Explore Agent Skills

Project directory organization and script naming conventions for research

Summarize academic papers, extract key findings, and identify research gaps

Document datasets, variables, sources, and merge keys for replication

Standardized Python & Stata coding practices for empirical research projects

Transfers prose edits from latex/index.tex (Overleaf) back into index.qmd. Use after pulling LaTeX edits from a collaborator.

Runs pre-submission checks (word count, anonymization, citations, placeholders, cross-refs) and generates a checklist. Use before journal submission.

Generates robustness check code and formats results as a combined table. Use for sensitivity analysis.

Runs the clean render pipeline (HTML, PDF, Word) via scripts/render.sh. Use when asked to render, build, or compile the manuscript.

Formats estimation output as a publication-quality regression table with stars, SEs, and fit statistics. Use when creating a results table.

Drafts a point-by-point response letter to referee comments with suggested edits. Use after a revise-and-resubmit.

Creates a Quarto revealjs slide deck in slides/ with the project style guide. Use when a presentation is needed.

Creates a Jupyter notebook with Jupytext pairing and registers it in _quarto.yml. Use when adding a new notebook.

Scaffolds a method-specific analysis notebook (DiD, IV, RDD, LASSO, Panel FE) with boilerplate. Use when starting a new econometric analysis.

Creates a structured annotation note in references/ with sections for research question, data, findings, and relevance. Use when documenting a paper.

Writes academic prose interpreting regression output. Use when describing estimation results in manuscript-ready language.

Fills all [FILL:] placeholders across the template to initialize a new research project. Use when setting up a freshly cloned project.

Writes a session handoff report to handoffs/ with project state, work done, decisions, and next steps. Use at session end or after significant work.

Checks whether registered notebooks have current, stale, or missing outputs. Use before rendering or to verify freshness.

Generates an HTML gallery of all project figures with captions and source notebooks. Use when reviewing figures.

Executes all registered notebooks, strips noisy cell metadata, and syncs Jupytext pairs. Use when asked to re-run notebooks or refresh outputs.

Captures tool versions, packages, and kernel info as a reproducibility record in notes/. Use when documenting the environment.

Drafts academic prose for a manuscript section from bullet points or an outline. Use when writing or expanding a section.

Scans notebooks for data file references and verifies each file exists on disk. Use when checking for broken data paths.

Auto-generates a Markdown codebook from a dataset (CSV, DTA, Excel, Parquet) with types and summary statistics. Use when documenting variables.