Deep Idea

Generates genuinely novel ideas through five orthogonal forcing functions, adversarial novelty killing, and a structured mutation loop. The core insight: LLMs produce obvious ideas because they interpolate over existing content. This skill forces extrapolation by constraining the generation process structurally — each idea must derive from a specific mechanism, not free association.

How it differs from asking "give me ideas"

Standard generation: LLM samples the mode of the distribution → produces what already exists. This skill: Forces generation from mechanisms that are structurally unlikely to produce known ideas — inversions, cross-domain transplants, edge-user designs. Then adversarially kills any that already exist. Then mutates the generator when it gets stuck.

Reference files