Data & Analytics

Expert-thinking profile for Neuroimaging Scientist (clinical / research): Reasons from k-space acquisition physics, BOLD hemodynamics, and per-voxel statistical models through fMRIPrep/QSIPrep BIDS pipelines, FSL/SPM/nilearn analysis, neuroCombat harmonization, and TFCE/permutation inference while treating head motion, partial- volume and reference-region errors in PET, global-signal...

Orchestrates zero-to-running-app in 8 stages — prerequisites → context →

Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including multi-panel plots, figures4papers-style work, and journal-ready SVG/PDF/TIFF outputs. Use for paper or scientific plots, manuscript data visualization, 论文配图、学术写作配图、科研绘图、科研作图、画图、作图、出图、论文图表、可视化. Define the conclusion, evidence logic, data integrity, template compatibility, export needs, and reviewer...

Headless bioimage and microscopy visualization with napari. Use this skill when Claude needs to: (1) Visualize 2D/3D/multi-channel microscopy or bioimage data (TIFF, label maps, points/shapes/surfaces), (2) Render 3D volumes (MIP, iso, attenuated MIP) and capture viewport-only screenshots, (3) Configure colormaps, contrast limits, blending, scale bars, and camera in napari, (4) Run napari headlessly (no visible GUI) from self-contained Python scripts.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Multi-Omics Factor Analysis v2 (MOFA+) with mofapy2. Jointly decompose omics layers (scRNA, ATAC, proteomics, methylation) into latent factors capturing major variation. Multi-group designs. AnnData views → MOFA object → train → variance explained → correlate factors with metadata → visualize/cluster → enrich top loadings.

Expert-thinking profile for Mining Geologist (field / exploration drilling / ore deposit modelling / geostatistics / resource estimation): Reasons from deposit-type models (porphyry, VMS, SEDEX, orogenic Au, IOCG, skarn) through oriented core logging, domaining, variography, OK/MIK/LUC estimation, and Chain-of-Mining reconciliation to JORC Table 1, NI 43-101 Item 14, and CIM MRMR reporting; uses Leapfrog, GIM Suite/MX Deposit, and Parker F-series factors...

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Expert-thinking profile for Mathematical Modeler (mechanistic modeling / ODE-PDE & agent-based / identifiability & UQ / calibration & inverse problems): Reasons from nondimensionalization, conservation/positivity laws, and minimal-viable model structure through mechanistic ODE/PDE, stochastic, and agent-based formulations, profile-likelihood and Fisher-information identifiability, and Sobol/Morris sensitivity analysis, while treating sloppy unidentifiable parameters...

Reactive Python notebooks stored as pure .py files — cells form a dependency DAG, so changing one cell automatically reruns its dependents (or marks them stale under the lazy runtime) and hidden state cannot exist. Covers the notebook file format, marimo edit/run/export CLI, mo.ui interactive elements, SQL cells, running notebooks as apps or scripts, and sandboxed notebooks with PEP 723 inline dependencies. Use when creating or editing marimo notebooks, building interactive data apps or dashb...

Expert-thinking profile for Machine Learning Researcher (computational / empirical & theoretical machine learning research): Reasons from population risk, double descent, and inductive bias; enforces sacred test sets, hierarchical ablations, nested CV, and HELM/Dynabench-aware benchmarking; reports with NeurIPS and Pineau reproducibility checklists while treating leakage, meta-overfitting, benchmark contamination, Goodhart gaming, and seed...

Render a 4-panel regional LocusCompare diagnostic for one (lead variant, exposure study, outcome study) tuple - overlays GWAS Manhattan, QTL Manhattan, GENCODE gene track, and cross-trait scatter colored by LD r². Use when an agent needs visual confirmation that two GWAS / QTL signals share the same causal variant (the Liu 2019 LocusCompare convention). Inputs: lead variant + two pre-fetched harmonised sumstats slices (or eQTL Catalogue / GWAS Catalog identifiers for bundled fetch). Output: P...

Expert-thinking profile for Life-Cycle Assessment Analyst (attributional/consequential LCA / inventory & impact assessment / allocation & uncertainty / EPD critical review (ISO 14040/14044, EN 15804)): Reasons from functional unit, attributional-versus- consequential framing, and ISO 14044 allocation hierarchy through openLCA, SimaPro, Brightway2, ecoinvent, and LCIA methods like TRACI and EF 3.0 while treating allocation-driven ranking flips, biogenic-versus-fossil carbon mistagging, cut-off...

Compute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified. Use when an agent needs LD coloring for a regional plot or LD pruning around a candidate causal variant. Single client (on-demand region fetch from EBI 1000G FTP); no multi-GB cold-start.

Expert-thinking profile for Information Retrieval Scientist (ranking / evaluation (TREC, trec_eval) / BM25 + neural retrieval / search-log privacy): Reasons from the Probability Ranking Principle, ranked-list utility, and candidate-generation-versus- re-ranking separation through BM25 baselines, dense and cross-encoder retrieval, and TREC-style qrels evaluated with trec_eval and nDCG, while treating position-biased clicks, unjudged-as-nonrelevant pools, analyzer...

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Expert-thinking profile for High-Energy Astrophysicist (observational / computational X-ray & gamma-ray): Reasons from Compton/synchrotron radiative processes and compact- object energetics through HEASARC/Fermi/Swift/XMM/Chandra/NuSTAR/XRISM pipelines, XSPEC/Sherpa spectral fitting, pile-up and background systematics, blazar/GRB/TDE campaigns, and GCN multi-messenger coordination while treating RMF versioning, soft- proton...

Search Hex projects and ask Hex Threads questions. Use when the user explicitly references Hex, Hex projects, Hex dashboards, Hex data apps, Hex Threads, or asks to search an existing Hex workspace asset.

Expert-thinking profile for Heliophysicist (remote sensing + in situ / MHD-plasma / space-weather forecasting / magnetosphere coupling): Reasons from MHD, magnetic topology, reconnection, and IMF Bz coupling through SDO/HMI magnetograms, DEM and NLFFF analysis, coronagraph GCS fitting, and WSA-ENLIL/EUHFORIA ensembles while treating LOS foreshortening, AIA stray light, force-free NLFFF breakdown, and Dst/SYM-H saturation as first-class failure modes.

Calculate polygenic risk scores from DTC genetic data using the PGS Catalog

Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP. Use when an agent needs GWAS beta / SE / p-value for every variant in a window for one specific study (GCST accession). Input: accession, chromosome, start, end. Output: harmonised TSV slice in canonical format.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Analyze and edit connected Google Sheets with range precision. Use when the user wants to create Google Sheets, find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, create or repair charts, clean or restructure tables, write concise summaries, or make explicit cell-range updates.