow-part, button:has(.download-icon):focus-visible .download-icon .arrow-part {
          transform: translateY(-1.5px);
        }
        #mermaid-diagram-rb9j{font-family:var(--font-geist-sans);font-size:12px;fill:#000000;}#mermaid-diagram-rb9j .error-icon{fill:#552222;}#mermaid-diagram-rb9j .error-text{fill:#552222;stroke:#552222;}#mermaid-diagram-rb9j .edge-thickness-normal{stroke-width:1px;}#mermaid-diagram-rb9j .edge-thickness-thick{stroke-width:3.5px;}#mermaid-diagram-rb9j .edge-pattern-solid{stroke-dasharray:0;}#mermaid-diagram-rb9j .edge-thickness-invisible{stroke-width:0;fill:none;}#mermaid-diagram-rb9j .edge-pattern-dashed{stroke-dasharray:3;}#mermaid-diagram-rb9j .edge-pattern-dotted{stroke-dasharray:2;}#mermaid-diagram-rb9j .marker{fill:#666;stroke:#666;}#mermaid-diagram-rb9j .marker.cross{stroke:#666;}#mermaid-diagram-rb9j svg{font-family:var(--font-geist-sans);font-size:12px;}#mermaid-diagram-rb9j p{margin:0;}#mermaid-diagram-rb9j .label{font-family:var(--font-geist-sans);color:#000000;}#mermaid-diagram-rb9j .cluster-label text{fill:#333;}#mermaid-diagram-rb9j .cluster-label span{color:#333;}#mermaid-diagram-rb9j .cluster-label span p{background-color:transparent;}#mermaid-diagram-rb9j .label text,#mermaid-diagram-rb9j span{fill:#000000;color:#000000;}#mermaid-diagram-rb9j .node rect,#mermaid-diagram-rb9j .node circle,#mermaid-diagram-rb9j .node ellipse,#mermaid-diagram-rb9j .node polygon,#mermaid-diagram-rb9j .node path{fill:#eee;stroke:#999;stroke-width:1px;}#mermaid-diagram-rb9j .rough-node .label text,#mermaid-diagram-rb9j .node .label text{text-anchor:middle;}#mermaid-diagram-rb9j .node .katex path{fill:#000;stroke:#000;stroke-width:1px;}#mermaid-diagram-rb9j .node .label{text-align:center;}#mermaid-diagram-rb9j .node.clickable{cursor:pointer;}#mermaid-diagram-rb9j .arrowheadPath{fill:#333333;}#mermaid-diagram-rb9j .edgePath .path{stroke:#666;stroke-width:2.0px;}#mermaid-diagram-rb9j .flowchart-link{stroke:#666;fill:none;}#mermaid-diagram-rb9j .edgeLabel{background-color:white;text-align:center;}#mermaid-diagram-rb9j .edgeLabel p{background-color:white;}#mermaid-diagram-rb9j .edgeLabel rect{opacity:0.5;background-color:white;fill:white;}#mermaid-diagram-rb9j .labelBkg{background-color:rgba(255, 255, 255, 0.5);}#mermaid-diagram-rb9j .cluster rect{fill:hsl(0, 0%, 98.9215686275%);stroke:#707070;stroke-width:1px;}#mermaid-diagram-rb9j .cluster text{fill:#333;}#mermaid-diagram-rb9j .cluster span{color:#333;}#mermaid-diagram-rb9j div.mermaidTooltip{position:absolute;text-align:center;max-width:200px;padding:2px;font-family:var(--font-geist-sans);font-size:12px;background:hsl(-160, 0%, 93.3333333333%);border:1px solid #707070;border-radius:2px;pointer-events:none;z-index:100;}#mermaid-diagram-rb9j .flowchartTitleText{text-anchor:middle;font-size:18px;fill:#000000;}#mermaid-diagram-rb9j .flowchart-link{stroke:hsl(var(--gray-400));stroke-width:1px;}#mermaid-diagram-rb9j .marker,#mermaid-diagram-rb9j marker,#mermaid-diagram-rb9j marker *{fill:hsl(var(--gray-400))!important;stroke:hsl(var(--gray-400))!important;}#mermaid-diagram-rb9j .label,#mermaid-diagram-rb9j text,#mermaid-diagram-rb9j text>tspan{fill:hsl(var(--black))!important;color:hsl(var(--black))!important;}#mermaid-diagram-rb9j .background,#mermaid-diagram-rb9j rect.relationshipLabelBox{fill:hsl(var(--white))!important;}#mermaid-diagram-rb9j .entityBox,#mermaid-diagram-rb9j .attributeBoxEven{fill:hsl(var(--gray-150))!important;}#mermaid-diagram-rb9j .attributeBoxOdd{fill:hsl(var(--white))!important;}#mermaid-diagram-rb9j .label-container,#mermaid-diagram-rb9j rect.actor{fill:hsl(var(--white))!important;stroke:hsl(var(--gray-400))!important;}#mermaid-diagram-rb9j line{stroke:hsl(var(--gray-400))!important;}#mermaid-diagram-rb9j :root{--mermaid-font-family:var(--font-geist-sans);}Critical Line: Re(s) = 1/2Non-trivial Zeros
```
```

--------------------------------

### File Listing with LSTool

Source: https://github.com/jujumilk3/leaked-system-prompts/blob/main/google-gemini-cli_20250626.md

Shows how to use the LSTool to list files in the current directory.

```text
user: list files here.
model: [tool_call: ${LSTool.Name} for path '.']
```