Rules reference

Understand what the deterministic engine checks

All currently shipped rules are deterministic. They score the structure and clarity of the prompt itself, not the quality of a model response.

Rules in the current public release

Rule IDCategoryWhat it checks
min-lengthspecificityPrompt is not too short.
max-lengthstructurePrompt is not excessively long.
no-output-formatspecificityThe expected answer format is specified.
no-examplesbest-practiceFew-shot examples are present.
no-rolebest-practiceA role or persona is assigned.
no-contextspecificityBackground context is provided.
ambiguous-negationclarityNegative instructions are not overly vague or stacked.
no-constraintsspecificityExplicit constraints are defined.
all-caps-abuseclarityALL CAPS is not overused for emphasis.
vague-instructionclarityQualifiers like good or appropriate are not left undefined.
missing-taskclarityAn explicit task or request is detectable.
no-structured-formatstructureLong prompts use visible structure such as sections or tags.

How scoring should be interpreted

  • The score is a structural signal, not a guarantee of output quality.
  • Rule weight and severity come from the active profile.
  • `missing-task` is intentionally the most important rule in the default experience.
  • Suggestions are sorted by likely impact, not just in file order.

What rules are not doing yet

PromptScore does not currently validate runtime grounding, output correctness, safety outcomes, or tool behavior. Those are different problems and should remain clearly separated from prompt linting.