brycewang-stanford/Auto-Empirical-Research-Skills - Page 6

topic-modeling

Structural topic modeling: STM spec, topic count, coherence-exclusivity.

Langue du texte source : anglais

vlm-ocr-pipeline

VLM-based OCR pipeline: model selection, prompts, architecture, evaluation.

Langue du texte source : anglais

stata-causal-inference

Design, run, and critique causal inference workflows in Stata. Use when the user is working on identification, treatment effects, DiD, IV, event studies, RD, or assumption-sensitive empirical claims.

Langue du texte source : anglais

stata-data-audit

Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness. Use when a researcher asks for data QA, codebook review, sanity checks, or pre-analysis cleanup guidance.

Langue du texte source : anglais

stata-data-provenance

Track dataset lineage, transformation steps, merge logic, and reproducibility risks in Stata workflows. Use when the user needs to explain where data came from, how it changed, or why a pipeline can be trusted.

Langue du texte source : anglais

stata-environment-diagnose

Diagnose local Stata, MCP, package, startup, graph-export, and permissions issues. Use when setup is failing, Stata is not discovered, packages are missing, logs are truncated, or a managed machine behaves differently from a normal workstation.

Langue du texte source : anglais

stata-graph

List, export, and review Stata graphs from the current session.

Langue du texte source : anglais

stata-help

Look up Stata command documentation and display formatted help text.

Langue du texte source : anglais

stata-inspect

Describe and summarize the current dataset in memory. Optionally inspect a specific variable with codebook.

Langue du texte source : anglais

stata-lint

Run static analysis on a Stata .do or .ado file and report style and best-practice issues.

Langue du texte source : anglais

stata-log

Tail, read, or search a Stata log file from a previous command or background task.

Langue du texte source : anglais

stata-modernize

Improve, modernize, and optimize existing Stata code for performance, portability, and maintainability. Use when legacy patterns such as preserve/restore, cd,

Langue du texte source : anglais

stata-power-analysis

Plan and critique power, MDE, and sample-size calculations for Stata-based research workflows. Use when the user is designing a study, checking detectability, or defending precision claims.

Langue du texte source : anglais

stata-publication-qa

Review regression outputs, tables, and graphs for publication readiness. Use when the user asks whether a result is ready for a paper, appendix, seminar, referee response, or coauthor review.

Langue du texte source : anglais

stata-referee-response

Organize and execute Stata workflows for referee responses, robustness requests, and coauthor follow-ups. Use when the user needs to answer a critique with targeted reruns, tables, figures, and a defensible audit trail.

Langue du texte source : anglais

stata-replication

Run replication, robustness, and specification-sensitivity workflows for Stata projects. Use when a researcher wants to reproduce a result, rerun a pipeline, compare specifications, audit a do-file sequence, or check whether a claim is stable.

Langue du texte source : anglais

stata-results

Fetch and display stored r(), e(), and s() results from the last Stata command.

Langue du texte source : anglais

stata-run

Run arbitrary Stata code or a .do file and display the result.

Langue du texte source : anglais

stata-setup

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.

Langue du texte source : anglais

stata

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.

Langue du texte source : anglais

stata-table-builder

Build and review paper-ready regression, balance, and summary tables from Stata outputs. Use when the user needs a clean table for a draft, appendix, or coauthor share-out.

Langue du texte source : anglais

stata-toolkit

Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication, or Stata errors. Route the task through mcp-stata tools and the specialized research skills instead of treating it as…

Langue du texte source : anglais

choosing-causalpy-methods

Choose the appropriate CausalPy experiment class from a causal question, data structure, treatment assignment, and identification assumptions. Use before writing analysis code when the method is not yet settled.

Langue du texte source : anglais

running-causalpy-experiments

Fit, summarize, plot, and interpret a chosen CausalPy experiment. Use after the causal method has been selected, including when configuring PyMC/sklearn models and scale-aware custom priors.

Langue du texte source : anglais

running-placebo-analysis

Performs placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance. Use when checking model robustness, verifying lack of pre-intervention effects, or estimating study power.

Langue du texte source : anglais

slr-prisma

Guide users through writing a systematic literature review (SLR) following the PRISMA 2020 framework. Use this skill whenever the user mentions 'systematic review', 'systematic literature review', 'SLR', 'PRISMA', 'PRISMA 2020', 'PRISMA flow diagram', 'PRISMA…

Langue du texte source : anglais

thematic-analysis

Conduct rigorous thematic analysis (TA) of qualitative data following Braun and Clarke's (2006) six-phase framework. Use whenever the user mentions 'thematic analysis', 'TA', 'Braun and Clarke', 'qualitative coding', 'identifying themes', or asks for help…

Langue du texte source : anglais

citation-check

Audit in-text/reference parity, DOIs, claim support, and citation style.

Langue du texte source : anglais

conjoint-cleaning

Clean and reshape Qualtrics conjoint exports to analysis-ready long format.

Langue du texte source : anglais

conjoint-diagnostics

Diagnose conjoint design integrity, estimation choices, and validity.

Langue du texte source : anglais

diverge

Before implementing, generate 3-5 conceptually distinct approaches labeled by creativity dimension (Novel, Surprising, Diverse, Conventional), then hold for selection. Brainstorm-then-select to resist defaulting to the most obvious solution.

Langue du texte source : anglais

fair-check

Audit manuscript and replication package against FAIR open-science principles.

Langue du texte source : anglais

figure-table-audit

Audit figures, tables, captions, cross-references, and statistical notes.

Langue du texte source : anglais

journal-review

Draft a senior peer-review report on a social-science manuscript.

Langue du texte source : anglais

list-experiment

Design and diagnose list experiments (item count technique).

Langue du texte source : anglais

methods-reporting

Check methods reporting against CONSORT, JARS, DA-RT standards.

Langue du texte source : anglais

replication-package

Scaffold or audit a social-science replication package at a target directory. Generates folder structure, README, master.R, figure/table crosswalk, codebook template, LICENSE placeholder, and pre-release checklist. Adapted from Yusaku Horiuchi's…

Langue du texte source : anglais

r-bayes

Patterns for Bayesian inference in R using brms, including multilevel models, DAG validation, and marginal effects. Use when performing Bayesian analysis.

Langue du texte source : anglais

r-oop

R object-oriented programming guide for S7, S3, S4, and vctrs. Use when designing R classes or choosing an OOP system.

Langue du texte source : anglais

r-package-development

R package development guide covering dependencies, API design, testing, and documentation. Use when developing R packages.

Langue du texte source : anglais