All skills

Guides Claude through DeepChem workflows for molecular property prediction — from SMILES loading and featurization to GNNs and pretrained-model fine-tuning.

Retrieve facts from 78 documented public database APIs reproducibly, with explicit endpoints, pagination, and provenance.

Organizes PyTorch code into LightningModules, Trainers and DataModules, with multi-GPU strategies and experiment logging.

Prevents silent off-by-one and wrong-build errors whenever genomic coordinates cross a file format, tool, or assembly boundary.

A skill that teaches Claude to query 20+ genomic databases quickly through the gget CLI and Python API.

Builds safety-bounded draft structures for clinical, trial, and safety reports and runs offline deterministic checks on structure and provenance.

Helps Claude write and deploy Python to Modal's serverless cloud with on-demand GPUs, volumes, web endpoints and cron jobs.

An audit-ready workflow for market reports where every claim carries source IDs and TAM/SAM/SOM plus forecasts are treated as scenarios.

Routes literature queries across 11 scholarly APIs (PubMed, arXiv, OpenAlex, Unpaywall and more) and returns papers, citations, and OA PDFs with reproducible provenance.

Deploy and drive Open Notebook — an open-source NotebookLM alternative — to ingest sources, search, summarize, and generate podcasts entirely through its REST API.

A metrology skill that tracks physical units, builds GUM/Monte Carlo uncertainty budgets, and audits Python code for silent unit and correlation bugs.

A skill that helps Claude write fast, idiomatic Polars code using its expression API, lazy engine, and pandas migration mappings.

A rigorous GeoPandas 1.1.4 playbook with correctness gates for CRS, geometry validity, join cardinality and exports, plus six local audit CLIs.

Guides Claude to read, write, and process DICOM files with pydicom 3.0.2 while enforcing PHI-safe output and a bounded de-identification preflight.

A version-pinned guide for building, simulating, transpiling, and running quantum circuits with Qiskit 2.x and IBM Quantum Runtime.

Describe a scientific diagram in plain language and get a publication-quality PNG, auto-regenerated only when an AI reviewer scores it below your document type's threshold.

An end-to-end Scanpy workflow skill for scRNA-seq: QC, normalization, PCA/UMAP, Leiden clustering, markers and cell-type annotation.

Drafts competitive funding proposals tailored to NSF, NIH, DOE, DARPA, and Taiwan NSTC review criteria and formatting rules.

A skill that guides Claude through scvi-tools deep generative models for batch correction, multimodal integration, and uncertainty-aware differential expression in single-cell data.

Zero-shot univariate time series forecasting with Google's TimesFM foundation model, including calibrated prediction intervals.