Data & Analytics

Biological data analysis including diversity metrics and alignments

Advanced scientific data visualization and figure composition

Single-cell RNA-seq analysis pipeline with clustering and visualization

Deep learning model training and experiment management

Bayesian statistical modeling and probabilistic programming

Healthcare data analytics and clinical prediction modeling

Interactive scientific data visualization with Plotly

Quantum machine learning and differentiable quantum computing

Computational pathology and whole slide image analysis

Network and graph analysis for biological and scientific networks

Geospatial data analysis and visualization with GeoPandas

Query NCBI Gene Expression Omnibus for transcriptomics datasets

Genomic interval machine learning for regulatory element analysis

Automated exploratory data analysis with statistical summaries and visualizations

Phylogenetic tree visualization, manipulation, and analysis

Tools for deep-sequencing data analysis and visualization

Access Google Data Commons public datasets and statistics

Biological sequence analysis, alignment, and molecular biology computations

Protein engineering and directed evolution analysis using Adaptyv Bio platform

Writes Spark jobs, debugs performance issues, configures cluster settings for distributed data processing, DataFrame transformations, and structured streaming analytics.

Performs pandas DataFrame operations for data analysis, manipulation, transformation, time series analysis, merging, aggregation, and performance optimization.

Authorize agent payments via Machine Payments Protocol (MPP). Handles microtransactions, API purchases, service subscriptions within budget governance. Triggered by pay, purchase, buy, transaction, payment, MPP, commerce.

Audit an LLM evaluation pipeline for correctness, coverage, and reliability. 6 diagnostic areas with structured Check/Finding output. Produces prioritized findings by severity and recommends next skills to run. Catches common eval pitfalls before they corrupt your metrics. Triggers on: "eval audit", "audit evals", "evaluation audit", "check eval pipeline", "eval health"

Calibrate LLM-as-Judge evaluators against human labels. Computes TPR, TNR, precision, recall, F1, and Cohen's kappa. Detects systematic biases and recommends prompt corrections. Produces a calibration report with confidence intervals. Triggers on: "validate evaluator", "calibrate judge", "judge accuracy", "evaluator validation", "judge metrics"