Economist's discipline for data analysis, causal inference, and econometrics — reduced-form and structural. A Claude Code plugin whose name is a homage to superpowers; it makes the silent failures of data work loud.
Skill Claude CodeCodex
Use throughout the EXECUTION of any analysis — while running, debugging, modeling, or cleaning data — to decide which decisions you may make on your own and which you must STOP and bring to the user first. Forces a human-in-the-loop checkpoint before any consequential analytical choice — changing the research design…
Skill Claude CodeCodex
Use when WRITING or EDITING analysis code, notebooks, or data pipelines in R, Julia, or Python — keeping the code minimal, surgical, and legible rather than over-engineered. Use whenever you're about to add a class/framework to a one-off script, refactor a working pipeline you were only asked to tweak, build…
Skill Claude CodeCodex
Use when reviewing a data analysis, notebook, script, model, or result — your own before you ship it, a colleague's before it's published, or one handed to you to "check" or "sanity-check" — in R, Julia, Python, or Stata. Hunts specifically for the silent-failure classes that pass code review but produce wrong answers…
Skill Claude CodeCodex
Use whenever an analysis phase, decision log, artifact registry, run record, or subagent handoff needs to be created, updated, resumed, or compacted. Replaces the old habit of growing and rereading one long plan file with a small docs/analysis/ YAML index and task-specific records. Use at phase boundaries…
Skill Claude CodeCodex
Use whenever an analysis makes or implies a CAUSAL claim — "the effect of", "X caused Y", "the policy raised", "the treatment increased", "because we did X, Y changed" — or whenever you're running difference-in-differences, event studies, instrumental variables, regression discontinuity, matching, synthetic control…
Skill Claude CodeCodex
Use when computing, transforming, cleaning, joining, merging, aggregating, reshaping, or modeling ANY result from data — before you trust a number, a table, a model metric, or a chart. Establishes data contracts and invariants up front, validates assumptions before building on them, asserts join cardinality before…
Skill Claude CodeCodex
Use when building, cleaning, or assembling the DATASET an analysis runs on in R, Julia, or Python — the moment someone says "clean the data", "the data is messy", "build/assemble the panel", "construct the dataset", "merge these files into one dataset", "prep the data", "dedupe these records", "reconcile the totals"…
Skill Claude CodeCodex
Use when the deliverable is a DESCRIPTION of what's in the data rather than an effect, a counterfactual, or a prediction — stylized facts, trends ("what's the trend in X", "how has Y changed over time", "plot the growth"), summary-statistics/Table-1 tables, distributions, descriptive maps/choropleths ("map where X is…
Skill Claude CodeCodex
Use once an analysis brief or pre-analysis plan is APPROVED and it's time to actually run the analysis — build the dataset, estimate the primary specification, run the robustness suite, placebo tests, and alternative designs, then assemble the results. Drives execution through the plan step by step, validating each…
Skill Claude CodeCodex
Use when making a FIGURE / CHART / PLOT for a paper, deck, or presentation — in ANY language (R/ggplot2, Python/matplotlib, Julia/Makie). Governs the visual style: 16.5pt text throughout (axes, legend, title), no y-label (the title carries the y-axis meaning; paper figures get no headline title), concise axis labels…
Skill Claude CodeCodex
Use BEFORE running a confirmatory analysis, an experiment readout, an A/B test, a policy evaluation, or any study whose credibility depends on not having fished for the result — especially causal/econometric work. Locks the hypotheses, estimand, primary specification, sample and exclusions, and the robustness suite…
Skill Claude CodeCodex
Use whenever the GOAL is a prediction that drives an action — predict, score, rank, flag, classify, forecast, or detect anomalies on units ("which pharmacy is likely diverting opioids", "which claim to audit", "who's likely to churn", "rank by risk"). Route by GOAL, not algorithm: a prediction deliverable is this…
Skill Claude CodeCodex
Use when finishing a piece of analysis and about to commit or push, when a directory has accreted files and it's unclear what is a deliverable versus scratch, when setting up or reorganizing a research repository, or when asked to clean up the directory, organize the repo, standardize naming, or make a project…
Skill Claude CodeCodex
Use BEFORE starting any data analysis, metric, model, causal study, or any deliverable built FROM data — "what's the trend", "is X driving Y", "how many users", "did the policy work", "build me a dashboard metric", "plot/map/visualize this", "make a figure/chart/map/dashboard/table of …", "build an interactive map of…
Skill Claude CodeCodex
Use ONLY when the user directly asks to verify, check, reconcile, or reproduce a result ("verify this", "check these numbers", "does this tie out?", "is this right?", "reproduce it from a clean kernel", "confirm the figures match the text") — never auto-fire it before reporting, shipping, or calling an analysis done.…
Skill Claude CodeCodex
Use whenever an analysis estimates the PRIMITIVES of an economic model — preferences/utility, costs, information/consideration, search, or conduct — or needs a COUNTERFACTUAL the data doesn't contain (a merger, a new product, a tax, a removed friction, welfare/surplus, equilibrium re-pricing). Fires for structural…
Skill Claude CodeCodex
Use when starting any data analysis, econometrics, or causal-inference task in R, Julia, or Python — establishes the Causal Powers discipline and routes to the right skill (question-framing, descriptive-evidence, pre-analysis-plan, analysis-state-management, data-contracts, data-preparation, analysis-craft…
Skill Claude CodeCodex
Use the moment a computed result looks wrong, surprising, suspicious, or "off" — a total that doesn't reconcile, revenue that tripled after a join, a mean that moved, a coefficient with the wrong sign, a count that's too high or too low, a metric that disagrees with another team's. Bisects the data pipeline to find…