The combination of wearable sensors with machine learning enables intelligent perception in human-machine interaction and healthcare, but achieving high sensitivity and a wide working range in flexible strain sensors for signal acquisition and accurate recognition remains challenging. Herein, we introduced carboxymethyl cellulose (CMC) into a carbon nanotubes (CNTs)/MXene hybrid network, forming tight anchoring among the conductive materials and, thus, bringing enhanced interaction. The silicone-rubber-encapsulated CMC-anchored CNTs/MXene (CCM) strain sensor exhibits an excellent sensitivity (maximum gauge factor up to 71 294), wide working range (200%), ultralow detection limit (0.05%), and outstanding durability (over 10 000 cycles), which is superior to most of the recently reported counterparts also based on a conductive composite film. Moreover, the sensor achieves seamless integration with human skin with the help of a poly(acrylic acid) adhesive layer, successfully obtaining stable and clear waveforms with meaningful profiles from the human body. On this basis, we proposed and realized a novel in-air handwriting recognition method via extracting multiple features of high-quality strain signals assisted by deep neural networks, achieving a high classification accuracy of 98.00 and 94.85% for Arabic numerals and letters, respectively. Our work provides an effective approach for significantly improving strain sensing performance, thereby facilitating innovative applications of flexible sensors.