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.
- Save the prompt that worked so the next person reuses it
- Keep one ask per prompt — chaining beats cramming
- Lower the reading level, then check what broke
Start with the smallest version
Lock the parts that never change and leave one slot for the variable. Now every run shares a family resemblance instead of starting from scratch.
- Name the audience and the single goal before you generate
- Compare two outputs instead of trusting one
- Save the prompt that worked so the next person reuses it
Write down what you never want as explicitly as what you do. The exclusions often do more work than the instructions.