This article focuses on the design of an interactive skill-transfer agent for parameter tuning of an image sensor used to distinguish inferior goods from regular goods in a production line. The authors analyze the difficulty of transferring skills from a viewpoint of ecological psychology that takes into account the reciprocal relations between the participant and the environment. This article introduces an agent-based interactive skill-transferring system that stretches the meaning of this reciprocity as an interaction between an instructor and a successor. In concrete terms, an interactive agent system is proposed using an interactive learning classifier system with facial icons to enhance the human user’s trust in the agent. The experimental results demonstrate the effectiveness of this system in transferring a human expert’s skills.