Update to fstack

{
  "description": "Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.",
  "included_files": [],
  "name": "principle-exhaust-the-design-space",
  "skill_md_contents": "---\r\nname: principle-exhaust-the-design-space\r\ndescription: \"Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.\"\r\nuser-invocable: false\r\ndisable-model-invocation: true\r\n---\r\n\r\n# Exhaust the Design Space\r\n\r\nWhen 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.\r\n\r\n**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.\r\n\r\n**When it applies:**\r\n- Novel UI interactions (no prior art in the codebase)\r\n- Architectural choices with multiple viable approaches\r\n- Product design decisions where user experience depends on feel, not logic\r\n\r\n**When it doesn't:**\r\n- Mechanical implementation where the pattern is established\r\n- Bug fixes or refactors with a clear target state\r\n- Changes where constraints dictate a single viable approach\r\n"
}