Guides empirical economics manuscripts from topic selection through AER submission, covering causal identification, literature positioning, body drafting, robustness checks, referee simulation, and R&R rebuttals with AEA-compliant data deposits.
Use when auditing a finished or near-finished AER, AER:Insights, or AEJ manuscript for internal consistency — headline numbers matching across abstract, introduction, results, and tables; sample sizes that add up; correct log-point and percentage-point conversions; resolvable cross-references; and a two-way match between in-text citations and the bibliography. Apply after the body and exhibits exist, before aer-referee-sim and aer-submission.
Use when selecting, implementing, or stress-testing the causal identification strategy for an empirical economics manuscript — difference-in-differences (including staggered designs), instrumental variables (including weak-IV-robust inference), regression discontinuity, synthetic control, or shift-share / Bartik. Apply before writing the introduction or results.
Use when drafting or rewriting the introduction of an economics manuscript targeted at AER, AER:Insights, or an AEJ, or when compressing an abstract to the mandatory 100-word limit. Implements the Keith Head / Bellemare five-paragraph formula and AER-specific formatting conventions.
Use when positioning a manuscript against the existing economics literature, building the antecedents map for the introduction, deciding what to cite, or verifying that every reference in the bibliography is real, correctly attributed, and cited to the published version. Apply at topic selection for the novelty scan and again before drafting the introduction.
Use when drafting or revising the body sections of an AER, AER:Insights, or AEJ manuscript — institutional background, data, empirical strategy, results, mechanisms, and conclusion. Covers equation conventions, results-paragraph narration, magnitude interpretation, and back-of-envelope policy calculations. Apply after the empirics are stable and before or alongside aer-introduction.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
面向 《美国经济评论》(AER)、AER: Insights 及 AEJ 系列期刊的 agent skill 栈。
简体中文 | English
面向 American Economic Review(AER)、AER: Insights 以及 AEJ 系列期刊的 agent skill 包:覆盖选题、文献定位、正文写作、识别策略、表图规范、投稿、模拟审稿、审稿回复的全流程。
本仓库是有立场的。它不是通用经济学写作工具箱,而是一套面向 top-5 经济学的 skill 栈:识别优先的实证、AEA 政策合规的复现包、Keith Head 风格的引言、AER 风格的 booktabs 表格、以及对编辑友好的 rebuttal 文体。
v1.1 把 AER-Skills 从十个核心 skill 扩展到十四个,并把"写完稿"之后最容易出错的环节前移成质量门:
aer-literature:先做最近邻论文地图和引用核验,避免凭记忆写文献与幻觉引用。aer-paper-body:覆盖 background、data、empirical strategy、results、mechanisms、conclusion,强调先写正文再写引言。aer-consistency:审计正文数字、表格、样本漏斗、单位换算、交叉引用和 bibliography;附可运行的 LaTeX 检查脚本。aer-referee-sim:在投稿前模拟 desk screen 和三位 adversarial referees,按 rubric 输出 revise list。docs/style-guide.md、docs/referee-report-rubric.md、examples/results-section-example.md、examples/referee-report-example.md。Top-5 经济学期刊的硬约束在生命科学类期刊中并不存在:
| 约束维度 | AER | AER: Insights | 含义 |
|---|---|---|---|
| 摘要字数 | 100 词 | 100 词 | 4-5 句话。卖结果,不卖动机。 |
| 正文长度 | ~40 排印页 | ≤ 7,000 词减每个 exhibit 200 词 | 行文要紧;5 个 exhibits 时上限为 6,000 词。 |
| Desk rejection | 高 | ~45% | 前三页决定生死。 |
| 复现要求 | 强制 | 强制 | AEA 数据与代码可用性政策有专人审核执行。 |
| 识别策略 | 因果、设计驱动 | 因果、设计驱动 | TWFE、弱 IV、朴素 RDD 会被直接 desk-reject。 |
| Cover letter | 可选 | 可选 | 仅用于 COI 披露或数据访问限制说明。 |
| Disclosure statements | 必需 | 必需 | 每位合作者单独提交一份 PDF;即使没有冲突也要明说。 |
通用的 "scientific writing" skill(例如 Nature-Paper-Skills、nature-skills)通常覆盖不到这些约束。
# 添加 marketplace(一次性)
/plugin marketplace add https://github.com/brycewang-stanford/AER-Skills
# 安装插件
/plugin install aer-skills
# 重新加载
/reload-plugins
之后十四个 skill 会全部自动可用。
git clone https://github.com/brycewang-stanford/AER-Skills.git
cd AER-Skills
# Claude Code(用户级)
python3 scripts/install_skills.py claude
# 或 Codex
python3 scripts/install_skills.py codex
安装脚本会复制完整 skill 目录。更新已有安装时加 --replace,正式复制前可用
--dry-run 预览计划中的复制操作。如果想用 skill 引用到的 templates/ 和
examples/ 资源,请保留这个 cloned repository。
重启 agent 后:
用 aer-workflow 告诉我这篇稿子下一步该用哪个 skill。
更完整的安装说明见 docs/installation-claude.md 和 docs/installation-codex.md。
aer-topic-selection
-> aer-literature
-> aer-identification
-> aer-robustness
-> aer-paper-body
-> aer-introduction
-> aer-tables-figures
-> aer-consistency
-> aer-referee-sim (循环直到 ≥ major R&R)
-> aer-replication
-> aer-submission
-> aer-rebuttal
核心默认假设:
aer-consistency)和对抗性模拟审稿(aer-referee-sim)是投稿前的硬门槛完整路线图见 docs/workflow-map.md。
npx claudepluginhub brycewang-stanford/aer-skills --plugin aer-skillsAgent-native Stata bridge for Claude Code. Bundles an MCP server (15 tools, token-economy result schema, typed errors, multi-session) and an agent skill that teaches Claude how to call it idiomatically.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.