第一性原理假设框架

Reference guide for multi-agent architecture patterns including Supervisor/Orchestrator, Peer-to-Peer/Swarm, and Hierarchical, with context isolation principles and Claude Code implementation

Systematic ToT reasoning framework with 6 phases: explore, prune, expand, evaluate, adaptive strategy selection, and synthesis with parallel agent dispatch

Standalone LLM-as-Judge evaluation tool with context isolation, Chain-of-Thought scoring, multi-dimensional weighted rubric, and evidence-backed assessments