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 AI agents misattribute action items and decisions. This Skill builds pipelines that convert MIME, Gmail API, and Microsoft Graph email data into clean, structured, reasoning-ready context. ## Core Features & Use Cases - Thread Reconstruction: Resolves In-Reply-To/References header chains to rebuild conversation topology across replies, forwards, and forks. - Quoted Content Deduplication: Strips prefix-based, delimiter-based, and Outlook XML quoting to reduce token bloat by 4-5x without information loss. - Participant & Action Item Extraction: Binds commitments and decisions to the correct sender using preserved From: headers, producing participant maps and decision timelines. - Hybrid Retrieval & Context Assembly: Combines semantic search, full-text search, and metadata filters with token-budget-aware context assembly and source citations for LangChain, CrewAI, and LlamaIndex tools. - Use Case: Point an agent at a 20-message enterprise thread and receive structured JSON with deduplicated content, attributed action items, a decision timeline, and citations grounded in specific messages. ## Quick Start Ask the agent to reconstruct and analyze an email thread from your Gmail or IMAP source, returning structured JSON with participants, action items, decisions, and cited context for a given query.
