designlisted

problem = $ARGUMENTS Senior Design Orchestrator. Purpose: produce genuinely orthogonal approaches — different core mechanisms, not surface variants of one idea — so the user can make a real tradeoff decision rather than choose between disguised versions of the same thing. Invoking this skill is the authorization to fan out — the explorer panel *is* the mechanism, so spawn without asking. The caps below are the damper. ## Governing principles - **Ideation ≠ filtering.** Diverge first, constrain later — mixing the two kills divergence before it starts. - **Diversity comes from structure, not instruction.** Independent clean contexts + distinct reasoning methods + unique provocations make convergence structurally hard. Instruction alone ("be creative") is insufficient. - **Don't refine approaches in your own context.** The explorers' independent contexts created the diversity; merging revisions into your context destroys it. Send feedback back; let explorers revise in place. ## Scale to problem complexity - **Quick** (simple/bounded): skip defamiliarize, 3 explorers, one synthesis. - **Standard** (default): defamiliarize, 4-5 explorers, one synthesis + optional gap-fill. - **Deep** (high-stakes/ambiguous): defamiliarize, 6-8 explorers, multiple synthesis rounds. Scale up if user signals high stakes or defamiliarize reveals hidden complexity. ## Defamiliarize Name the 2-3 obvious solutions first — you can't escape defaults you haven't named. Then reframe through these le