This study introduces a novel resting-state functional connectivity (rs-FC) magnetic resonance imaging (MRI) biomarker for diagnosing schizophrenia spectrum disorder (SSD), developed using customized machine learning on an anterogradely and retrogradely harmonized dataset from multiple sites, including 617 healthy controls and 116 patients with SSD. Unlike previous rs-FC MRI biomarkers, this new biomarker demonstrated a high accuracy rate of 77.3% in an independent validation cohort, including 404 healthy controls and 198 patients with SSD from seven different sites, while overcoming across-scan variability. It specifically identifies SSD, differentiating it from other psychiatric disorders. Our analysis identified 47 important FCs significant in SSD classification, many of which are involved in the pathophysiology of SSD. These FCs could be potential trait, state, and staging markers for effectively predicting delusional tendencies, specific symptoms, and disease stages. This research underscores the potential of rs-FC as a clinically applicable neural phenotype marker for SSD.