From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

Multi-agent systems (MAS) for structured data-science tasks externalize analytical control through workflows, but repeatedly executing orchestration incurs deployment overhead. Distilling workflows into single-agent skills raises a selective-transfer question: which components should survive? We distinguish capability resources, which expand available actions and knowledge, from pipeline guidance, which constrains explored solutions. On the same causal-estimation instances, capability-matched pipeline retention changes normalized utility by $+20.0$ points under method-selection accuracy but $-10.3$ under numerical error. We introduce Behavior-Outcome Freedom ($F$), a pre-synthesis diagnostic of signed behavior–outcome rank mismatch, and give a candidate-conditional account through Signed Anchor-Rank Transfer with an explicit remainder for coarse representations. AdaSkill preserves validated capabilities, removes runtime orchestration, and calibrates an $F$-threshold on module-level development interventions, freezing it before target construction. Across 16 matched interventions, structural effect decreases with $F$ ($r=-0.80$, $p<0.001$); 15 atomic treatments localize the reversal to pipeline guidance. Across 11 datasets and four task families, directly executed skills combine strong performance with lower latency than source workflows. Workflow-excluded construction tests the calibrated policy separately from the mechanism analysis.