Surface-level air pollution is a major source of human mortality worldwide, and future emissions projections and resulting climate change are expected to alter concentrations of pollutants such as ozone and particulate matter. Estimating the health burden of these changes requires combining climate model projections with epidemiological frameworks, such as those developed in the Global Burden of Disease (GBD). However, significant barriers hinder this integration. Climate model outputs differ from health metrics in spatial resolution, temporal aggregation, and pollutant metrics. For example, GBD quantifies ozone exposure as the highest seasonal average of 8-h daily maximum concentrations, while most climate models provide hourly or monthly mean data. Furthermore, climate model outputs often require bias correction and spatial downscaling to ensure exposure estimates are as accurate as possible, so that applying exposure-response functions derived from observational data yields more trustworthy mortality projections. We present an open-access workflow explicitly designed to bridge this gap. Our goal is to enable researchers to process climate model data for health impact assessments of air quality. The workflow processes climate model pollutant data to align with GBD metrics, applies bias correction and downscaling methods, and calculates mortality using established GBD exposure-response functions and baseline demographic data. We demonstrate the workflow through a single illustrative worked example, rather than a comprehensive multi-model projection of future air-quality mortality. The underlying pipeline, however, is designed to support consistent, reproducible estimation across different scenarios and models. By making the workflow publicly available, we aim to lower barriers for interdisciplinary research and support collaboration between climate scientists and epidemiologists. Our work provides a foundation for quantifying the health implications of changing air quality under plausible future air pollutant scenarios and climate conditions, improving decision-making around mitigation and adaptation strategies.