Extracting temporally extended skills can significantly improve the efficiency of reinforcement learning (RL) by breaking down complex decision-making problems with sparse rewards into simpler subtasks and enabling more effective credit assignment. However, existing abstraction methods either discover skills in an unsupervised manner, which often lacks semantic information and leads to erroneous or scattered skill extraction results, or require substantial human intervention. In this work, we propose to leverage the extensive knowledge in pretrained Vision-Language Models (VLMs) to progressively guide the latent space after vector quantization to be more semantically meaningful through relabeling each skill. This approach, termed Vision-language model guided Temporal Abstraction (VanTA), facilitates the discovery of more interpretable and task-relevant temporal segmentations from offline data without the need for extensive manual intervention or heuristics. By leveraging the rich information in VLMs, our method can significantly outperform existing offline RL approaches that depend only on limited training data. From a theory perspective, we demonstrate that stronger internal sequential correlations within each sub-task, induced by VanTA, effectively reduces suboptimality in policy learning. We validate the effectiveness of our approach through extensive experiments on diverse environments, including Franka Kitchen, Minigrid, and Crafter. These experiments show that our method surpasses existing approaches in long-horizon offline reinforcement learning scenarios with both proprioceptive and visual observations.