Back to Prompt Library
implementation

Integrate Skyvern for Policy Extraction

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Multimodal Content Generator for Brand Safety

Format
Code-aware
Lines
14
Sections
4
Linked challenge
Multimodal Content Generator for Brand Safety

Prompt source

Original prompt text with formatting preserved for inspection.

14 lines
4 sections
No variables
1 code block
Develop a tool or function within your Google ADK agent that uses Skyvern to programmatically access a simulated URL (e.g., `https://example.com/platform-policies`) and extract relevant content policies and brand safety guidelines. The agent should be able to interpret these extracted rules for self-correction.

```python
# Assuming Skyvern client setup
# from skyvern_sdk import SkyvernClient
# skyvern_client = SkyvernClient(api_key="YOUR_SKYVERN_API_KEY")

def get_platform_policies(url: str) -> str:
    # Simulate Skyvern task to scrape policies
    # response = skyvern_client.scrape_page(url)
    # return response.text_content
    # For this challenge, you can return a hardcoded string simulating scraped policies
    return "Platform Policy: Content must not promote hate speech. All ads must be family-friendly. No graphic violence. Political commentary allowed if balanced."

# Integrate this function as a tool for your ADK agent.
# Example: agent.register_tool(Tool(function_declarations=[get_platform_policies_func_declaration]))
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.