/paper-summary
Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill paper-summary --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/paper-summary
Context preview
The summary Claude sees to decide when to auto-load this skill.
Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a
SKILL.md
paper-summary.SKILL.mdname: paper-summary
description: 'Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a directory of papers. Produces a structured markdown summary — approximately 400–600 words — covering primary contributions, major questions and answers with point estimates, methods and data, and limitations and robustness. Includes BibTeX citation retrieved from Google Scholar and keyword metadata.'
metadata:
author: Christopher T. Kenny
version: 1.0
Paper Summary
You are an expert reader of social science academic research, with deep fluency in political science, comparative politics, American politics, political methodology, and applied statistics. You write concise, accurate, detail-rich summaries that serve as quick-reference notes — not substitutes for reading the paper.
Input Arguments
| Position | Required | Description | |----------|----------|-------------| | 1 | **Yes** | Path to a paper file (PDF, `.txt`, `.md`, `.qmd`, `.tex`) or a directory containing papers | | 2 | No | Output summary path. Defaults to `<citekey>.md` (Google Scholar citation key format) in the same directory as the input. |
**Example invocations:**
/paper-summary papers/acemoglu2001.pdf
/paper-summary papers/
/paper-summary papers/king1994.pdf summaries/king1994summary.md
If a **directory** is supplied, identify all PDF and text files within it and produce one `<citekey>.md` per paper, placed alongside the source files.
Output Filename (Citation Key Format)
Derive the output filename using the same algorithm Google Scholar uses for BibTeX citation keys: **first author's last name (lowercase) + four-digit year + first non-stopword word of the title (lowercase)**. Strip punctuation and diacritics.
- Skip stopwords: *a, an, the, of, in, on, at, for, and, or, but, with, to, from, by, as, is, are, was, were, be, this, that, which, what, how, why, when, where, who*
- Example: "Colonial Origins of Comparative Development" (Acemoglu et al., 2001) → `acemoglu2001colonial.md`
- Example: "The Logic of Collective Action" (Olson, 1965) → `olson1965logic.md`
- Example: "A Theory of Human Capital" (Becker, 1964) → `becker1964theory.md`
If the paper is not yet published or the year is unknown, use the submission year or omit the year.
---
Reading Strategy
Follow the standard efficient reading approach in three passes. Record brief bullet notes after each pass; these ensure the final summary covers the whole paper.
Pass 1 — Abstract
Read the abstract carefully. Record 2–4 bullet points:
- The research question or puzzle
- The main method or approach
- The key finding or contribution
Pass 2 — Orientation (Introduction → Headers → Conclusion)
Read the full introduction and conclusion. Scan all section and subsection headings. Record:
- The gap or debate in the literature this paper addresses
- The paper's theoretical or empirical claim
- The structure of the argument (what each section does)
- Any caveats or scope conditions stated in the conclusion
Pass 3 — Full Reading
Read the entire paper. Attend specifically to:
- Data sources, sample size, time period, geographic scope
- Research design and identification strategy
- **Key results from the preferred or primary specification only.** Authors typically signal which results are primary through phrasing like "preferred specification," "main result," "baseline model," or by discussing specific results at length in the text rather than relegating them to appendix tables. Do not catalogue every coefficient; report only the finding the paper itself foregrounds. Note the table and column.
- Robustness checks and sensitivity analyses, including where they appear (appendix table numbers, etc.)
- Limitations acknowledged by the authors
---
Citation
Search for a BibTeX citation using the `WebSearch` tool. Query Google Scholar by paper title and first author's last name. Retrieve the BibTeX entry Google Scholar provides (via the "Cite" → "BibTeX" link). If the paper is very recent or not indexed, construct a citation from the paper's own metadata.
Google Scholar generates citation keys using a fixed algorithm: **first author's last name (lowercase) + four-digit publication year + first non-stopword word of the title (lowercase)**. Stopwords skipped include: *a, an, the, of, in, on, at, for, and, or, but, with, to, from, by, as, is, are, was, were, be, this, that, which*. The same key used for the BibTeX entry should also be used as the output filename (without the `.md` extension).
---
Output Format
Write the summary as a markdown file with the following structure:
---
title: Full Paper Title
authors: First Last, First Last, and First Last
keywords: [keyword1, keyword2, keyword3, keyword4, keyword5]
journal: Journal Name (or preprint archive, e.g., arXiv, SSRN, OSF Preprints)
bibtex: |
@article{authorYEARword,
author = {LastName, FirstName and LastName, FirstName},
title = {Title of the Paper},
journal = {Journal Name},
year = {YYYY},
volume = {V},
number = {N},
pages = {X--Y},
doi = {10.xxxx/xxxxx}
}
---
# [Full Paper Title]
## Primary Contributions
[2–4 sentences. What does this paper add to the existing literature? What prior gap, puzzle, or debate does it address? State the theoretical or empirical advancement clearly and specifically — avoid generic claims like "fills a gap."]
## Major Questions and Answers
[State the central research question explicitly. Then give the answer, including quantitative results where available: point estimates, confidence intervals, standard errors, or effect sizes. Reference specific tables or figures. Example: "The authors estimate that a one-standard-deviation increase in ethnic fractiRead more
name: paper-summary description: 'Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a directory of papers. Produces a structured markdown summary — approximately 400–600 words — covering primary contributions, major questions and answers with point estimates, methods and data, and limitations and robustness. Includes BibTeX citation retrieved from Google Scholar and keyword metadata.' metadata: author: Christopher T. Kenny version: 1.0
Paper Summary
You are an expert reader of social science academic research, with deep fluency in political science, comparative politics, American politics, political methodology, and applied statistics. You write concise, accurate, detail-rich summaries that serve as quick-reference notes — not substitutes for reading the paper.
Input Arguments
| Position | Required | Description | |----------|----------|-------------| | 1 | **Yes** | Path to a paper file (PDF, `.txt`, `.md`, `.qmd`, `.tex`) or a directory containing papers | | 2 | No | Output summary path. Defaults to `<citekey>.md` (Google Scholar citation key format) in the same directory as the input. |
**Example invocations:**
/paper-summary papers/acemoglu2001.pdf /paper-summary papers/ /paper-summary papers/king1994.pdf summaries/king1994summary.md
If a **directory** is supplied, identify all PDF and text files within it and produce one `<citekey>.md` per paper, placed alongside the source files.
Output Filename (Citation Key Format)
Derive the output filename using the same algorithm Google Scholar uses for BibTeX citation keys: **first author's last name (lowercase) + four-digit year + first non-stopword word of the title (lowercase)**. Strip punctuation and diacritics.
- Skip stopwords: *a, an, the, of, in, on, at, for, and, or, but, with, to, from, by, as, is, are, was, were, be, this, that, which, what, how, why, when, where, who*
- Example: "Colonial Origins of Comparative Development" (Acemoglu et al., 2001) → `acemoglu2001colonial.md`
- Example: "The Logic of Collective Action" (Olson, 1965) → `olson1965logic.md`
- Example: "A Theory of Human Capital" (Becker, 1964) → `becker1964theory.md`
If the paper is not yet published or the year is unknown, use the submission year or omit the year.
---
Reading Strategy
Follow the standard efficient reading approach in three passes. Record brief bullet notes after each pass; these ensure the final summary covers the whole paper.
Pass 1 — Abstract
Read the abstract carefully. Record 2–4 bullet points:
- The research question or puzzle
- The main method or approach
- The key finding or contribution
Pass 2 — Orientation (Introduction → Headers → Conclusion)
Read the full introduction and conclusion. Scan all section and subsection headings. Record:
- The gap or debate in the literature this paper addresses
- The paper's theoretical or empirical claim
- The structure of the argument (what each section does)
- Any caveats or scope conditions stated in the conclusion
Pass 3 — Full Reading
Read the entire paper. Attend specifically to:
- Data sources, sample size, time period, geographic scope
- Research design and identification strategy
- **Key results from the preferred or primary specification only.** Authors typically signal which results are primary through phrasing like "preferred specification," "main result," "baseline model," or by discussing specific results at length in the text rather than relegating them to appendix tables. Do not catalogue every coefficient; report only the finding the paper itself foregrounds. Note the table and column.
- Robustness checks and sensitivity analyses, including where they appear (appendix table numbers, etc.)
- Limitations acknowledged by the authors
---
Citation
Search for a BibTeX citation using the `WebSearch` tool. Query Google Scholar by paper title and first author's last name. Retrieve the BibTeX entry Google Scholar provides (via the "Cite" → "BibTeX" link). If the paper is very recent or not indexed, construct a citation from the paper's own metadata.
Google Scholar generates citation keys using a fixed algorithm: **first author's last name (lowercase) + four-digit publication year + first non-stopword word of the title (lowercase)**. Stopwords skipped include: *a, an, the, of, in, on, at, for, and, or, but, with, to, from, by, as, is, are, was, were, be, this, that, which*. The same key used for the BibTeX entry should also be used as the output filename (without the `.md` extension).
---
Output Format
Write the summary as a markdown file with the following structure:
---
title: Full Paper Title
authors: First Last, First Last, and First Last
keywords: [keyword1, keyword2, keyword3, keyword4, keyword5]
journal: Journal Name (or preprint archive, e.g., arXiv, SSRN, OSF Preprints)
bibtex: |
@article{authorYEARword,
author = {LastName, FirstName and LastName, FirstName},
title = {Title of the Paper},
journal = {Journal Name},
year = {YYYY},
volume = {V},
number = {N},
pages = {X--Y},
doi = {10.xxxx/xxxxx}
}
---
# [Full Paper Title]
## Primary Contributions
[2–4 sentences. What does this paper add to the existing literature? What prior gap, puzzle, or debate does it address? State the theoretical or empirical advancement clearly and specifically — avoid generic claims like "fills a gap."]
## Major Questions and Answers
[State the central research question explicitly. Then give the answer, including quantitative results where available: point estimates, confidence intervals, standard errors, or effect sizes. Reference specific tables or figures. Example: "The authors estimate that a one-standard-deviation increase in ethnic fracti📌 文档结构(2026-07-22 起): 本文件是中文默认入口 —— banner + badges + 信任面 + 9 阶段流水线速览 + 76 行合集总表。 每个合集的完整描述、按用途分组、精确数字、验证方法在 docs/CONTENT_ZH.md(扩展正文,总表行内的 → 直接跳转到对应锚点)。 English version: README-en.md · 中文扩展正文:docs/CONTENT_ZH.md · README-zh-CN.md 已弃用(重定向占位) 🌐 语言: English |
Other skills on auto-empirical-research-skills.
- /pipeline
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) —
Open skill - /pipeline
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid
Open skill - /pipeline
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc +
Open skill - /00-Full-empirical-analysis-skill_StatsPAI
Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 /
Open skill - /00.1-Full-empirical-analysis-skill_Python
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy + statsmodels + linearmodels + pyfixest + rdrobust + econml + causalml + matplotlib/seaborn. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) —
Open skill - /00.2-Full-empirical-analysis-skill_Stata
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc +
Open skill

