Prompts tagged "feedback" in the PromptCraft library.
By default, helpful = agreeable = burying the real problem in paragraph four. Three one-line instructions reverse it: problem first, force a recommendation, explicitly forbid softening. The difference between reading and fixing.
A method dreamed up by a teacher 19 essays into a 30-essay all-nighter. Where typical AI prompts "act as an English teacher" and devolve into a wall of rubric noise, this chain solves the real grading workflow: don't comment on everything.