Menu
Record observed objective values and update run history.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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-record-observation |
| description | Record observed objective values and update run history. |
Use this skill when outcomes for suggested experiments are available.
Read bo_runs/<RUN_ID>/state.json to get active_features and target_column. If the human's result is informal (e.g. "got 312 mV with 60% Ru, 40% Ir"), map it to the correct feature names. For any feature not mentioned, use the value from the original suggestion. Confirm ambiguous mappings with the user before recording.
uv run python -m bo_workflow.cli observe --run-id <RUN_ID> --data <JSON_OR_FILE>
--data formats'{"x": {"feat1": 1.0, "feat2": 2.0}, "y": 5.2}''[{"x": {...}, "y": 5.2}, {"x": {...}, "y": 3.1}]'.json file: list of {"x": {...}, "y": ...} objects.csv file: must have a y column; all other columns become xThe y key can also be the target column name (e.g. "Target" instead of "y").
Quick status check: uv run python -m bo_workflow.cli status --run-id <RUN_ID>