Background: Timely interventions have a proven benefit for people experiencing psychotic illness. One bottleneck to accessing timely interventions is the referral process to the specialist team for early psychosis (STEP). Many general practitioners lack awareness or confidence in recognising psychotic symptoms or state. Additionally, referrals for people without apparent psychotic symptoms, although beneficial at a population level, lead to excessive workload for STEPs. There is a clear unmet need for accurate stratification of STEPs users and healthy cohorts that this study aimed to investigate by applying digital behavioural tests. Methods: To discriminate between the STEPs users (SU; n=32) and controls (n=32, age and sex matched), we employed naive Bayes classifier, and applied it to objective, quantitative and interpretable features of a "mirror game" (MG) and trail making task (TMT). The MG is a movement coordination task shown to be a potential socio-motor biomarker of schizophrenia, while TMT is a neuropsychiatric test of cognitive function. Findings: The proposed classifier shows an excellent performance, AUC = 0.92 (95%CI 0.75-1), Sensitivity = 0.88 (95%CI 0.62-1), Specificity = 1 (95%CI 0.75-1), evaluated on 25% hold-out and 1000 folds. The study demonstrates that cheap off-the-shelf equipment (laptop computer and a leap motion sensor) records clinically relevant behavioural data sufficiently. We also find that MG and TMT are unsuitable in isolation to successfully differentiate between SU with and without at-risk-mental-state or first episode psychosis with sufficient level of performance. Interpretation: Including digital behavioural tests into healthcare practice could allow improvements in care for people at risk of developing psychotic illness. Our findings show that introduction of standardised battery of digital behavioural tests would benefit both clinical and research practice. It would allow standardization of referrals, while the high specificity of digital behavioural tests would benefit research on prognostic instruments for psychosis by enriching and homogenising clinical high-risk populations. Here we demonstrate that digital behavioural tests can be successfully used and could help to address this need. Funding: EPSRC Impact Acceleration Account, Impact & Knowledge Exchange Award, Jean Golding Institute seed corn, Avon & Wiltshire Mental Health Partnership NHS Trust Research Capability Funding. PS was generously supported by the Wellcome Trust Institutional Strategic Support Award 204909/Z/16/Z. KTA gratefully acknowledges the financial support of the EPSRC via grant EP/T017856/1.