Command Claude Code
Measure ConGLUDe model performance on labeled benchmark data. Invoke ONLY when the user explicitly mentions "ConGLUDe" or "conglude" together with intent to assess model quality on data with known ground truth — e.g. "evaluate", "benchmark", "run eval.py", "compute metrics", "test set performance", "AUC", "BEDROC"…
Command Claude Code
Score unlabeled ligands against proteins using ConGLUDe. Invoke ONLY when the user explicitly mentions "ConGLUDe" or "conglude" together with prospective prediction intent — e.g. "run predict", "score ligands", "virtual screening", "predict affinity", "run predict.py", "screen a library", "embed a library", "encode…
Command Claude Code
Install or troubleshoot the ConGLUDe conda environment and repository. Invoke when the user mentions "ConGLUDe" or "conglude" together with environment setup intent — e.g. "install conglude", "set up the environment", "create the conda env", "fix import errors", "setupenv.sh", "install dependencies", "CUDA mismatch"…
Command Claude Code
Train the ConGLUDe model. Invoke ONLY when the user explicitly mentions "ConGLUDe" or "conglude" together with training intent — e.g. "train", "start training", "run train.py", "fine-tune", "retrain", "train the model", "debug training run". Do NOT trigger on evaluation, prediction, or embedding requests — use the…