Use this skill when user wants to view one or multiple PDB / SDF files in the 3D structure viewer. Trigger when user mentions: open pdb, open sdf, 3D structure, view protein, view molecule, or provides local .pdb/.sdf file(s) to view. Supports viewing multiple files simultaneously by chaining path parameters with '&'.
When the service is deployed on a cloud server, use this skill when the user provide a file path and ask to download to their personal computer. This skill upload a file to Alibaba Cloud OSS and generate a shareable preview link for users to download easily. Trigger especially when user mentions: download file, upload to OSS, cloud storage upload, view image, preview image, generate share link, preview file via URL, or provides a local file path that needs to be shared online.
输入PDB ID，获取相应的PDB文件
预测化合物的admet性质
Build the final collection report in two steps: model writes a report template, then script injects each paper's Brief Conclusion and abs URL from summary.md by arXiv-id placeholders.
Tool-only paper processing skill with a manual language parameter: supports batch artifact download for many papers or single-paper download, then the model manually reads source/PDF and writes summary.md in the selected language. Use when per-paper comprehension should be model-driven instead of script-generated.
Model-driven arXiv retrieval workflow for building a paper set with a manual language parameter: initialize a run, fetch metadata for each model-designed query, let the model filter irrelevant items per query by keep indexes, then merge and dedupe into per-paper metadata directories. Use when query planning and relevance filtering should be done by the model, not rule-based heuristics.
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (`subagent_parallel` default max 5, or serial).