Guides building 2-3 competing prototypes to compare before committing to a novel UI or architecture decision.
- What it does
- This skill encodes a design principle: when a novel interaction or architectural decision has no precedent, build two or three competing prototypes or sketches and compare them side by side before committing. It defines when the rule applies, such as novel UI interactions, architectural choices with multiple viable approaches, and product decisions driven by feel, and when it does not, such as mechanical implementation, clear-target bug fixes or refactors, and constraint-dictated single approaches. It is instructions only and produces no files or artifacts.
- When to use it
- Use it when facing a novel UI interaction or architectural decision with no prior art in the codebase and no obvious right answer. It is not meant for established patterns, bug fixes or refactors with a clear target state, or changes where constraints leave only one viable approach.
- Requirements
- No tools, packages, runtimes, credentials, or network access are required; it ships no scripts and is instructions only.
Exhaust the Design Space
When a novel interaction or architectural decision has no established precedent, explore several concrete alternatives before implementation. Building the wrong thing costs more than exploring three options.
The rule. When the right answer is not obvious, build 2-3 competing prototypes or sketches. Compare them side by side. Only then commit. Design it twice is this rule by another name. A second flavor of the first shape does not count.
When it applies:
- Novel UI interactions (no prior art in the codebase)
- Architectural choices with multiple viable approaches
- Product design decisions where user experience depends on feel, not logic
When it doesn't:
- Mechanical implementation where the pattern is established
- Bug fixes or refactors with a clear target state
- Changes where constraints dictate a single viable approach
