Data

Provides a rigorous, step-by-step workflow for planning A/B tests, including hypothesis lock, metrics definition, sample size calculation, and execution readiness checks. Use before implementing any test to ensure validity and avoid peeking.

Provides expert guidance for planning, designing, and implementing A/B tests and growth experiments. Covers hypothesis formulation, sample size calculation, metric selection, variant design, and statistical analysis.

Normalize and analyze cross-channel ad campaign data from Google, Meta, LinkedIn, and more. Diagnose performance, quantify uncertainty, and propose evidence-labeled budget experiments for optimal spend allocation.

Provides templates and guidance for implementing analytics tracking code, such as Google Analytics event and page view tracking, to measure user behavior.

Converts laboratory instrument output files to Allotrope Simple Model (ASM) JSON or flattened CSV, standardizing data for LIMS, data lakes, and analysis. Supports auto-detection of instrument types and generates reusable parser code for data engineers.

Run nf-core pipelines (rnaseq, sarek, atacseq) for RNA-seq, WGS/WES, and ATAC-seq analysis. Handles local or public data, samplesheet creation, and genome management.

Guides deep learning-based single-cell analysis using scvi-tools, covering data integration, multi-modal analysis, label transfer, and spatial transcriptomics. Ideal for scRNA-seq, ATAC-seq, and CITE-seq data.

Performs quality control on single-cell RNA-seq data using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when you need to QC, filter low-quality cells, or assess data quality.

Answer data questions from quick lookups to full analyses. Use for single metric lookups, trend investigations, segment comparisons, or formal data reports.

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.

Create publication-quality visualizations with Python. Use when turning query results or a DataFrame into a chart, selecting the right chart type for a trend or comparison, generating a plot for a report or presentation, or needing an interactive chart with hover and zoom.

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.