In this paper, an automated lesson generation system for guiding beginners to learn basic dance movements is proposed. It analyzes the dance to generate a two-phase lesson which can provide a suitable cognitive load thus offering an efficient learning experience. In the first phase, the dance is divided into small pieces which are patterns, and then those patterns are arranged to form an easy-to-complex learning path according to the prerequisite relations. The courseware of the second phase is responsible for guiding students to assemble all the patterns into the full dance. The learning process of the second phase adapts to the student's background knowledge and preference. It keeps monitoring the students' performances during the learning process, and adaptively adding new patterns for the students to learn. A user study which involved 52 college students who had never been trained to dance before was conducted and the results are optimistic implying that the two-phase lesson is a practical way for people to learn dance. (Contains 10 tables and 21 figures.)