Skin sicknesses present critical medical care difficulties around the world, requiring precise and opportune location for successful therapy. AI became promising stuff for computerizing the discovery and characterization of skin illnesses. This study presents a clever methodology that uses the choice tree strategy for skin sickness location. In computerized location, we utilize an exhaustive dataset containing different skin sickness pictures, including melanoma, psoriasis, dermatitis, and contagious diseases. Dermatologists skillfully mark the dataset, guaranteeing solid ground truth for precise grouping. Preprocessing strategies like resizing, standardization, and quality improvement are applied to set up the symbolism for the choice tree calculation. Then, we remove applicable elements from the preprocessed pictures, enveloping surface, variety, and shape descriptors to catch infection explicit examples successfully. The choice tree model is prepared utilizing these removed elements and the named dataset. Utilizing the choice tree's capacity to learn progressive designs and choice principles, our methodology accomplishes an elevated degree of exactness in grouping skin sicknesses. Extensive experiments and evaluations on a dedicated validation set demonstrate the effectiveness of our decision tree-based method, achieving a classification accuracy of 96%. Our proposed method provides a reliable and automated solution for skin disease detection, with potential applications in clinical settings. By enabling early and accurate diagnoses, our approach has the capacity to improve patient outcomes, trim down healthcare overheads, and alleviate the burden on dermatologists.