Artificial Intelligence for Science (AI4S) is emerging as a key research paradigm for accelerating knowledge discovery in chemistry and materials science. Plenty of efforts have been dedicated to this area, where the efficient extraction of chemical experimental protocols plays a crucial role, as it bridges the gap between domain-specific scientific knowledge and the automated execution of experiments. To explore its potential and facilitate the community, we develop a novel automated system to extract experimental protocols through multi-module collaboration. Our designed system consists of several core modules, including literature uploading and OCR parsing, protocol information extraction based on prompt keywords, multi-model result selection, and expert feedback for revision. We also validate its customized optimization across four representative scenarios: high-entropy alloys (HEA), metal-organic frameworks (MOF), organic synthesis (OS), and general synthesis domains (GD). And the results demonstrate the practicality and stability of our designed system. Therefore, this system can offer an alternative and efficient approach for extracting experimental protocols, laying the foundation for building intelligent and automated chemical experimentation platforms. System access URL: https://ai4s.iflytek.com/annotation .