Grade the prompt before it grades your output.
Rubrkit grades prompts, agent specs, commands, skills, and workflows against a clear rubric, then rewrites them into instructions you can test.
Specimen RBR-082
Undefined success criteria
The model can answer, but it has no reliable way to know what good means.
Objective clarity
4/5
Output specification
3/5
Evaluation criteria
2/5
An editorial loop for instructions that need to hold.
01
Submit the specimen
Drop in a prompt, command, skill, agent spec, or workflow.
02
Rubrkit marks it
The audit grades the instruction against the rubric for that artifact type.
03
Rewrite with a gate
Get specific fixes, a stronger version, and checks that prove it works.
One grading system, five instruction artifacts.
Rubrkit classifies the artifact and switches to the rubric that matches how it is supposed to behave.
Most prompt tools generate more text. Rubrkit shows you what is weak, why it matters, how to fix it, and whether the fix can survive a real eval.
From vague ask to inspectable instruction.
Write a professional launch email for my new course and make it engaging.
Write a launch email for [TARGET AUDIENCE] that drives [PRIMARY GOAL]. Use a clear subject line, three short sections, one CTA, and avoid claims that are not supported by [CONTEXT].
Free now, built for serious review loops.
Pro features are staged as locked states while the product is in preview.
Free
$0
For quick checks and first rewrites.
Limited audits
Basic score
Top 3 issues
One rewrite
Pro
Preview
For builders who reuse and test instructions.
Full rubric
Advanced rewrites
Eval kit generation
Version comparison
Saved library
Exports
Team
Preview
For shared standards and review workflows.
Team library
Shared rubric library
Admin controls
Private examples
Review reports