[Feature Request] Prompt Generator

## Describe the solution you'd like

Input a summary of the task, the LLM will propose a prompt optimized for that task.

## Why the solution needed

Because of the need to optimize prompts for accuracy.
To assist those who have no knowledge of prompt engineering.

## Additional context

## Implementation feasibility

Are you willing to discuss the solution with us, decide on the approach, and assist with the implementation?

- [x] Yes
- [ ] No

The issue names no files, tests, or entry points. Start by mapping the existing chat input and LLM request flow, then define the prompt-generator interface and evaluation criteria with maintainers; done means a usable summary-to-prompt flow is implemented and its output quality and behavior are tested.

Written by the indexing model from the issue text.