skills/67-econfin-workflow-toolkit/paper-style/SKILL.md
Restructure an academic paper's title and section structure to match a target journal's house style. Asks the user to specify the target journal first, then adjusts main.tex accordingly (title wording and case, section skeleton, heading case, numbering scheme, merging/splitting sections). Trigger when user says "paper style" / "paper-style" / "期刊风格" / "按目标期刊调整" / "调整为XX风格" / "JFE风格" / "convert to journal style" / "restructure for [journal]", or wants a paper's title/sections reformatted for a specific journal submission.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research paper-styleInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill adapts an existing academic paper (main.tex) to the house style of a target journal, focusing on two things:
The skill asks the user for the target journal first, before analyzing the paper, because the journal determines every subsequent judgment. It then proposes a complete restructuring plan, gets approval, and applies the changes to main.tex in place.
Scope discipline: This skill changes structure, not content. Body prose is never rewritten, except for minimal transition sentences where sections are merged (the opening sentence of a merged section must announce its combined contents). Empirical results, tables, figures, citations, and arguments are untouched.
Input: A project folder containing main.tex (plus tables/figures subfolders, ref.bib, possibly journal .sty/.bst files).
Output: Revised main.tex with journal-conforming title and section structure.
Receive folder path from user (via $ARGUMENTS or ask). Verify main.tex exists with Glob.
Check for Dropbox conflict copies before any editing: Glob for files matching *冲突副本* or *conflicted copy* in the project folder. If found, warn the user and stop until they resolve which version is canonical (concurrent Overleaf editing can silently revert edits).
Ask for the target journal — unless it was already given in $ARGUMENTS. Use AskUserQuestion with the most common targets as options plus free-form "Other":
Ask this before reading the paper. The journal choice drives the entire analysis.
references/journal-profiles.md and locate the profile for the chosen journal. Each profile specifies: title conventions, numbering scheme, heading case, introduction treatment, canonical section skeleton, literature-review placement, hypothesis conventions, and typical section count.jfe.bst, jfe.sty, ecta.cls): if style files for the target journal are already present, numbering and case may be partially handled by the class — note this and avoid fighting the style file.main.tex in full.\title{}), running head if any, abstract length, keywords/JEL.\section, \subsection, \subsubsection with its heading text and \label.\ref{sec:...} and any hardcoded "Section 5"-style mentions (Grep for Section~?\s*\d and Sections~?\s*\d). Hardcoded numbers will break under renumbering and must be tracked.Present one complete plan covering both deliverables, then get approval. Do not edit anything before approval.
Offer the current title plus 2–3 candidates that conform to the journal's title conventions, with one-line rationales. Use AskUserQuestion so the user picks (options: keep current title — case-adjusted if needed — or one of the candidates; "Other" lets them type their own).
Present a mapping table:
现有结构 → 目标结构(JFE 风格)
| # | 现有章节 | 动作 | 目标章节 | 理由 |
|---|---------|------|---------|------|
| 1 | Introduction | 保留 | 1. Introduction | — |
| 2 | Rating Environment and Hypothesis Development | 改名 | 2. Institutional background | JFE 标题用 sentence case、短标题 |
| 6 | How Issuers Respond to a Downgrade | 改名 | 5. Mechanisms | 叙事式标题不符合 JFE 惯例 |
| 8 | Dynamics and Welfare Effects | 合并入 | 7. Additional analyses | JFE 偏好 6–8 节的紧凑结构 |
| 9 | Cross-Rater Evidence | 合并入 | 7. Additional analyses | 同上 |
...
章节数:10 → 8。受影响的交叉引用:3 处硬编码 "Section 9" 需更新。
Actions vocabulary: 保留 (keep), 改名 (rename), 合并 (merge), 拆分 (split), 移动 (reorder), 降级 (demote to subsection), 升级 (promote to section).
Explain why each change follows from the journal profile, not just what changes. Then use AskUserQuestion: approve the whole plan / adjust specific rows / cancel.
Fast path: if the user has said "直接改" / "无需确认" / "apply directly", skip the approval questions: pick the best title candidate yourself and apply the full plan.
Edit main.tex with the approved plan. Craft rules:
\title{} and any running-head command. Do not rename the folder or file.\section to \subsection (or fold its text in). Keep every \label intact — a dissolved section's label stays attached to the absorbed subsection so all \refs still resolve. Update the merged section's opening sentence to announce all the content it now covers. Remove \clearpage/\newpage commands that the merge has orphaned.Section~\ref{sec:...}; otherwise update the number..sty file. If the target journal's style file is present, rely on it. If not, do not hand-fake Roman numerals inside \section{} text; instead add the appropriate \renewcommand{\thesection}{...} lines in the preamble, and tell the user what was added.\section*{} plus manual TOC/label handling only if the user's template doesn't already handle it; mention the change explicitly.\refs resolve, transitions at merge seams read naturally, and no duplicate section numbers exist.\label{}, \ref{}, \cite{}/\citep{}, math, and table/figure environments exactly.---) in any newly written sentence (merge transitions, revised headings). Use a colon, comma, parentheses, or two sentences instead. Leave en-dashes (--) in ranges untouched.abstract.tex or chapter files via \input), apply it consistently across them.tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.