菜单
Decode BO descriptor suggestions back to nearest real molecules.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Orchestrate an end-to-end chemistry or materials optimization study from a plain-English research question to BO execution and a paper draft.
BO execution layer — initializes a run from a resolved experiment spec, records observations, and continues through suggest/observe/report.
Initialize a BO run from a dataset or explicit search-space JSON.
Generate a final BO report and summarize optimization status.
Run an external evaluator loop for a BO run using a pre-provisioned backend id.
Design and stabilize an expensive or fragile chemistry evaluator before BO setup.
| name | bo-decode-molecule-descriptors |
| description | Decode BO descriptor suggestions back to nearest real molecules. |
Use this skill when the BO engine has suggested descriptor vectors and the user wants the closest real molecules from a descriptor catalog.
uv run python -m bo_workflow.converters.molecule_descriptors decode \
--catalog <CATALOG_CSV> --query '<JSON>'
Optional flags: --k <N> (number of nearest neighbors, default 3).
rank, distance, and all non-descriptor metadata columns from the catalog (including original SMILES columns).--query accepts a JSON dict of descriptor values (inline JSON), matching engine suggestion x keys.--catalog is typically the catalog.csv from encode, but can be any external CSV with matching descriptor columns.