Data & Analytics

> [!info] What it does > Submit compact ClinicalTrials.gov API v2 requests for study search, metadata, enums, search areas, and field statistics. Use when a user wants concise ClinicalTrials.gov summaries **Source:** [skills/clinicaltrials-skill/SKILL.md](../../../skills/clinicaltrials-skill/SKILL.md) · **Domain:** [Bio Databases, Lab & Cloud Platforms](../../maps/bio-databases-platforms.md) · **Table:** [skills.base](../../skills.base) · **Index:** [Skills Index](../../index.md)

N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF/GRIB/Zarr files, climate/weather/oceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.

Labeled array, schema validation, and embedded SQL analytics workflows with xarray, pandera-validation, duckdb-docs, query, read-file, and polars. Use when combining NetCDF/Zarr multidimensional arrays, DataFrame schemas, Parquet/CSV/Arrow analytics, or validation gates for scientific data pipelines.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Headless topological data analysis and visualization with the Topology ToolKit (TTK) on top of ParaView. Use this skill when Claude needs to: (1) Compute and visualize persistence diagrams, contour trees, merge trees, and Morse-Smale segmentations, (2) Extract and render critical points of scalar/vector fields, (3) Apply persistence-based topological simplification to denoise scalar fields, (4) Run TTK filters headlessly via pvpython (loading TTK plugins and using the Scalars_ naming conventi...

Expert-thinking profile for Traffic Engineer (operations / safety / signal & corridor analysis): Reasons from LWR/CTM flow, HCM delay/v/c/LOS, K-D-PHF-DDHV volumes, ITE TGM 12th/MTIASD TIAs, Synchro/HCS/SIDRA/VISSIM workflows, and HSM SPF+CMF+EB safety — treating unc calibrated models, naive before–after crashes, and LOS-without-v/c as first-class failure modes.

Expert-thinking profile for Toxicologist (regulatory / pharmaceutical / industrial chemical safety): Reasons from dose–response, ADME/TK, MOA/AOP, and exposure context; separates hazard from risk; derives BMDL/DNEL/RfD PODs and interprets OECD/ICH batteries with vehicle, strain, S9, and histopath artifacts as first-class failure modes.

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Expert-thinking profile for Statistician (applied inference / experimental design / Bayesian-frequentist / causal & survey methods / SAP-driven consulting): Reasons from estimands, generative-model assumptions, and a budgeted Type I/II error tradeoff through analysis plans (SAP, ICH E9(R1) estimands), mixed models, multiple imputation under MCAR/MAR/MNAR, and Benjamini-Hochberg FDR while treating naive post-selection SEs, unadjusted multiplicity, ignored clustering in...

Expert-thinking profile for Statistical Physicist (theoretical / computational / equilibrium and non-equilibrium statistical mechanics): Reasons from ensembles and partition functions through finite-size scaling (Binder cumulant, data collapse), Wolff/cluster MC, and RG/MCRG to Jarzynski–Crooks fluctuation theorems; uses ALPS, NetKet, WHAM, and ED/DMRG while treating critical slowing down, subleading FSS humps, and poor work-histogram overlap as...

Design statistically honest and uncertainty-aware visualizations. Use when the user needs help showing distributions, intervals, confidence, missingness, sampling effects, or analytical rigor in charts and dashboards.

Spatial omics workflows with SpatialData and Squidpy alongside scanpy, anndata, and napari-viz. Use when working with Visium, Xenium, CosMx, MERFISH, Slide-seq, spatial transcriptomics, spatial proteomics, tissue images linked to AnnData, spatial neighbor graphs, spatial autocorrelation, ligand-receptor proximity, image features, or napari-spatialdata.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box mo...

Single-cell RNA-seq analysis in R with Seurat v5 — QC, normalization (LogNormalize or SCTransform), dimensionality reduction, clustering, marker detection, integration of multiple samples, and interconversion with AnnData/scanpy. Use when single-cell work must stay in R/Bioconductor, when collaborators expect a Seurat object, or when following an R-based tutorial. For Python single-cell workflows use scanpy/anndata instead.

RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.

Standard scRNA-seq preprocessing and clustering with Scanpy. Use for QC, normalization, HVG selection, PCA, neighbor graph construction, UMAP, Leiden clustering, and export of an analysis-ready AnnData object.

Single-cell immune receptor analysis with Scirpy for scanpy, anndata, and scvi-tools projects. Use for TCR/BCR V(D)J import, clonotype definition, clonal expansion, repertoire overlap, immune receptor QC, MuData/AnnData integration, and Scanpy-linked immune repertoire visualization.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.

Query NCBI GEO for gene expression datasets. Use when user asks about RNA-seq datasets, microarray data, expression data, GEO accessions, or finding public datasets. Triggers on "geo", "gene expression omnibus", "expression dataset", "RNA-seq dataset", "microarray dataset", "GSE", "GDS".

Expert-thinking profile for Quantitative Biologist (computational / live-imaging / dynamical systems biology): Reasons from SBML/PEtab ODE models, structural and profile-likelihood identifiability, Bayesian inference (Stan/PyMC/AMICI), and live- cell pipelines (Cellpose/TrackMate/PhotoFiTT, REMBI); treats sloppiness, phototoxicity, and segmentation-tracking artifacts as first-class failure modes.

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

Visualize, analyze, and render protein and molecular structures using PyMOL. Use when the user wants to create images of protein structures, perform structural alignments or superposition, measure distances or contacts, highlight binding sites or active site residues, color by B-factor/pLDDT, or analyze protein-ligand interactions. Do not use for docking, molecular dynamics, or sequence-only analysis.