What problem does it solve? Raw email threads are structurally chaotic: quoted replies duplicate content 4-5x, forwarded chains collapse multiple conversations, and flattened threads strip sender identity so action items get attributed to the wrong person. This Skill builds pipelines that convert raw email into clean, structured context that AI agent frameworks can consume reliably. ## Core Features & Use Cases - Thread Reconstruction & Deduplication: Resolve In-Reply-To/References header chains into conversation topology and strip quoted content across Gmail, Outlook, and Apple Mail quoting styles. - Structured Extraction: Build participant maps, decision timelines, and action items with correct sender attribution, output as JSON with source citations. - Hybrid Retrieval & Context Assembly: Combine semantic search, full-text search, and metadata filters with token-budget-aware context assembly, exposed as LangChain tools, CrewAI skills, or MCP servers. - Use Case: Connect a shared mailbox, index historical threads, and let an agent answer questions like "what did the client commit to last quarter?" with citations grounded in specific messages. ## Quick Start Ask the agent to ingest a raw email thread, reconstruct its conversation topology, and return structured JSON with participants, decisions, and action items.
