Owner: [TENANT_CONFIGURATION_REQUIRED — AI Governance Lead] Status: Draft
Holds scoring rubrics used by the “LLM-as-judge” evaluation prompts in evaluation-prompts.md — e.g., the specificity/fairness/consistency rubric for matching rationale, and the groundedness rubric for RAG answers.
No rubric files are populated yet in this documentation-only phase; author them alongside the first skill implementation, keeping scoring bands explicit (e.g., 1-5 scale definitions) so evaluations are reproducible across reviewers.