You don't need a hundred writing prompts. You need five you trust and actually reuse.
Anchor to one reader
Ask for the reasoning, then the result. When the model shows its steps you can see exactly where to push back.
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.
Generate options, not answers
Treat the first output as a draft, not a verdict. The prompt does the typing; you keep the judgment about what ships.
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.