Your build starts here
Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.
Help evaluate this reusable prompt:
[prompt]
Intended task: [task]
Required output shape: [format]
Important errors to avoid: [errors]
Create a small representative evaluation set with normal cases, ambiguous cases, boundary cases, and an input that should produce no result or a clear refusal to infer missing facts. State the expected result or scoring rule for each case.
Compare prompt revisions on the same cases. Report specific failures, propose one targeted revision, and rerun the relevant cases if tools allow. Do not use a confidence claim as a substitute for correct output.Make this prompt yours
Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.
The docs behind it
These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.
Documentation links checked .
Editorial review · October 28, 2026
Limited: Read the complete original template or project/path specification for conceptual consistency, explicit scope, and checkable outcomes. No implementation or prompt-quality benchmark was executed.