skill-opt

Use to optimize/improve an existing agent skill against scored tasks. Ports Microsoft SkillOpt: treats the target SKILL.md as a trainable document and improves it via a rollout→reflect→edit→gate→memory loop with a held-out gate, while keeping the model frozen. Trigger when the user wants to tune, harden, or measurably improve a skill.

Independent GitHub snapshot · Automated classification · Original documentation governs