"Write me a blog post" — why this prompt fails and how to fix it
A blog post prompt that returns generic filler, the four things it never specifies, and the rewritten version that produces something usable.
Bad prompt examples, graded and rewritten
Eight prompts of the kind people actually type. Each one is scored against the same five-part rubric the free grader uses, then rewritten — so you can see exactly which change moved the grade.
"Write a marketing email" — the prompt that returns filler, rewritten
Why a one-line marketing email prompt produces generic copy, and a reusable version with audience, offer, constraints and a ranking rule.
"Write some Instagram captions" — why the output is interchangeable
A social caption prompt that returns lines you could paste under any brand, and the rewritten version that does not.
"Write a product description" — the four gaps that make it generic
A product description prompt that produces adjectives instead of information, and the version that produces something a buyer can act on.
"Write a cold email" — why it reads like every other cold email
The cold outreach prompt that produces templated openers, and a rewritten version built around a specific reason for contact.
"Give me some headlines" — the prompt with no way to pick a winner
A headline prompt that returns twenty options and no way to choose, plus the version that ranks them against a real criterion.
"Write a case study" — the prompt that produces a testimonial, not evidence
Why an open case-study prompt returns vague praise instead of a result, and the rewritten version built around a measurable before and after.
"Do a competitor analysis" — the prompt that returns a Wikipedia summary
Why an open-ended competitor analysis prompt returns generic profiles, and a version scoped to a decision you actually need to make.
Common questions
- How are these prompts scored?
- Every prompt on these pages is run through the same rubric as the free grader, scoring context, structure, specificity, reusability and decision logic. The numbers are generated when the site builds, not written by hand.
- What is the single most common problem with these prompts?
- No rule for choosing between options. Most rough prompts describe a topic and leave the model to decide what good looks like, so it returns a list and hands the judgement back to you.
- Can I use these rewritten prompts as they are?
- Yes. Replace the {{placeholders}} with your own inputs and run them in any model. They are plain text with nothing vendor-specific in them.