Skin is one of the largest organs in the human body. It acts as a protective covering to the multiple delicate internal organs present inside the human anatomical structure and it consists of different layers like epidermis, dermis and subcutis (Rasool et al. in J. Comput. Biomed. Inform. 4, 66–75, 2023) (Rasool et al. in J. Comput. Biomed. Inf. 4:66–75, 2023). It also acts a indicator of our overall general health. Skin diseases or Skin Abnormalities are a range of conditions which affect the human skin. These diseases can vary over a large array of different types like acne, eczema, sunburns, psoriasis, vitiligo etc. According to a study, it is estimated about 10–30% of the total population of the world suffers from different skin afflictions with different degrees of pain or suffering. The effect of skin abnormalities in a country or a specific region can be based on different factors like conditions, environment and geographical variation, age demography, lifestyle factors etc. (Inthiyaz et al. in Adv. Eng. Softw. 175, 103361, 2023) (Inthiyaz et al. in Adv. Eng. Softw. 175, 2023). These diseases should be contained as they can have an economic impact in the region where the disease is rampant. The impact can be in the form of increased healthcare costs, work absenteeism and reduced productivity in different sectors of the economy. In some cases, it can lead to disability and necessitate long term treatment (Chaturvedi et al. in Multimed. Tools Appl. 79(39–40), 28477–28498, 2020) (Chaturvedi et al. in Multimedia Tools Appl. 79:28477–28498, 2020). A considerable chunk of public resources will be needed be directed toward research and development for eradication of these diseases. Keeping in view the expeditious developments in the domain of technology and science, the tools and architectures can be used to ease the process of addressing these issues by collecting data on each patient individually and predicting the trend of the disease over time. In the research, multiple deep learning techniques are used to identify and classify the diseases by rendering the images to the machine which in turn, learns after each epoch. There are multiple deep learning classifiers used in this study namely VGG-16, VGG-19, Inception v3 and a customized architecture. A dataset called DERMNET is used as a source material for the purpose of training the data.