Documenting responses of biotic assemblages to coal-mining impacts is crucial to informing regulatory and reclamation actions. However, attributing biotic patterns to specific stressors is difficult given the dearth of preimpact studies and prevalence of confounding factors. Analysing species distributions and abundances, especially stratified by species traits, provides insights into how assemblage composition shifts occur. We evaluated stream habitats and fish assemblages along a mining intensity gradient in 83 headwater (2nd- and 3rd-order) streams of the upper Clinch and Powell river basins in Virginia. Our multivariate gradient (MINE.PC1) was based on percentages of watershed area covered by surface mine, underground mine and valley fill to represent spatial variance in mining intensity. MINE.PC1 was positively correlated with conductivity and percentage of substrate as cobble. Forty fish-assemblage metrics were analysed via boosted regression trees to assess assemblage responses to mining intensity, while accounting for environmental variation and spatial structure among sites. Conductivity and MINE.PC1 were strongly negatively related to occurrences of Fantail Darter (Etheostoma flabellare) and sculpin (Cottus) spp. Several taxonomic, trophic and reproductive metrics of assemblage composition responded strongly to mining intensity or its instream correlates. For example, coal mining favoured omnivore-herbivores, but inhibited invertivores, simple lithophils and nonsimple nonlithophils. We revealed distinct negative and positive responses to mining-related stressors, which suggest changes to macroinvertebrate prey availability and/or contaminant loads contribute to fish extirpations in coalfield streams. Future assessments of mining impacts on fish assemblages could be more instructive by including characterisations of physicochemical stressors and regionally calibrated biotic metrics with demonstrated sensitivity to mining.