Humans exhibit a remarkably robust reaction to external perturbations that prevent dropping objects held in hand, using only tactile inputs. In less than 200 ms, the sensorimotor system processes tactile information stemming from the deformation of the skin, to determine the frictional strength of the contact and to react accordingly. Given the thousands of afferents innervating the fingertips, it is unclear how the nervous system can process such a large influx of data in a sufficiently short time span. In this study, we measured the deformation of the skin during the initial stages of incipient sliding for a wide range of frictional conditions. We show that the dominant patterns of deformation are sufficient to estimate the distance between the frictional force and the frictional strength of the contact. From these stereotypical patterns, a classifier is able to predict if an object is about to slide during the initial stages of incipient slip. The prediction is robust to the actual value of the interfacial friction, showing sensory invariance. These results suggest that the nervous system efficiently encodes tactile information by projecting the measured deformation of the skin onto a compact basis of deformation patterns, that we call Eigenstrains. Our findings suggest that only 6 of these Eigenstrains are necessary to classify the slippage sensed by tens of thousands of afferents. These findings are relevant to the understanding of the unconscious regulation of grasp, and the insights are directly applicable to the design of robotic grippers and prosthetics that rapidly react to external perturbations.