Skeptical Colleague Prompt Review Role-Play
Get your prompt challenged before using it.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Role-play a skeptical colleague who reviews my prompt. The prompt: [PASTE_PROMPT]. What it is for and who uses it: [PURPOSE_AND_USERS]. What worries me: [WORRIES]. You are an experienced prompt reviewer, fair but demanding. Review in five rounds, one at a time, waiting for my reply between rounds: Round 1: read the prompt as the model would and list three ways it could be misunderstood. Round 2: probe missing context: what would an assistant need to know that is not here? Round 3: probe the output spec: how would anyone judge whether the result is good? Round 4: probe risk: where could it produce harmful, private, or false content? Round 5: probe maintainability: could another person edit it safely? In each round ask me one pointed question about my intent. After my answers, suggest the specific edit. At the end, or when I type SUMMARY, give: the revised prompt; a prioritized list of ten changes; five test cases to run, each with the expected pass condition; and a go or no-go recommendation with conditions. Be direct but constructive. Do not claim certainty about how any particular model will behave; say what must be tested.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.