pedrohcgs/claude-code-my-workflow / .claude/skills/stata-replication
stata-replication
VerifiedEnd-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 + execution
Build 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/.
When to use
- Your project's analysis language is Stata (not R). Common in econ field experiments, RCT studies, and any AEA submission where the original replication package is Stata.
- You're porting an R-first project to Stata for an AEA submission.
- You're adding a Stata robustness check to an R-first paper.
- You want a one-command reproduction:
do scripts/stata/99_run_all.do.
When NOT to use
- Your project is R-first. Use
/data-analysis. - Your project is Python-first. Neither this skill nor
/data-analysisis the right fit; consider extending the convention rule for Python or porting one of these skills. - You're doing quick exploratory work. The numbered-pipeline scaffold is for replication packages, not scratch notebooks.
Prerequisite: stata-mcp installed
This skill requires the stata-mcp MCP server. Install once per user:
claude mcp add stata-mcp --scope user -- uvx stata-mcp
The 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.
Workflow
Phase 0: Pre-flight
- Verify
stata-mcpis registered in the user's MCP configuration. If not → halt with install instructions. - Verify Stata is installed locally (the MCP server cannot run without it). Output stata version to confirm.
- Confirm
scripts/stata/directory exists or can be created. - Read
.claude/rules/stata-code-conventions.md— every emitted.dofile follows this convention. - If
--from-rflag is set, locate the existing R pipeline atscripts/R/and use it as a translation source. Apply the Stata → R pitfalls table fromreplication-protocol.mdin reverse.
Phase 1: Scaffold the pipeline
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.
Phase 2: Execute (unless --no-execute)
For each script in numbered order:
- Dispatch to
stata-mcpto execute the.dofile. - Capture the log (Stata writes to
output/NN_log.smclper the header convention) and the resulting.dta/.tex/.pdfoutputs. - If a script fails, first append its specification to the ledger (step 4) with Status
failedand 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. - Append every specification each estimation
.dofile ran — kept, dropped, or failed — toquality_reports/spec-ledger.md, with the same columns, commit stamp and append-only block as/data-analysisPhase 3 ("Specification ledger"). A failed run is a row too, with Statusfailedand 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.
Phase 3: Verify
- Confirm every expected output exists in
output/. - Check
output/sessionInfo_stata.txtwas captured (package versions). - Run
/audit-reproducibilityif a manuscript exists — it reads Stata.dtaoutputs viahaven/pyreadstat. - Report scripts run, outputs produced, any warnings from Stata.
Phase 4 (optional): R cross-check
If --from-r was set, run the R version of the same analysis (assumed to live at scripts/R/) and compare:
- Point estimates: should match to ~0.01 (per
replication-protocol.mdtolerance). - Standard errors: should match to ~0.05 (clustering df adjustments can differ slightly between Stata and R).
- Sample sizes: must match exactly.
Discrepancies are surfaced for the user to investigate — typical culprits: clustering df, default options (logit vs probit for PS), bootstrap seed handling.
Companion skills
/data-analysis— R analogue. Same pipeline shape, different language./audit-reproducibility— reads both.rdsand.dtaoutputs. Cross-checks manuscript claims against the produced values./review-paper— if the paper exists and cites tables/figures produced by this pipeline,/review-paperauto-invokes/audit-reproducibility(percross-artifact-review.md).
Anti-patterns
- Hand-editing
.dtafiles. Never. All transformations happen via the.dofiles;.dtaoutputs are derived and reproducible. - Skipping the
99_run_all.do. This is the AEA-mandated one-command entry point. Build it even for small projects. - Using
, robustby default. Use, cluster(id)at the appropriate level — seestata-code-conventions.md§6. - Hand-formatting tables in LaTeX. Use
esttaband\input{}— seestata-code-conventions.md§4. - Pinning Stata version in only one .do file. Every
.dofile starts withversion 18per the convention.
Cross-references
.claude/rules/stata-code-conventions.md— the discipline contract..claude/rules/replication-protocol.md— tolerance thresholds (applies across R / Stata / Python).- stata-mcp on GitHub — the MCP server this skill depends on.
- AEA Data Editor checklist — replication-package standards.
Long-running fits / batch reruns: use the Monitor tool (Apr 2026)
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).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |