Deep learning techniques automate the classification of skin diseases from dermoscopic images, to enhance diagnostic precision and accelerate treatment processes. Due to the high health risks associated with malignant conditions like melanoma, early and accurate detection is essential. A CNN model consists of 2500 dermoscopic images from ISIC archive, which includes nine distinct classes of skin conditions. To improve model performance, we applied techniques like rotation, scaling, and color adjustments, effectively increasing the training dataset. This enhanced the model’s ability to generalize to new images, reducing training time and improving accuracy. The final model achieved a high accuracy of 91.0%, with sensitivity and specificity rates above 90% across all classes, proving its capability to distinguish between different skin conditions accurately. Visualization tools, such as Matplotlib, make the model’s output more interpretable. These results emphasize the potential of deep learning in dermatology, offering a valuable tool for accurate and early skin condition diagnosis. Future work will focus on further improving classification accuracy and robustness by expanding the dataset to include more diverse skin types and incorporating clinical metadata.