A good research prompt isn't a magic trick. It's a checklist you don't have to remember, run by something that never gets bored.
Make the output reviewable
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.
Name the failure modes
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.