Skip to content

v1.9.0 Pass 4 — Stata expansion (stata-mcp + /stata-replication + audit-reproducibility)#121

Merged
pedrohcgs merged 1 commit into
mainfrom
feat/v1.9.0-pass4-stata-expansion
May 20, 2026
Merged

v1.9.0 Pass 4 — Stata expansion (stata-mcp + /stata-replication + audit-reproducibility)#121
pedrohcgs merged 1 commit into
mainfrom
feat/v1.9.0-pass4-stata-expansion

Conversation

@pedrohcgs

Copy link
Copy Markdown
Owner

Summary

User-driven expansion of the template to support Stata-first projects. Three sub-items:

  • 4.1 — Integrate SepineTam/stata-mcp. New ecosystem subsection + TROUBLESHOOTING entry.
  • 4.2 — New /stata-replication skill (mirrors /data-analysis for R) + new .claude/rules/stata-code-conventions.md (header scaffold, numbered pipeline, esttab tables, clustering discipline, AEA compliance, Stata-trap table).
  • 4.3/audit-reproducibility now handles .dta outputs via haven/pyreadstat; "Source-language coverage" section documents R / Stata / Python ecosystems.

On-disk changes

  • New: .claude/skills/stata-replication/SKILL.md
  • New: .claude/rules/stata-code-conventions.md
  • Modified: .claude/skills/audit-reproducibility/SKILL.md, TROUBLESHOOTING.md, guide/workflow-guide.qmd
  • Counts: 35 / 16 / 25 / 6 → 36 / 16 / 26 / 6. All 6 count-bearing surfaces updated.

Test plan

  • ./scripts/check-surface-sync.sh — 26/26
  • check-skill-integrity — pass
  • quarto render — clean
  • quality_score — 100/100

🤖 Generated with Claude Code

… + 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)
Copilot AI review requested due to automatic review settings May 20, 2026 15:43
@pedrohcgs
pedrohcgs merged commit 159ba5b into main May 20, 2026
@pedrohcgs
pedrohcgs deleted the feat/v1.9.0-pass4-stata-expansion branch May 20, 2026 15:43

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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-replication skill plus a new path-scoped Stata conventions rule for .do pipelines and outputs.
  • Extended /audit-reproducibility documentation to cover Stata .dta outputs (via haven/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"]
Comment thread guide/workflow-guide.qmd

**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).
Comment thread docs/index.html
@@ -209,7 +209,7 @@ <h2>What's in the template</h2>
<li><strong>14 specialized agents</strong> <span class="desc">&mdash; 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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants