Skill Upgrader

Takes any skill file and upgrades it to Decision Theory v5 Hybrid format by spawning four parallel agents that hit Ragie partitions loaded with planning and logic textbooks. Agent 1 extracts MDP structure from LaValle, Agent 2 designs policies using Sutton & Barto, Agent 3 formalizes constraints with Blackburn's modal logic, and Agent 4 verifies safety properties from Huth & Ryan. They collaborate on a shared blackboard, then you synthesize the final skill with proper state spaces, policies, and formal constraints. It's meta-tooling for formalizing your other skills, assuming you've already got those CS textbooks indexed in Ragie. The parallel agent design is clever, though you're betting hard on having that RAG infrastructure ready.