Skin Cancer is a significant global health concern that re-quires an advanced technique for early and precise detection to improve patient outcomes. Despite this fact, the spike in the fatality rate is due to the absence of immediate and user-friendly healthcare assistance as well as medical care. This work intends to provide easy and quick pre-liminary research aid to detect skin cancer. The International Skin Imag-ing Collaboration (ISIC) dataset underwent training using some efficient deep-learning models. The model that illustrated robust outcomes, the Region-specific Convolutional Neural Network (RCNN), served as the chosen option for seamless integration with the chatbot named Skanobot. It acts as a virtual artificial intelligence (AI) powered health assistance that provides a reliable, accessible, and user-friendly research tool for early risk assessment. It enables users to upload skin lesion images for real-time analysis and provides a diagnostic report indicating whether the lesion falls under benign, malignant, or premalignant categories. The goal is to provide a research tool that can be further advanced to help people with an early risk assessment, helping them to seek proper anal-ysis and further treatment. It seeks to bridge the gap between advanced technology and the healthcare industry.