What problem does it solve? During incident response, engineers waste time hunting through wikis and chat history for known fixes, past incidents, and service dependency information. This Skill queries the RAPTOR knowledge base directly, surfacing curated runbooks, similar past incidents, and dependency graphs before falling back to Confluence. ## Core Features & Use Cases - Incident-Aware Search: Match current symptoms against runbooks and past incidents, optionally filtered by affected service. - Service Dependency Graph Queries: Look up dependencies, dependents, owners, runbooks, and blast radius for any service entity. - Similar Incident Retrieval: Find historical incidents with matching symptoms to reuse known resolutions. - Knowledge Teaching: Record new learnings from an investigation with typed knowledge (procedural, factual, etc.), entity links, and confidence scores, with automatic duplicate and contradiction detection. - Use Case: When payment-gateway returns 503 errors, search for matching runbooks, check the blast radius of the service, find similar past incidents, and after resolution teach the root cause back to the knowledge base. ## Quick Start Ask the agent to search the RAPTOR knowledge base for runbooks and past incidents matching the current symptoms of the affected service.
