A Pythonic wrapper around RDKit that handles the most common drug discovery cheminformatics tasks without forcing you to dig through RDKit's sprawling API. Use it for SMILES parsing, molecular standardization, computing descriptors and fingerprints, clustering compounds, and generating 3D conformers. It returns native rdkit.Chem.Mol objects so you can drop back to RDKit anytime you need fine-grained control. The batch processing with parallelization is solid for datasets up to a few thousand molecules, and it supports reading from S3 or GCS out of the box. If you're doing standard molecular informatics work and want sensible defaults instead of configuration archaeology, this is the right abstraction layer.
npx skills add https://github.com/davila7/claude-code-templates --skill datamol