uditakhourii/adhd ? reverse-engineered prompt
Reverse engineered prompt
Build me a coding agent skill that helps with brainstorming and tricky decisions by exploring several different angles at once, then picking the best ones.
I want it to work for things like design choices, fuzzy bugs, naming, API ideas, and any question where I’d normally ask for a few options. It should split into separate thought paths with different mindsets, compare them, drop weak or risky ideas, and then expand the strongest ones into a useful final answer. I’d like it to be easy to use with Claude Code and other agent setups, with a clear install and simple docs showing how to try it on a sample prompt.
Please keep the implementation in TypeScript, include tests and a way to evaluate the results, and make sure the examples show the difference between a normal single answer and this wider idea search. If you need to look up current docs online while wiring it in, go ahead.
Are you gonna build this?
make sure you review the code using coderabbit