Treats your NeuralMemory instance like a database that needs tuning. It analyzes which memories actually get recalled versus which sit cold, runs test queries across your main topics to measure confidence scores, then proposes specific actions: consolidate five fragmented PostgreSQL notes into one solid entry, prune that 90-day-old standup note, enrich your auth topic by asking you three targeted questions. The bottleneck analysis is methodical, scoring issues by frequency times severity times fixability. What's useful here is the evidence-based approach. It doesn't guess what might be wrong with your memory graph, it measures recall patterns and shows you the numbers before suggesting any changes.
npx skills add https://github.com/nhadaututtheky/neural-memory --skill memory-evolution