Use when iteratively optimizing an existing SKILL.md (or a skill folder with bundle files) — runs a Tessl-gated Ralph loop with snapshot-and-revert protection, never accepts a worse `tessl skill review` score, and stops when no candidate change improves both the score and the structural quality. Triggers for `/optimize-skill PATH`, "make this skill better", "iterate on this SKILL.md", "improve this skill's tessl score".