Skill Transfer: Adapting Agent Skills from Strong to Weak Agents

Agent skills are modular bundles of instructions, code, and resources that an agent loads on demand, increasingly authored and validated on frontier models and shared as an open standard. The same skill can behave differently across models: a strong model turns it into a large accuracy gain, while a weak model realizes little of that value and sometimes performs even worse than with no skill at all, even though the skill is effective for the strong model. We hypothesize that the strong model silently supplies procedural steps the skill leaves implicit, which the weak model omits, and formalize closing this gap as \emph{Skill Transfer}: holding the skill's capability ceiling and the model's parameters fixed, we adapt the skill so a specific weak agent can execute it well. Our method abstracts strong and weak trajectories into typed execution structures, localizes their structural divergence with a graph edit distance (GED), and repairs the skill through an iterative diagnoser-patcher loop. Across three benchmarks and two model families, Skill Transfer raises pass rate over the unmodified skill significantly and well over other skill-evolution baselines. The adapted skill also improves the strong agent it was never adapted for, and transfers out of distribution to a structurally related, unseen task.