The purpose of this study was to determine whether a skills-based workshop will improve medical students' management of problem drinking and alcohol dependence in simulated patients. Seventy-six 3rd and 4th year Ontario medical students were randomized to receive a 3-h workshop on either problem drinking and alcohol dependence or depression (control condition). Students then completed eight simulated office visits (OSCE stations) with simulated patients presenting with depression, problem drinking or alcohol dependence. Examiners completed a checklist of the questions asked and advice given by the student, and simulated patients and examiners completed a global rating scale. Four months later, students were sent a survey on their knowledge, attitudes, and behavior towards patients with alcohol problems. The alcohol group received significantly higher assessment and management checklist scores and global rating scores than did the depression group (p < 0.01) and performed better on almost all aspects of clinical management of both problem drinking and alcohol dependence. On the follow-up survey (n = 55) the alcohol group showed a significant increase in beliefs about self-efficacy in managing alcohol problems (p < 0.05) and had greater knowledge of reduced drinking strategies, but the two groups did not differ on other measures. A skills-based workshop causes marked short-term improvements in medical students' management of problem drinking and alcohol dependence, an increase from baseline to postworkshop in self-efficacy beliefs that was sustained through to follow-up, and greater knowledge of reduced drinking strategies. Repeated reinforcement of clinical skills may be required for a long-term impact on clinical behavior.