Provide the material and clear criteria so Jev can evaluate named questions against the same context.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Evaluate a request against named categories and an urgency rubric.
/oo Jev: Evaluate this request [text] with Jev. Classify it as billing, bug, or account access using [category criteria]. Score urgency using these ordered levels [low, medium, high criteria]. Show answers and available probabilities.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →No personal API key or account authorization is required. Jev access depends on the product’s configured service.
Connect Jev →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
Jev evaluates supplied state with Noul probability questions, Choice classifications, and Score rubrics. Results include model information, answers, and usage.
Evaluate binary probabilities, choose among named categories, or score against an ordered rubric.
Evaluate text or structured JSON state against typed Noul, Choice, and Score questions with Jev.
Leina 
Wanta 
jev.evaluate No matching tools.
Yes. The shared context can be text or structured values such as records and lists.
Supply at least two ordered criteria, from the lowest level to the highest, describing what each level means.
It is a model assessment under your supplied criteria. Review the source material and criteria when using it for decisions.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.