evaluate-nist-ai-rmf-govern

Implements 10 of the NIST AI RMF 1.0 GOVERN function's ~25 documented subcategories. Use when an org wants to programmatically validate their NIST AI RMF posture against a manifest of policies, role assignments, training records, and inventory mechanisms. The skill verifies that the manifest exists, is current (within declared review cadence), declares evidence, and covers at least 50% of the population each subcategory applies to. Emits one OCSF Compliance Finding (class 2003) per subcategory with `compliance.requirement` set to the subcategory ID and `compliance.status` ∈ {pass, partial, fail, not_applicable}. Use when the user mentions NIST AI RMF GOVERN, AI governance posture, AI risk-management policy audit, AI roles + responsibilities review, or AI inventory completeness check. Do NOT use as a substitute for the qualitative org-level assessment NIST AI RMF requires; this is a manifest-completeness + freshness check, not the assessment itself. Do NOT use to grade the other three functions (MAP / MEASURE / MANAGE) — those ship as sibling skills.