Looker Performance Optimizer

This master developer skill governs the lifecycle of auditing, diagnosing, and optimizing query performance in new or existing Looker projects. It enforces a strict performance-first design, database caching alignment, strategic data materialization, and advanced SQL profiling using parallel subagents and Looker MCP tools.

All optimizations developed under this skill must be dialect-agnostic, database-efficient, and preserve the integrity of existing business logic.

1. Operating Modes (Preventative vs. Reactive)

This skill operates in two distinct modes to address performance at different stages of the development lifecycle:

Mode A: Performance-by-Design (Preventative Engineering)

Use this mode when adding new explores, views, or Persistent Derived Tables (PDTs) to an existing project. The agent MUST ensure that performance is engineered from the first second:

1. Correct Join Cardinalities: Declare precise join relationships (many_to_one, one_to_one) immediately to prevent compiler-driven Symmetric Aggregations.
2. PDT Indexing & Partitioning: Every new PDT definition MUST declare partition keys and clustering/index keys based on the fields most commonly used as dashboard filters.
3. ETL-Aligned Caching: Every new explore MUST be assigned to a centralized datagroup triggered by an ETL/ELT metadata query, avoiding arbitrary persist_for time windows.