The present study aims to examine the effectiveness of ChatGPT in teaching writing skills for vocational high school students. This study employed a quantitative research method with a quasi-experimental design to investigate the effectiveness of ChatGPT in teaching writing skills. The subjects of this study were the eleventh-grade students of SMK AL Huda Kota Kediri. The sample consisted of two classes: the experimental group, which used ChatGPT during the learning process, and the control group, which used peer-correction. The data were collected through writing tests in the form of pre test and post-test. The students’ writing was assessed based on content, organization, grammar, vocabulary, and mechanics. The collected data were analyzed using IBM SPSS Statistics 27, due to the data were not normally distributed, Mann Whitney U test was used. The results revealed a significant difference in writing achievement between the experimental and control groups. The significance value of the Mann–Whitney U test was 0.036 (p < 0.05), indicating that the use of ChatGPT had a positive effect on students’ writing skills. The experimental group achieved higher post-test scores compared to the control group. This finding indicates that students who used ChatGPT improved their writing more effectively through instant feedback, corrections, and suggestions provided during the writing process. In conclusion, the study highlights that ChatGPT is effective at enhancing students’ writing skills and can serve as a supportive learning tool in English writing classes at vocational high school level.