Gives Claude expert use of datamol, the Pythonic RDKit wrapper, for SMILES parsing, standardization, fingerprints, clustering and 3D conformers.
Run OpenMM molecular dynamics simulations and analyze the resulting trajectories with MDAnalysis.
Guides Claude through loading molecular data and training/evaluating property-prediction models, from fingerprint baselines to GNNs and pretrained chemistry transformers.
Restructures PyTorch code into LightningModules and configures multi-GPU training, logging, and checkpointing.
Predict spatial expression for ~19k protein-coding genes directly from 224x224 H&E histology tiles.
Drafts and validates research-only CDS artifacts — intended-use statements, GRADE evidence profiles, aggregate cohort tables, survival plans, model evaluations, and privacy/governance checklists.
Safely detects the CPU, memory, disk, scheduler and accelerator limits that actually apply to the current process, producing a redacted JSON snapshot plus conservative workload plans.
Discovers and wires up curated Hugging Face datasets, models, and Spaces across 17 scientific domains, from protein design to climate modeling.
An expert skill for designing, reviewing, migrating and safely planning MATLAB/Octave numerical workflows.
Turns SMILES structures into ML-ready feature vectors using 100+ featurizers such as ECFP, MACCS, descriptors and ChemBERTa embeddings.
A skill that guides Claude through LaminDB artifact registration, querying, lineage tracking, and ontology-backed validation for biological data.
Teaches Claude Code to build, deploy and scale Python and AI/ML workloads on Modal's serverless GPU cloud.
Builds auditable market research reports where every claim maps to a source and TAM/SAM/SOM plus forecasts are presented as scenarios.
Query the 1000 Genomes Project cohort (3,202 genomes, GRCh38) at the level of individual participants and variants.
Authors, reviews, migrates, and simulates Opentrons Python Protocol API v2 protocols for Flex and OT-2 lab robots.
An end-to-end phylogenetics pipeline: MAFFT alignment, IQ-TREE 2 / FastTree ML inference, and ETE3 tree analysis and plotting.
Extract velocity fields from PIV image pairs and derive vorticity, strain rate, and turbulence statistics with OpenPIV.
Run and interpret ORA/GSEA pathway enrichment (GO, KEGG, Reactome, MSigDB) from gene lists or ranked gene tables.
Teaches Claude idiomatic Polars — expressions, lazy queries, and pandas-to-Polars migration.
Reads, validates, and exports protocols.io data against current v3/v4 REST and MCP contracts, while mutations are produced only as non-executing dry-run plans.