What problem does it solve?
Textbook safety stock formulas assume roughly normal demand, but real SKU portfolios contain intermittent and high-variability items where that assumption fails silently. This Skill computes the standard zsigmasqrt(LT) result and then empirically stress-tests it against actual demand history, so you know where the number can be trusted before committing inventory capital.
Core Features & Use Cases
- Formula computation with assumption checks: Calculates safety stock and reorder points using the normal formula, including the extended form when lead time varies, and flags SKUs (CV >= 1.0 or intermittent demand) where results will be optimistic.
- Empirical stress testing: Replays actual demand history against the proposed stock level and reports both achieved cycle service and achieved fill rate, exposing the gap between theoretical and real service.
- Cost-of-nines analysis: Shows safety stock required at 90/95/98/99% service targets so service levels can be treated as pricing decisions.
- Use Case: A supply chain analyst has 12+ periods of demand history per SKU and a 95% service target in a contract. The Skill classifies each SKU by variability, computes formula-based safety stock, stress-tests it against history, and recommends per-class policies (formula, empirical sizing, or MTO) instead of one global target.
Quick Start
Analyze my SKU demand history file and compute safety stock and reorder points for a 95% fill rate target, then stress-test the results against the actual history.