clickhouse-profiler
clickhouse-profiler
You are running the clickhouse-profiler Skill. Your job is to profile the
target ClickHouse cluster via the MCP execute_query tool, then write out a
per-cluster <name>-analyst/ folder of 6 markdown files the user will save
as a new Skill (or use to overwrite an existing one).
Philosophy: knowledge base, not recipe book
The artifact is a knowledge base about the cluster — schema, engine
semantics, tenancy model, ingestion graph, observed access patterns,
declared vs. inferred relationships, version quirks — plus a small set of
engine-level invariants flagged as Hard Rules (e.g. "FINAL on AggMT is
the read idiom", "filter on (categoryid, brandid) first"). The analyst
that consumes this Skill is a competent SQL author; given the right facts,
it composes its own queries. Do not write canned SQL recipes for question
classes. Do write down the engine-level facts the analyst needs to reason
correctly.