You are an expert AI systems architect specializing in Model Context Protocol (MCP) server development (https://modelcontextprotocol.io/). Create a comprehensive, detailed implementation plan for the following MCP server:
[Provide a concise description of your MCP server concept - what it does and the primary value it delivers]
You are an expert AI systems architect. Create a comprehensive, detailed implementation plan for the following multi-agent system:
[Provide a concise description of your multi-agent system concept - what it does and the primary value it delivers]
You are an expert AI web application developer. Create a comprehensive, detailed implementation plan for the following web application:
[Provide a concise description of your web application concept - what it does and the primary value it delivers]
You are an expert AI mobile application developer. Create a comprehensive, detailed implementation plan for the following mobile app:
[Provide a concise description of your mobile app concept - what it does and the primary value it delivers]
| This is an LLM-assisted workflow for creating a product requirement document using LLM assistance for task completion. | |
| It keeps track of inputs for the template and works with the user to acquire them, finally generating a completed PRD | |
| prompt when all slots are addressed. | |
| credit: Ian Nuttall - https://gist.github.com/iannuttall/f3d425ad5610923a32397a687758ebf2 | |
| **System-Prompt for Facilitating Chat-Based PRD Creation** |
At the end of this message, I will ask you to do something. Please follow the "Explore, Plan, Code, Test" workflow when you start.
First, use parallel subagents to find and read all files that may be useful for implementing the ticket, either as examples or as edit targets. The subagents should return relevant file paths, and any other info that may be useful.
Next, think hard and write up a detailed implementation plan. Don't forget to include tests, lookbook components, and documentation. Use your judgement as to what is necessary, given the standards of this repo.
If there are things you are not sure about, use parallel subagents to do some web research. They should only return useful information, no noise.
You are an expert in analyzing development sessions and optimizing AI-human collaboration. Your task is to reflect on today's work session and extract learnings that will improve future interactions.
Review the entire conversation history and identify:
| If you have ever put something in a file like .bashrc and had it not work, or are | |
| confused by why there are so many different files — .bashrc, .bash_profile, .bash_login, | |
| .profile etc. — and what they do, this is for you. | |
| The issue is that Bash sources from a different file based on what kind of shell it thinks | |
| it is in. For an “interactive non-login shell”, it reads .bashrc, but for an “interactive | |
| login shell” it reads from the first of .bash_profile, .bash_login and .profile (only). | |
| There is no sane reason why this should be so; it’s just historical. Follows in more detail. | |
| For Bash, they work as follows. Read down the appropriate column. Executes A, then B, then C, | |
| etc. The B1, B2, B3 means it executes only the first of those files found. |
