adjudication-sheets
Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to…
Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any
$ npx -y skills add kennethkhoocy/applied-micro-skills --skill latex-empirical-tables --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/latex-empirical-tablesContext preview
The summary Claude sees to decide when to auto-load this skill.
Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any
name: latex-empirical-tables description: >- Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any mention of estout, esttab, estauto, estwide, or table fragments; (b) formatting or repairing estout-style regression tables that overflow the right margin, have cramped or boxed notes, misaligned columns, or poor significance stars, or when asked to match a reference paper, make the note fill the table width, or choose among \estwide, \estauto, and landscape layouts; (c) diagnosing "Misplaced \omit" errors from \input-ed table fragments inside tabular environments. Covers \@@input, \estwide, \estauto, \estautoLT, \specialcell, \sym, minipage notes below tabulars, and the convert-and-verify workflow. Do NOT trigger for general LaTeX documents like beamer presentations, problem sets, letters, or CVs. metadata: author: Claude Code version: 1.1.0 date: 2026-07-20 consolidates: Merges estout-table-formatting, latex-results-preamble, and latex-input-multicolumn-omit-fix into one skill.
Empirical economics and finance papers export regression and estimation output as estout/esttab "body fragments" — rows of `\multicolumn` headers, coefficients with `\sym` stars, and parenthesised p-values or SEs, with no `\toprule`/`\bottomrule` — pulled into the manuscript through a wrapper macro (`\estauto`/`\estwide`/`\estautoLT`). Done well this reads like a top-journal table. Done naively it looks broken: wide tables spill past the right margin, the note legend is jammed inside the tabular as a boxed cell, columns sit at uneven widths, and `\input`-ed fragments throw "Misplaced \omit". This skill sets a results `.tex` up from scratch, converts ugly estout tables to the gold-standard pattern, and diagnoses the `\omit` error. The reasoning behind each choice is given so you can adapt rather than copy blindly.
| You want to... | Go to | |----------------|-------| | Set up `results.tex`/`main.tex` and its preamble from scratch | Section A | | Fix or reformat existing estout tables (overflow, cramped notes, stars, alignment) | Section B | | Diagnose a "Misplaced `\omit`" error from an `\input`-ed fragment | Section C | | Merge several self-compiling block `results.tex` files into one master document | Section D | | Fix skipped table numbers (Table 1, Table 3, ...) when `\captionof` + `longtable` are combined | Section D |
---
When producing regression or estimation tables, follow this workflow to create a compilable LaTeX document with a standard empirical-economics preamble and estout macros.
All output lives under `outline/` relative to the project root:
outline/
├── preamble/
│ └── preamble.tex ← LaTeX preamble (no \begin{document})
├── Tables/
│ ├── table_01.tex ← table fragments (auto-increment)
│ ├── table_02.tex
│ └── ...
├── Figures/
│ └── ... ← figures (.pdf, .png, etc.)
└── results.tex ← master document (created on first table)Create `outline/preamble/` and `outline/Tables/` if they don't already exist. Also create `outline/Figures/` if figures will be produced.
Copy `references/preamble.tex` from this skill's directory to `outline/preamble/preamble.tex`. This file contains everything up to but NOT including `\begin{document}` — the document class, all packages, and the estout macro definitions (`\estauto`, `\estwide`, `\estautoLT`, `\sym`, `\specialcell`). The macros are defined there in full; Section B lists a minimal subset if you only need to graft them onto an existing preamble.
Do NOT create `outline/results.tex` yet — it gets created automatically when the first table is generated.
Each time a regression or summary table is generated:
1. Save the table fragment to `outline/Tables/table_XX.tex` with auto-incrementing numbering (01, 02, 03, ...).
2. If `outline/results.tex` does **not** exist, create it:
\input{preamble/preamble}
\begin{document}
\section{Tables}
\subsection{Descriptive Title}
\begin{table}[H]
\caption{Descriptive Title}
\centering
\estauto{Tables/table_01.tex}{N}{D{.}{.}{-1}}
\end{table}
\FloatBarrier
\end{document}3. If `outline/results.tex` **already exists**, insert the following block BEFORE `\end{document}`:
\subsection{Descriptive Title}
\begin{table}[H]
\caption{Descriptive Title}
\centering
\estauto{Tables/table_XX.tex}{N}{D{.}{.}{-1}}
\end{table}
\FloatBarrierWhere `N` = number of data columns in the fragment (excluding the label column).
Three macros are defined in the preamble for including table fragments generated by any tool (pyfixest, esttab, R, etc.). All use the TeX primitive `\@@input` to avoid `\multicolumn`/`\omit` errors (Section C explains why this matters).
| Macro | Use case | Environment | |-------|----------|-------------| | `\estauto{file}{ncols}{colspec}` | Standard-width tables | `tabular` | | `\estwide{file}{ncols}{colspec}` | Full-page-width tables | `tabular*` | | `\estautoLT{file}{ncols}{colspec}` | Multi-page tables | `longtable` |
The default column spec is `D{.}{.}{-1}` (decimal-aligned via `dcolumn`). Use `c` only when columns contain non-numeric content.
Fragments must follow these conventions — the wrapper macros add `\toprule` and `\bottomrule`, so fragments should NOT include them.
Claude Code and Codex skills for empirical applied-microeconomics research: reproducibility auditing, LLM-assisted classification methods, event studies, data infrastructure (WRDS, Stata, pyfixest), and publication-grade tables, figures, and documents.
Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to…
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter…
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence…
Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1)…
Place pre-screened literature citations into a LaTeX or Word manuscript, or restyle the citations already in one. Three modes: (1) inline placement — inline…
Download the actual PDF binary from bot-gated sites (taxpolicycenter.org, urban.org, SSRN-hosted mirrors, think-tank/publisher sites) via the Wayback Machine…