Automated software defect prediction (ASDP) is a fundamental and vital action in the software progress domain. Nevertheless, software as a contemporary system is integrally huge and complex, with several associated metrics that capture diverse aspects of software components. Such a huge associated metrics number renders building a Software Defect (SD) prediction (SDP) model so complex. Therefore, selecting and identifying a metrics subset that enhances the SDP performance of the method is imperative. The chief goal of the current work is to build an ASDP (SDP) tool and assess its performance. The SDP tool calculates significant software (CK) metrics that measure code characteristics, for evaluating software quality and anticipating issues, and four basic transformations to predict (SD) and defect density (DD). The research also compares the initial values of extracted metrics from software to those resulting from the Log, Ln, Power, and Root transformations shown in the case study. In the suggested SDP tool, the kurtosis of the software metrics decreased, and predicting DC and DD became more precise. This helps increase software quality by enhancing the classes that include defects, the suggested SDP tool has a user-friendly interface and is easy to use.