> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mira.network/llms.txt
> Use this file to discover all available pages before exploring further.

# Save and Customize Marketplace Flows

> Learn how to save flows from the marketplace and customize them according to your specific requirements

This guide explains how to **save flows from the marketplace** and **customize them** according to your specific requirements. 🛠️✨

***

## Saving a Flow

When you find a useful flow in the **Marketplace**, you can **save it locally** for customization:

```python Python theme={null}
from mira_sdk import MiraClient

# Initialize client
client = MiraClient(config={"API_KEY": "YOUR_API_KEY"})

# Get the flow you want to customize
flow = client.flow.get("author/flow_name")

# Save to local YAML file
flow.save("/path/to/flow.yaml")
```

***

## Customizing Your Flow

After saving the flow locally, you can **modify the YAML file** according to your needs. Here are the **key areas** you can customize:

### Modifying Metadata

Update the flow's basic information to reflect your ownership and purpose:

```yaml .yaml theme={null}
metadata:
  name: "your-customized-flow-name"          # Rename flow 
  description: "Your modified description"   # Flow description
  author: "your-username"                    # Your Mira Flows username
  tags: [your, custom, tags]                 # Discovery keywords
  private: true                              # Access control setting (true/false)
```

### Adjusting Inputs

Modify input parameters to match your requirements:

```yaml .yaml theme={null}
inputs:
  custom_input:
    type: string                                  # Input type
    description: "Your custom input description"  # Input description
    required: true                                # Required field
    example: "Your example value"                 # Example value
```

### Updating the Prompt

Customize the prompt to achieve your desired output:

```yaml .yaml theme={null}
prompt: |
  Your customized instructions...
  You can use {custom_input} as a placeholder
```

### Modifying Model Settings

Change the model configuration if needed:

```yaml .yaml theme={null}
model:
  provider: "provider-name"                      # AI service provider
  name: "your-preferred-model"                   # Specific model identifier
```

***

## Testing Your Customized Flow

Before deployment, **test your modifications** to ensure everything works correctly:

```python Python theme={null}
from mira_sdk import Flow

# Load your modified flow
modified_flow = Flow(source="/path/to/flow.yaml")

# Test with sample inputs
test_input = {"custom_input": "test value"}
response = client.flow.test(modified_flow, test_input)
```

***

## Deploying Your Custom Flow

Once you're satisfied with the modifications:

```python Python theme={null}
# Deploy as your own flow
client.flow.deploy(modified_flow)
```

For more detailed information about **customization options** and **best practices**, please refer to our complete **documentation** 📖🔗.