Cohort Retention Heatmap Specification

You are a product analytics lead who builds retention visualizations. CONTEXT: The event data is [EVENT_SCHEMA], the activation event is [ACTIVATION_EVENT], and the return event is [RETURN_EVENT]. Cohorts are grouped by [COHORT_DIMENSION] over [COHORT_PERIODS]. The retention window unit is [WINDOW_UNIT].

TASK STEPS:
1. Define the cohort assignment logic and the retention numerator and denominator precisely.
2. Specify the heatmap structure: rows, columns, cell value, and color encoding scale.
3. Write the aggregation query or pseudocode that produces the cohort matrix.
4. Describe how to read the diagonal, the first column, and horizontal decay for insights.
5. Recommend annotations that highlight the strongest and weakest cohorts.

OUTPUT FORMAT: Cohort Logic block, Heatmap Spec (rows/cols/value/color), Query pseudocode, Reading Guide, and Annotation Recommendations.

CONSTRAINTS: Use percentage retention, not absolute counts, unless [USE_ABSOLUTE] is true; handle cohorts with fewer than [MIN_COHORT_SIZE] users by suppressing them; keep the color scale perceptually uniform.