What problem does it solve? Setting up a Stata replication pipeline for an academic paper involves repetitive scaffolding of numbered .do files, consistent logging conventions, and manual execution tracking. This Skill automates the entire pipeline from scaffold to verified outputs, following AEA replication package standards. ## Core Features & Use Cases - Pipeline Scaffolding: Generates numbered .do files (00_install through 99_run_all) in scripts/stata/ following a strict code-conventions rule, including esttab tables and graph export. - MCP-Based Execution: Runs each .do file via the stata-mcp MCP server, captures SMCL logs and outputs to scripts/stata/_outputs/, and halts on substantive failures for user review. - R-to-Stata Porting: With the --from-r flag, translates an existing R pipeline into Stata and cross-checks point estimates, standard errors, and sample sizes against tolerance thresholds. - Use Case: An economist preparing an AEA submission whose original analysis is in Stata can scaffold the full replication package, execute it end-to-end, and produce publication-ready .tex tables with one command. ## Quick Start Ask the assistant to set up a Stata replication pipeline for your paper and run all the .do files, optionally passing a paper or data pointer and the --from-r flag if porting from R.
