End-to-end Stata replication pipeline — scaffolds numbered `.do` files in `scripts/stata/`, executes them via the `stata-mcp` MCP server, captures logs and outputs to `output/`, and produces publication-ready tables (esttab) and figures (graph export). Mirrors `/data-analysis` for R-first projects. Use when user says "stata replication", "set up Stata pipeline", "scaffold the .do files", "run Stata analysis", "AEA replication package in Stata", or when a project's analysis language is Stata not R.
/stata-replication — Stata pipeline scaffold + executionBuild a complete Stata replication pipeline in scripts/stata/: numbered .do files following .claude/rules/stata-code-conventions.md, executed via the stata-mcp MCP server, with outputs landing in output/.
do scripts/stata/99_run_all.do./data-analysis./data-analysis is the right fit; consider extending the convention rule for Python or porting one of these skills.stata-mcp installedThis skill requires the stata-mcp MCP server. Install once per user:
claude mcp add stata-mcp --scope user -- uvx stata-mcpThe MCP server provides command-guarded Stata execution (refuses destructive operations like !/shell/erase), RAM monitoring, and Stata Language Server pairing. Maintained by SepineTam.
If stata-mcp is not installed, the skill halts at Phase 0 with installation instructions.
stata-mcp is registered in the user's MCP configuration. If not → halt with install instructions.scripts/stata/ directory exists or can be created..claude/rules/stata-code-conventions.md — every emitted .do file follows this convention.--from-r flag is set, locate the existing R pipeline at scripts/R/ and use it as a translation source. Apply the Stata → R pitfalls table from replication-protocol.md in reverse.Emit (or update) these files in scripts/stata/, each conforming to the header convention from stata-code-conventions.md:
scripts/stata/
├── 00_install.do # ssc install, set globals, paths, sessionInfo capture
├── 01_clean.do # raw → cleaned panel
├── 02_descriptive.do # summary tables, balance (iebaltab), attrition
├── 03_analyze.do # main regression specs (reghdfe / ivreg2 as needed)
├── 04_robustness.do # alt specs, sensitivity
├── 05_tables_figures.do # esttab .tex outputs + graph export PDFs
└── 99_run_all.do # do "01_clean.do" / do "02_..." / ...If the paper or data source suggests specific specs (e.g., DiD with reghdfe, IV with ivreg2, RD with rdrobust), tailor 03_analyze.do accordingly.
--no-execute)For each script in numbered order:
stata-mcp to execute the .do file.output/NN_log.smcl per the header convention) and the resulting .dta / .tex / .pdf outputs.failed and the error in Why, then halt — do NOT auto-fix unless the failure is trivial (typo flagged by Stata at parse time). For substantive failures (insufficient observations, singular matrices, missing covariates), surface to the user..do file ran — kept, dropped, or failed — to quality_reports/spec-ledger.md, with the same columns, commit stamp and append-only block as /data-analysis Phase 3 ("Specification ledger"). A failed run is a row too, with Status failed and the error in Why.For long-running scripts (> 2 minutes), use the Monitor tool to stream stdout — same pattern documented in /data-analysis and /audit-reproducibility.
output/.output/sessionInfo_stata.txt was captured (package versions)./audit-reproducibility if a manuscript exists — it reads Stata .dta outputs via haven/pyreadstat.If --from-r was set, run the R version of the same analysis (assumed to live at scripts/R/) and compare:
replication-protocol.md tolerance).Discrepancies are surfaced for the user to investigate — typical culprits: clustering df, default options (logit vs probit for PS), bootstrap seed handling.
/data-analysis — R analogue. Same pipeline shape, different language./audit-reproducibility — reads both .rds and .dta outputs. Cross-checks manuscript claims against the produced values./review-paper — if the paper exists and cites tables/figures produced by this pipeline, /review-paper auto-invokes /audit-reproducibility (per cross-artifact-review.md)..dta files. Never. All transformations happen via the .do files; .dta outputs are derived and reproducible.99_run_all.do. This is the AEA-mandated one-command entry point. Build it even for small projects., robust by default. Use , cluster(id) at the appropriate level — see stata-code-conventions.md §6.esttab and \input{} — see stata-code-conventions.md §4..do file starts with version 18 per the convention..claude/rules/stata-code-conventions.md — the discipline contract..claude/rules/replication-protocol.md — tolerance thresholds (applies across R / Stata / Python).Long Stata fits (multi-hour bootstrap with cluster bootstrap, large reghdfe with millions of observations, simulation studies) should be background-launched and tailed with the Monitor tool — same pattern as /data-analysis and /audit-reproducibility for R / Python. The .do file logs to SMCL (output/NN_log.smcl). Monitor does not attach to a background job or its stderr: only the stdout of the command you give it becomes events. So run Monitor on a command that tails the log and filters for progress lines and Stata errors, e.g. tail -f output/NN_log.smcl | grep --line-buffered -E '\{err\}|r\([0-9]+\);|<your progress marker>', so Claude can react to errors mid-stream (a multi-hour run needs persistent: true, then TaskStop once the job ends).
pedrohcgs/claude-code-my-workflow
fe70774
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.