What problem does it solve? AI systems often lose track of relevant information across long conversations, multi-agent pipelines, and enterprise knowledge bases. This Skill provides expert guidance for designing context engineering systems that deliver the right information, memory, and tools to AI agents at the right time. ## Core Features & Use Cases - Context Engineering & Orchestration: Design dynamic context assembly, token budget management, and context pruning strategies for multi-agent workflows. - Vector Databases & RAG: Implement semantic search with Pinecone, Weaviate, or Qdrant, plus advanced Retrieval-Augmented Generation pipelines with chunking and hybrid search. - Memory & Knowledge Graphs: Architect long-term, episodic, and working memory systems, and build knowledge graphs with entity linking and semantic reasoning. - Use Case: When building a customer support platform with multiple AI agents, use this Skill to design context handoff protocols, shared memory stores, and retrieval pipelines so each agent receives coherent, relevant state. ## Quick Start Ask the AI to design a context management architecture for your multi-agent workflow, including vector retrieval, memory layers, and token budget optimization.
