data-science-ai-superpowers

Use when a research question spans multiple SQL, pandas, or notebook steps and you need explicit cohorts, windows, metrics, validation checks, outputs, and statistical methods before touching queries or cells

Use when you already have a written analysis plan and want to execute SQL, notebook, or validation tasks in a separate session with review checkpoints and rerun-based evidence between batches

Use when a metric definition, denominator, CUPED covariate, linearization choice, invariant, outlier treatment, missingness pattern, or leakage risk may distort an experiment or validation readout

Use when creating, editing, reviewing, or finalizing analytical notebooks whose code, assumptions, transformations, diagnostics, or conclusions need to be understandable to another analyst

Use when notebook results depend on parameters, caches, run order, hidden state, seeds, external helper code, or exported tables and the analysis must be rerunnable by another analyst

Use when an experiment analysis, metric study, notebook investigation, or methodology proposal is close to decision-ready and you need an independent check of design, statistics, interpretation, and reproducibility

Use when executing a written analysis plan in the current session and tasks are mostly independent across SQL extracts, notebook sections, metric validations, robustness checks, or memo sections

Use when notebook outputs, SQL results, experiment metrics, row counts, or sample ratios disagree and duplicate joins, timezone bugs, missing rows, hidden filters, or stale notebook state may explain the mismatch

Use when starting any notebook-based analytics, experiment, metric, or validation conversation and you need to route automatically to the right local data science skill before asking questions, writing SQL, or editing notebooks

Use when about to claim that an experiment result, metric validation, or notebook analysis is final, significant, trustworthy, or decision-ready and you need fresh rerun evidence instead of stale outputs

Use when receiving feedback on experiment design, SQL logic, notebook analysis, or statistical conclusions and comments may mix real methodological issues with preferences, misunderstandings, or unsupported claims

Use when a new notebook-based analytics request is still vague or could change the hypothesis, randomization unit, metric hierarchy, time window, or robustness checks before analysis starts

Use when 2 or more data science tasks are independent enough to run concurrently, such as separate SQL extracts, metric checks, robustness analyses, or review sidecars, and they do not share notebook state, output tables, or write scope

Use when planning or revisiting an A-B test, A-A validation, split methodology, or quasi-experiment and decision quality depends on the hypothesis, randomization unit, exposure unit, guardrails, or contamination risk