Full Empirical Analysis — Classical Stata Workflow

This skill is the canonical 8-step pipeline an applied economist runs on every empirical paper, written in the traditional Stata ecosystem — native Stata + the 20+ community commands that have become de-facto standards (reghdfe, ivreg2, csdid, did_imputation, eventstudyinteract, sdid, rdrobust, rddensity, synth, synth_runner, psmatch2, teffects, ebalance, coefplot, esttab, outreg2, boottest, ritest, rwolf, bacondecomp, honestdid, binscatter).

Companion skills: if the user wants the same pipeline in Python, route to 00-StatsPAI_skill (agent-native DSL) or 00.1-Full-empirical-analysis-skill (explicit Python stack). This skill is the Stata counterpart — every step produces a .do file you can hand to a journal's replication office or a co-author who refuses to leave Stata.

Philosophy

1. Stata idioms, not Python-translated. reghdfe, not "statsmodels analogue of reghdfe". esttab, not "Stata's stargazer".
2. Reproducible .do files. Every code block below is runnable after use data.dta, clear. No Jupyter, no notebooks — just do-files and log files.
3. Full pipeline, not just regressions. Stata users historically over-invest in Step 5 (modeling) and under-invest in Steps 1–4 and 6–8. This skill treats them as first-class.
4. Rich outputs. Every step yields at least one table (.tex/.rtf) or figure (.pdf/.png) — never a coefficient printed to the Results window and forgotten.
5. Progressive disclosure. SKILL.md gives the canonical command at each step; references/ holds variant-specific depth (dozens of tests, estimator-specific diagnostics, graph recipes).

SkillOpt-style execution gate

Use this long playbook as a seed skill, not as a script to exhaustively apply. SkillOpt discipline: treat each local .do-file change as a candidate patch that must beat a selection check and survive a held-out check before it becomes reusable boilerplate. Before writing or revising a .do file, compress the user's request into a task-local best_skill card: