The Scientific Data Skill Bank, independently developed by the Computer Network Information Center of the Chinese Academy of Sciences, has been officially launched. The platform introduces the concept of Scientific Data Skills for the first time. It organizes dataset descriptions, file structures, usage guidance, and provenance information into skill resources that AI agents can discover, understand, and invoke, facilitating the transformation of scientific data services toward an Agent-Ready model. Scientific Data Skills also incorporate the Common Science and Technology Resource Identifier (CSTR) for the first time, enabling persistent identification, standardized citation, and provenance tracking.

The first release covers six disciplines: physics, chemistry, earth sciences, biology, materials science, and computer science and technology. By supporting AI agents in the standardized discovery and use of scientific data, the platform represents an important step toward the intelligent application of scientific data and the advancement of AI for Science.

Platform: https://dataskills.onescience.cn