What problem does it solve? Hierarchical multi-agent systems waste tokens by replaying the full orchestrator trajectory into every worker call, while summarization adds latency and loses information. This Skill explains how to transfer orchestrator state to workers at the representation level by compacting the worker model's KV cache instead of re-serializing text. ## Core Features & Use Cases - Task-guided KV compaction: Score trajectory positions by attention from the current worker task prompt, keeping only relevant tokens via a shared global mask and MAD-based thresholding. - Decision framework: Compare Latent Briefing against prefix caching, summarization, and RAG to pick the right cross-agent memory mechanism for your bottleneck. - Use Case: In a recursive orchestrator-worker system doing long-document QA, compact the growing orchestrator trajectory before each worker call to cut worker tokens while preserving task-relevant reasoning state. ## Quick Start Ask the AI to explain how to share orchestrator memory with workers via KV cache compaction using task-guided Attention Matching.
