Review a grant proposal before submission through six specialized perspectives. Receive a consolidated report covering funder fit, research methods, feasibility, budget, consistency, and writing, with prioritized revisions and questions a review panel might ask.
Build and check research replication packages so a project's results can be reproduced. Routes checks to a dedicated agent that examines seeds, versions, file paths, workflow integrity, data documentation, execution environments, and matching outputs.
Review econometric code, proofs, data workflows, and outputs with multiple specialist agents. Assess identification—the assumptions that let data establish an effect—alongside estimation, numerical stability, and reproducibility, then consolidate findings into prioritized tasks.
Turns a copy-edit report into conflict markers that display original and suggested text together in the source file. Review each proposed change using VS Code or Positron's merge interface, optionally limiting edits to one Quarto section.
Review a pre-analysis plan before registration or submission using six specialized agents. Combine checks of clarity, consistency, causal design, statistics, and feasibility into a prioritized report with revision recommendations tailored to the selected registry or journal.
Search academic sources for papers on a topic, retrieve publication details, and find available PDFs. The skill guides source selection, combines results across services, and removes duplicates using DOIs, unique identifiers assigned to papers.
Route structural estimation tasks into a staged workflow, from data validation and identification, checking whether model parameters can be determined, through estimation, standard errors, robustness checks, and results. Each phase must meet its conditions before the next begins.
Develop Bayesian models for quantitative social science, from choosing priors to reporting posterior results. Guide MCMC, a sampling method for estimating distributions, check convergence, and assess sensitivity for hierarchical models and small datasets.
Find legally available free versions of paywalled papers using a DOI, the paper's identifier. Unpaywall provides access links and manuscript versions, helping retrieve PDFs and record where each accessible copy came from.
Find NBER working papers, research papers shared before formal publication, by keyword or research program. Retrieve recent papers, authors, dates, and citation details, and access US business cycle dates and links to economic datasets.
Analyze empirical economics PDFs through five questions covering the research problem, causal identification, target effect, robustness, and contribution. Receive a structured Chinese report and a practical checklist of research methods to adapt to other studies.
Choose and implement machine learning methods for estimating causal effects with many control variables or effects that differ across groups. Guidance covers DML, causal forests, and related methods, including diagnostics and limits on interpretation.
Turn papers, documents, or notes into slides with Marp, a Markdown presentation tool. The workflow covers outlining, theme selection, content and layout reviews, image checks, and final exports to HTML, PDF, and editable PPTX.
Create summary tables, treatment and control comparisons, and correlation matrices using Python, R, or Stata. Summarize averages, variation, sample sizes, and missing data to understand a dataset before regression or prepare tables for a research paper.
Revise a LaTeX academic manuscript using internal review comments, annotations, or tracked changes. Compare original passages with proposed revisions, approve each change individually, and receive a summary of applied and skipped items.
Choose and implement methods for estimating causal effects from observational data or policy changes. Guidance covers method assumptions, estimation, diagnostic checks, and robustness tests that examine whether findings hold under alternative analysis choices.
Turn a recurring workflow into an agent skill, or improve an existing one. Draft instructions, compare test outputs against a baseline, review quality and resource usage, and refine the description that determines when the skill is invoked.
Turn regression results and summary statistics from Stata, R, or Python into LaTeX tables for academic papers. Format model comparisons, decimal places, statistical significance markers, and notes, with guidance for wide tables and inclusion in a paper.
Create a literature review from a topic, journals, and publication period. Multiple agents search academic databases, collect available PDFs and citation records, organize findings by theme, and draft, review, revise, and compile a LaTeX document.
Coordinate multiple helper agents to screen large paper collections, extract detailed findings, and explore citations. Consolidate structured results into review records and summaries, while checking coverage, duplicate entries, and consistency in relevance scoring.
Audit references in a LaTeX manuscript by checking whether papers exist, bibliographic details are accurate, and cited findings support each claim. Produce a structured report with suggested corrections, then review and apply edits with a change log.
Screen search results by scoring paper abstracts, then examine promising papers for specific measurements, methods, or datasets. Record findings and review history so you can identify useful evidence and avoid checking the same papers again.
Find scientific papers in PubMed by turning a research question into targeted search terms and synonyms. Collect titles, authors, abstracts, and identifiers into a structured paper list ready for relevance evaluation.
Estimate policy effects by constructing a weighted comparison from untreated regions or other units. Guides donor selection, weight fitting, placebo tests, and reporting, with examples in R, Python, and Stata for studies with few treated units.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)