brycewang-stanford/Auto-Empirical-Research-Skills / skills/30-zirui-song-claude-skills/lit-review
lit-review
VerifiedSummarize academic papers, extract key findings, and identify research gaps
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
SKILL.md
View on GitHub---
name: lit-review
description: Summarize academic papers, extract key findings, and identify research gaps
---
# Literature Review Assistant
When the user provides a paper (PDF, URL, or description), help them systematically analyze and document it for their research.
## Paper Summary Template
When summarizing a paper, extract and organize the following:
### 1. Basic Information
- **Citation:** Authors (Year). "Title." *Journal*, Volume(Issue), Pages.
- **Paper Type:** Empirical / Theoretical / Review / Method
- **Field:** Finance / Economics / Accounting / Management
### 2. Research Question
- What is the main question or hypothesis?
- What gap in the literature does it address?
### 3. Data & Sample
- **Data sources:** (e.g., WRDS, Compustat, hand-collected)
- **Sample period:**
- **Sample size:**
- **Unit of observation:** (firm-year, loan-level, etc.)
- **Key filters/restrictions:**
### 4. Methodology
- **Identification strategy:** (DiD, RDD, IV, matching, etc.)
- **Main specification:** Describe the regression model
- **Key variables:**
- Dependent variable(s):
- Independent variable(s) of interest:
- Controls:
- **Fixed effects:**
### 5. Main Findings
- List 2-4 key results with magnitudes when available
- Economic significance (not just statistical)
### 6. Robustness & Limitations
- What robustness checks do they perform?
- Potential concerns or limitations noted by authors
- Your assessment of identification concerns
### 7. Relevance to My Research
- How does this relate to your current project?
- What can you cite this paper for?
- Any data/methods you could adopt?
---
## Quick Commands
When the user says:
- **"summarize this paper"** - Use the full template above
- **"quick summary"** - Provide only: citation, research question, main finding, and relevance
- **"compare papers"** - Create a comparison table across multiple papers
- **"find gaps"** - Identify what questions remain unanswered
- **"cite for"** - Suggest how to cite this paper for a specific claim
---
## Comparison Table Format
When comparing multiple papers on a topic:
| Aspect | Paper 1 | Paper 2 | Paper 3 |
|--------|---------|---------|---------|
| Research Question | | | |
| Sample/Period | | | |
| Identification | | | |
| Main Finding | | | |
| Limitation | | | |
---
## Literature Gap Analysis
When asked to identify gaps, consider:
1. **Unexplored settings:** Are there contexts where this hasn't been studied?
2. **Mechanism:** Is the channel well-identified or just a black box?
3. **Heterogeneity:** Which cross-sectional variations are unexplored?
4. **External validity:** Does it generalize beyond the specific sample?
5. **Time period:** Are findings stable across different periods/regimes?
6. **Data limitations:** What would better data reveal?
---
## BibTeX Generation
When summarizing, also provide a BibTeX entry:
```bibtex
@article{AuthorYear,
author = {Last1, First1 and Last2, First2},
title = {Paper Title},
journal = {Journal Name},
year = {YYYY},
volume = {XX},
number = {X},
pages = {XXX--XXX},
doi = {10.xxxx/xxxxx}
}
```
---
## Notes
- Always note if a paper is published vs. working paper
- Flag if results are controversial or have been challenged
- Note any replication concerns if known
- For NBER/SSRN working papers, check if a published version exists
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |