This paper explores the integration of domain-specific knowledge into prompt engineering to enhance the performance of large language models (LLMs) in scientific domains, particularly in chemistry, materials science, and biology. The authors curate a benchmark dataset that encapsulates the intricate physical-chemical properties of small molecules, their drugability, and the functional attributes of enzymes and crystal materials. They propose a domain-knowledge embedded prompt engineering method, which outperforms traditional prompt engineering strategies on metrics such as capability, accuracy, F1 score, and hallucination drop. The effectiveness of this method is demonstrated through case studies on complex materials, including the MacMillan catalyst, paclitaxel, and lithium cobalt oxide. The study highlights the potential of LLMs as powerful tools for scientific discovery and innovation when equipped with domain-specific prompts. The paper also discusses limitations and future directions for domain-specific prompt engineering development, including expanding domain coverage, integrating datasets and tools, multi-modal prompting, and human-in-the-loop refinement.This paper explores the integration of domain-specific knowledge into prompt engineering to enhance the performance of large language models (LLMs) in scientific domains, particularly in chemistry, materials science, and biology. The authors curate a benchmark dataset that encapsulates the intricate physical-chemical properties of small molecules, their drugability, and the functional attributes of enzymes and crystal materials. They propose a domain-knowledge embedded prompt engineering method, which outperforms traditional prompt engineering strategies on metrics such as capability, accuracy, F1 score, and hallucination drop. The effectiveness of this method is demonstrated through case studies on complex materials, including the MacMillan catalyst, paclitaxel, and lithium cobalt oxide. The study highlights the potential of LLMs as powerful tools for scientific discovery and innovation when equipped with domain-specific prompts. The paper also discusses limitations and future directions for domain-specific prompt engineering development, including expanding domain coverage, integrating datasets and tools, multi-modal prompting, and human-in-the-loop refinement.