Rubric library
Every row is a real, gradeable-criteria markdown document per the define-outcomes.md schema. Filter with ?rubric_type=text or ?rubric_type=file. See how the real field shape maps here.
rbc_cowork_feature_adoption — Cowork Feature Adoption Rubric
Scores the second improvement batch this session: an explicit audit of which Claude Cowork features (scheduled tasks, persisted artifacts, model routing, memory/dreams) were and were not adopted while building the subagentjobs workers, with concrete deterministic follow-through rather than a vague "consider using X" note.
rbc_worker_quality — Worker Quality Rubric
The rubric subagentevaluations.com actually scores this session's 9 shipped workers against. Structured as explicit, gradeable criteria per the real Managed Agents guidance: structure the rubric as explicit, gradeable criteria rather than vague ones (platform.claude.com/docs/en/managed-agents/define-outcomes.md).