Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills

Abstract

Automating multistep computational chemistry tasks remains challenging because reasoning, workflow specification, software execution, and high-performance computing (HPC) execution are often tightly coupled. We demonstrate a decoupled agent-skill design for computational chemistry automation leveraging OpenClaw. Specifically, OpenClaw provides centralized control and supervision; schema-defined planning skills translate scientific goals into executable task specifications; domain skills encapsulate specific computational chemistry procedures; and DPDispatcher manages job execution across heterogeneous HPC environments. In a molecular dynamics (MD) case study of methane oxidation, the system completed cross-tool execution, bounded recovery from runtime failures, and reaction network extraction, illustrating a scalable and maintainable approach to multistep computational chemistry automation.

Figures (3)

• Figure 1: Architecture of the OpenClaw-based decoupled agent-skill framework for computational chemistry automation.
• Figure 2: (a) Schematic of the LLM-based decision-making process; (b) Workflow of the automated computational task execution process.
• Figure 3: Workflow of the methane oxidation MD simulation.