What problem does it solve? Answering questions that span multiple systems (chat, wikis, task trackers, email) is slow and error-prone when done manually, and single-source searches often miss the real answer. This Skill turns one natural language question into coordinated, source-specific searches and merges the evidence into a single coherent answer. ## Core Features & Use Cases - Query Decomposition: Classifies questions by type (decision, status, document, person, factual, temporal, exploratory) and extracts keywords, entities, intent signals, and constraints. - Source-Specific Query Translation: Maps enterprise filters like from:, in:, and after: to the correct syntax for chat, knowledge base, and project tracker sources, choosing semantic or keyword search appropriately. - Ranking and Synthesis: Scores results by relevance, freshness, authority, and completeness, then deduplicates and merges them into one answer. - Use Case: A user asks "What did we decide about the API migration timeline?" The Skill runs parallel searches across chat, the wiki, and the task tracker, prioritizes thread conclusions and meeting notes, and returns a synthesized decision summary. ## Quick Start Ask the assistant to find what was decided about a project across chat, the wiki, and the task tracker, and have it synthesize the results into one answer.
