Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate…
An end-to-end workflow for economics and finance research, from a research idea to a paper PDF ready for submission. It covers literature review, idea and data checks, study design, data work, writing, charts, review, and LaTeX compilation.
A multi-stage research-idea workflow that scans existing knowledge, generates ideas, filters them, checks their novelty, and records the results in a research wiki.
An end-to-end research workflow that moves from finding ideas through experiment design, execution, evaluation, and paper writing, with saved progress and review checkpoints.
Install, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code. Activate when users ask to set up the Stata toolkit or troubleshoot the installation.
Show mcp-stata identity, connected tools, and status. Use when the user asks if mcp-stata is available, asks about access to the toolkit, or asks what Stata tools are connected.
Run Stata commands, .do files, view data, inspect results, and get help from the terminal. Wraps PyStata with a daemon mode for fast execution. Built-in Stata reference library with 57 topics. Designed for AI agents.
An AI assistant for Stata, a statistics program used to analyse data. It covers writing, running, and debugging Stata code and working with datasets, regression models, and other statistical analyses.
Use this skill whenever the user asks to run Stata code, debug a .do file, work with a Stata-backed Jupyter notebook, repair a Stata error, interpret r() / e() results, or write/plan a Stata analysis — and the stata-code MCP server is available (or, when it is not, to generate self-contained do-files). The skill…
A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.
Review economics papers, working papers, theses, and submissions with referee-grade rigor and exhaustive verified comments. Use when the user asks to evaluate, referee, audit, stress-test, pre-review, find all problems, or comprehensively review empirical, experimental, descriptive, forecasting, prediction/ML…