What problem does it solve? When a design, architecture, or business-model problem has many interacting choices, teams anchor on a few familiar combinations and miss viable ones. This Skill structures the problem as a morphological field (parameters × discrete values), prunes impossible value pairs through a reasoned Cross-Consistency Assessment, and reports exactly how many internally consistent configurations remain. ## Core Features & Use Cases - Zwicky box construction: Define 4–8 MECE parameters with 2–6 discrete values each and compute the raw configuration count as the product of value counts. - Cross-Consistency Assessment (CCA): Judge every cross-parameter value pair as consistent or excluded, with each exclusion typed logical, empirical, or normative and carrying a stated reason. - Deterministic companion tool: scripts/morph.py enumerates the consistent solution space, filters configurations by driver values, and audits CCA coverage — stdlib-only Python, offline, with JSON output. - Use Case: A product team exploring residential home-energy architectures defines five parameters (storage, control, revenue, ownership, pricing), records nine reasoned exclusions, and learns that 172 of 432 raw configurations are internally consistent — 54 of which can sell grid flexibility. ## Quick Start Ask the assistant to run a morphological analysis on your design problem, listing the parameters and their options so it can build the Zwicky box, assess pair consistency, and count the viable configurations.
