Structured guidance for building production AI agent systems through effective context management and multi-agent architectures.

• Covers foundational context engineering concepts including attention degradation patterns, context poisoning, and signal-to-noise optimization for language models
• Provides architectural patterns for multi-agent coordination (supervisor, peer-to-peer, hierarchical), memory system design, and filesystem-based context management
• Includes operational excellence guidance on context compression, token optimization, and multi-dimensional evaluation frameworks for production systems
• Addresses tool design principles, hosted agent infrastructure patterns, and staged project development methodology with idempotent pipelines
• Organized as an interconnected collection of 11 skills covering fundamentals, architecture, and operations that work independently or in combination