MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
Use this skill before running any EDA, funnel, or insight query against the Atlys `atlys` ClickHouse database, or before trusting a business/data claim about it. Loads the current business context from `agent_meta.current_context` and explains the…
Use this skill whenever you've verified something new about Atlys (a contradiction, a confirmation, a new table/entity/metric, a resolved open question) and need to write it into the living context layer — the same append-only path this repo's Chronicler…
Ground-truth schema for the Atlys ClickHouse `atlys` database — real table and column names, data quirks, metric formulas, and the planted contradictions in base_context.md to surface. Apply on every Atlys analytics query so column names and metric…
Use when a newly instrumented feature table has been created and you must analyze it end-to-end and produce a PM-ready insight summary AND a machine-readable insights manifest (Atlys/schemas/{spec_name}.insights.json — numeric confidence scores, related known…
Use when analyzing the Atlys 4-step conversion funnel (destination_card_clicked -> application_started -> document_uploaded -> purchase_completed), computing drop-off, step-through, or conversion rate. Provides correct windowFunnel/uniqExact ClickHouse…
How to query the two table shapes in the Atlys `atlys` database — the 8 legacy raw tables have FLAT columns, while every newly instrumented spec is ONE table with a single JSON column named `payload`. Detect the shape with DESCRIBE first, then use the right…
Use when an anomaly or unusual segment/time movement appears in Atlys data and you need to explain the why by correlating it with the documented known-issues log (K1-K7) — e.g. iOS pay drop vs OTP autofill regression. Correlate, don't over-claim causation.