v1.9.0 Pass 4 — Stata expansion (stata-mcp + /stata-replication + audit-reproducibility)#121
Merged
Merged
Conversation
… + audit-reproducibility
User-driven expansion to support Stata-first projects. Correction
to plan: AEA does not mandate Stata — the expansion targets users
whose pipelines are Stata-first for audience reach or original-
replication-package fidelity.
Three sub-items:
4.1 — stata-mcp integration. New ecosystem subsection in
guide/workflow-guide.qmd documents SepineTam/stata-mcp (171 stars,
v1.17.3, May 2026): install via
`claude mcp add stata-mcp --scope user -- uvx stata-mcp`. New
TROUBLESHOOTING entry covers the "stata-mcp not registered" pre-
flight failure with install steps + verification.
4.2 — New skill /stata-replication. Mirrors /data-analysis for R-
first projects. Scaffolds numbered .do pipeline (00_install.do
through 99_run_all.do), executes via stata-mcp, outputs land in
scripts/stata/_outputs/. --from-r flag ports R pipelines with
optional cross-check. Phase 0 halts if MCP server not registered.
4.2 — New rule .claude/rules/stata-code-conventions.md.
Path-scoped on **/*.do and scripts/stata/**. Codifies header
(version 18, clear all, set seed/sortseed, log capture); numbered
pipeline; outputs convention with sessionInfo.txt; esttab for
publication-ready tables; significance stars convention; clustering
discipline (reghdfe, cluster bootstrap < 50 groups); balance via
iebaltab; AEA Data Editor compliance checklist; Stata-trap table.
4.3 — /audit-reproducibility source-language coverage extended.
New "Source-language coverage" section documents R / Stata /
Python ecosystems with read-output methods (haven::read_dta,
pyreadstat). Stata-specific notes: esttab .tex as strongest
provenance signal under \input{} pattern; clustering-df diagnosis
for reghdfe vs reg, cluster().
On-disk inventory: 36 skills / 16 agents / 26 rules / 6 hooks
(was 35/16/25/6 after Pass 3B). +1 skill (/stata-replication),
+1 rule (stata-code-conventions).
Verification:
- check-surface-sync.sh: 26/26 pass, counts 36/16/26/6
- check-skill-integrity: pass on new SKILL.md
- quarto render: clean
- quality_score: 100/100
🤖 Generated with [Claude Code](https://claude.com/claude-code)
There was a problem hiding this comment.
Pull request overview
This PR expands the academic workflow template to better support Stata-first replication projects by adding a dedicated Stata replication skill, Stata-specific code conventions, and extending reproducibility auditing/docs to account for Stata outputs and the stata-mcp MCP server.
Changes:
- Added
/stata-replicationskill plus a new path-scoped Stata conventions rule for.dopipelines and outputs. - Extended
/audit-reproducibilitydocumentation to cover Stata.dtaoutputs (viahaven/pyreadstat) and documented multi-language coverage (R/Stata/Python). - Updated guide/troubleshooting/landing pages and count-bearing surfaces to reflect the new skill/rule and document
stata-mcp.
Reviewed changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
TROUBLESHOOTING.md |
Adds guidance for resolving stata-mcp registration issues for /stata-replication. |
templates/skill-template.md |
Updates the referenced skill count (35 → 36). |
README.md |
Updates headline inventory counts (skills/rules). |
guide/workflow-guide.qmd |
Documents stata-mcp, adds /stata-replication and Stata rule entries. |
guide/workflow-guide.html |
Rendered guide update reflecting the new stata-mcp section and updated counts. |
docs/workflow-guide.html |
Published HTML guide update reflecting the same rendered changes. |
docs/index.html |
Updates public landing page counts (skills/rules) and metadata description. |
CLAUDE.md |
Adds /stata-replication to the skills quick reference table. |
CHANGELOG.md |
Documents the Stata expansion pass and related additions/changes. |
.claude/skills/stata-replication/SKILL.md |
New skill: scaffolds and runs a numbered Stata replication pipeline via stata-mcp. |
.claude/skills/audit-reproducibility/SKILL.md |
Documents Stata output handling and adds “Source-language coverage” section. |
.claude/rules/stata-code-conventions.md |
New rule: Stata .do pipeline conventions, outputs, tables/figures, and AEA compliance guidance. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| version: 1.0.0 | ||
| argument-hint: "[paper-or-data-pointer] [--from-r] [--no-execute]" | ||
| disable-model-invocation: true | ||
| allowed-tools: ["Read", "Write", "Edit", "Glob", "Grep", "Bash", "Task"] |
|
|
||
| **Why it matters for this template:** v1.9.0 added [`/stata-replication`](#sec-appendix) for Stata-first projects, which depends on this MCP server. R-first projects (the original template focus) continue to use [`/data-analysis`](#sec-appendix); the two skills are parallel — same pipeline shape, different source language. AEA submissions where the original replication package is in Stata are the canonical use case. | ||
|
|
||
| For end-to-end Stata workflows, see [`.claude/rules/stata-code-conventions.md`](.claude/rules/stata-code-conventions.md) (header scaffold, numbered pipeline, esttab tables, clustering discipline, AEA Data Editor compliance). |
| @@ -209,7 +209,7 @@ <h2>What's in the template</h2> | |||
| <li><strong>14 specialized agents</strong> <span class="desc">— proofreader, slide auditor, pedagogy reviewer, R reviewer, TikZ critic, domain reviewer, adversarial QA pair, translator, verifier, claim-verifier (Chain-of-Verification), plus simulated-peer-review trio (editor, domain referee, methods referee)</span></li> | |||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
User-driven expansion of the template to support Stata-first projects. Three sub-items:
SepineTam/stata-mcp. New ecosystem subsection + TROUBLESHOOTING entry./stata-replicationskill (mirrors/data-analysisfor R) + new.claude/rules/stata-code-conventions.md(header scaffold, numbered pipeline, esttab tables, clustering discipline, AEA compliance, Stata-trap table)./audit-reproducibilitynow handles.dtaoutputs viahaven/pyreadstat; "Source-language coverage" section documents R / Stata / Python ecosystems.On-disk changes
.claude/skills/stata-replication/SKILL.md.claude/rules/stata-code-conventions.md.claude/skills/audit-reproducibility/SKILL.md,TROUBLESHOOTING.md,guide/workflow-guide.qmdTest plan
./scripts/check-surface-sync.sh— 26/26check-skill-integrity— passquarto render— cleanquality_score— 100/100🤖 Generated with Claude Code