Reusability of Prompts

[jerop]

TL;DR

Currently, the prompts used by the Gemini CLI are defined inline within the workflow files.

When we improve a prompt, users who have copied our provided workflows won't get the updates unless they manually copy the new prompt from our repository. This means users can easily be running on old, sub-optimal prompts.

Detailed design

Consider serving prompts via the Model Context Protocol (MCP), similar to how we currently serve custom tools.

This would involve:

1. Defining our prompts in a structured format that the MCP server can understand.
2. Configuring the MCP server to expose these prompts to the Gemini CLI.
3. Updating the workflows to reference the prompts via MCP.

Additional information

Learn more in https://modelcontextprotocol.io/specification/2025-06-18/server/prompts

[sethvargo]

I wonder if, as a stop-gap, we can move these prompts into text files in the repo. Once the repo is public, the model could retrieve from the links?

[jerop]

I wonder if, as a stop-gap, we can move these prompts into text files in the repo. Once the repo is public, the model could retrieve from the links?

The challenge is that we also want users to be able to configure the prompts with their own preferences (e.g. code standards) - so we'd need to support dynamically switching from text files in our repo vs those they've configured elsewhere 🤔