Data & Analytics

Expert-thinking profile for Computational Neuroscientist (computational / dry / modeling & neural data analysis): Reasons from encoding/decoding, GLM/LNP spike-train likelihood, mean-field E-I balance, and neural manifolds through NEST/Brian/NEURON/BMTK, GPFA/LFADS, Brain-Score alignment, and trained-RNN reverse engineering while treating spike-sorting contamination, model non-identifiability, nested-CV leakage, and...

Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways

Ancestry decomposition PCA against the Simons Genome Diversity Project

Forecast private capital cashflows for existing portfolios using Chronograph MCP data and a Takahashi-Alexander style model. Use when Codex needs to analyze or forecast LP-level contributions, distributions, NAV, unfunded exposure, net cashflows, or Excel-style cashflow forecast outputs from existing Chronograph funds, commitments, groups, or portfolios.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

DL cell/nucleus segmentation for fluorescence and brightfield microscopy with Cellpose 4's Cellpose-SAM and CellposeDINO models. Handles grayscale, multichannel, 2D, and 3D images and outputs label masks for morphology and tracking. Use scikit-image watershed for rule-based segmentation; use Cellpose when learned generalization is needed.

Cell-cell / ligand-receptor communication analysis for single-cell data using LIANA+ (recommended consensus default), CellPhoneDB, CellChat (R), and squidpy's ligrec. Use for inferring cell-cell communication, ligand-receptor pairs, source->target signaling from an annotated .h5ad. Trigger terms - "cell-cell communication", "ligand-receptor", "CellPhoneDB", "CellChat", "LIANA", "cell interaction", "ligrec".

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

Biology research tools reference. Always available inside agent containers.

Meta-agent that routes bioinformatics requests to specialised sub-skills. Handles file type detection, analysis

Refinement loop for the bio-manuscript pipeline: three-reviewer iterative optimization (editor, computational, biological). Use when reviewing a manuscript plan, producing structured review comments, revising round by round, and tracking score and revision history toward a target journal.

Step 5 of the bio-manuscript pipeline: design the analysis-method system. Use when planning which analyses, tools, and biological validations support each figure and task, mapping analyses to BioClaw-compatible tools or fallbacks, and connecting analyses to figure panels.

Expert-thinking profile for Bayesian Statistician (probabilistic modeling / hierarchical inference / MCMC diagnostics / model criticism / decision theory): Reasons from Bayes' rule, coherent uncertainty, exchangeability, and partial-pooling hierarchy through Stan/PyMC HMC-NUTS fits, prior and posterior predictive checks, PSIS-LOO, and SBC calibration while treating divergent transitions and funnels, weak identifiability and label switching, improper posteriors, and...

Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Expert-thinking profile for Applied Mathematician (theoretical / computational / interdisciplinary modeling): Reasons from formulation-first modeling, Buckingham scaling, and asymptotics (matched expansions, boundary layers) through FEM/FVM numerics (FEniCS, PETSc, LAPACK), Tikhonov inverse problems, and ASME/Sandia V&V while treating ill-posed inversion, stiffness, and numerical diffusion as first-class failure modes.

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

Expert-thinking profile for AI Researcher (empirical ML / experiment design / evaluation methodology / reproducibility / LLM & RL / trustworthiness (robustness, fairness, safety)): Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchm...

Use for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Expert-thinking profile for Additive Manufacturing Engineer (LPBF / DED metal AM / qualification): Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.

Cut Grafana Cloud Metrics cost by shrinking active-series count with Adaptive Metrics aggregation rules — auto-recommendations from query history, custom exact/regex rules, label-drop config, unused-metric detection, and Alloy remote_write fallback. Use when investigating a high Mimir/Grafana Cloud bill, hunting high-cardinality labels (`pod_uid`, `service_instance_id`, `version`), pre-aggregating counters/gauges, dropping unused metrics, or measuring `grafanacloud_instance_active_series` bef...

Denoise an erratic 1D series with discrete wavelet decomposition + universal soft thresholding (sigma estimated from MAD of the detail coefficients) to extract the underlying trend/seasonality without lagging the signal — a far better trend extractor than rolling means for spiky retail or sensor data

Aggregate high-dimensional spatial sensor grids into hierarchical region statistics at multiple granularities

Re-cluster retail stores by scale-normalized weekday/dayoff mean+std profiles using Ward agglomerative clustering, replacing vendor-supplied "type/cluster" labels that correlate with store size instead of demand shape