Lit Review Assistant logo

Lit Review Assistant

CommunityPopular
brycewang-stanford
lit-review-assistant

Search, summarize, and synthesize economics literature

Overview

Publisherbrycewang-stanford
RepositoryAuto-Empirical-Research-Skills
Skill namelit-review-assistant
Stars
3.8K
Forks
479
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by brycewang-stanford on GitHub. Read the source before you install it.

Installation

Install the Lit Review Assistant AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git /tmp/Auto-Empirical-Research-Skills
mkdir -p .claude/skills
cp -r /tmp/Auto-Empirical-Research-Skills/skills/09-meleantonio-awesome-econ-ai-stuff/_skills/literature/lit-review-assistant .claude/skills/lit-review-assistant
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lit Review Assistant in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lit Review Assistant on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lit Review Assistant is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Literature Review Assistant

Purpose

This skill helps economists conduct literature reviews by structuring searches, summarizing papers, and synthesizing findings. It provides templates for organizing literature and identifying research gaps.

When to Use

  • Starting a literature review for a new project
  • Finding related work for a paper's introduction
  • Synthesizing existing evidence on a topic
  • Identifying gaps in the literature

Instructions

Step 1: Define the Research Domain

Ask the user:

  1. What is your specific research question?
  2. What's the scope? (Narrow field survey vs. cross-disciplinary review)
  3. What databases do you have access to? (JSTOR, EconLit, Google Scholar, NBER)
  4. What time period is relevant?
  5. Are there seminal papers to start from?

Step 2: Structure the Search

Help define search terms:

  1. Primary terms: Core concepts (e.g., "minimum wage", "employment")
  2. Methodological filters: (RCT, IV, difference-in-differences)
  3. Outcome terms: What effects are measured
  4. Geographic/temporal scope: If relevant

Step 3: Organize and Synthesize

Create a structured summary for each paper:

  • Citation
  • Research question
  • Data and methods
  • Key findings
  • Limitations
  • How it relates to user's project

Step 4: Identify Patterns and Gaps

  • What do papers agree on?
  • Where are disagreements?
  • What questions remain unanswered?
  • What methods haven't been applied?

Example Output: Literature Summary Template

markdown
# Literature Review: [TOPIC]

## Search Strategy

**Databases:** EconLit, NBER, Google Scholar, SSRN
**Date range:** 2010-2024
**Search terms:** 
- ("minimum wage" OR "wage floor") AND (employment OR jobs)
- ("minimum wage") AND ("difference-in-differences" OR "DiD")

**Inclusion criteria:**
- Peer-reviewed or NBER working papers
- Focused on [specific outcome]
- Uses causal identification strategy

---

## Seminal Papers

### Card and Krueger (1994)
**Citation:** Card, D., & Krueger, A. B. (1994). Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania. *American Economic Review*, 84(4), 772-793.

**Research Question:** What is the effect of minimum wage increases on employment?

**Data & Method:** 
- DiD comparing NJ (treatment) to PA (control)
- Survey of fast-food restaurants before/after NJ minimum wage increase

**Key Findings:**
- No negative employment effect found
- Employment slightly increased in NJ relative to PA

**Contribution:** Challenged conventional view; pioneered quasi-experimental methods in labor economics

**Limitations:**
- Single state, short time horizon
- Potential survey response bias

---

### Cengiz et al. (2019)
**Citation:** Cengiz, D., Dube, A., Lindner, A., & Zipperer, B. (2019). The Effect of Minimum Wages on Low-Wage Jobs. *Quarterly Journal of Economics*, 134(3), 1405-1454.

**Research Question:** Do minimum wage increases destroy jobs or compress the wage distribution?

**Data & Method:**
- Bunching estimator using 138 minimum wage events
- Examine employment distribution around minimum wage

**Key Findings:**
- Jobs below the new minimum wage disappear
- But replaced by jobs just above the minimum
- No significant overall employment loss

**Contribution:** Novel bunching methodology; large-scale evidence

---

## Synthesis: What We Know

| Finding | Evidence Quality | Consensus Level |
|---------|-----------------|-----------------|
| Small minimum wage increases have minimal employment effects | Strong (multiple RCTs/quasi-experiments) | High |
| Effects may be heterogeneous by region | Medium | Growing |
| Large increases (e.g., $15) less studied | Limited | Low |

## Research Gaps

1. **Mechanism:** How do firms absorb higher labor costs? (Prices, profits, productivity?)
2. **Long-run effects:** Most studies focus on 1-2 years
3. **Geographic heterogeneity:** Do effects differ in low vs. high cost-of-living areas?
4. **Spillovers:** Effects on workers earning above minimum wage

## Connection to Your Project

Your study of [SPECIFIC QUESTION] can contribute by:
- [How your work fills a gap]
- [What new data/method you bring]

Paper Summary Template

markdown
## [Author(s)] ([Year])

**Title:** [Full title]

**Published in:** [Journal/Working Paper Series]

**Research Question:** [One sentence]

**Data:**
- Source: [Dataset name]
- Period: [Years]
- Sample: [N observations, unit of analysis]

**Identification Strategy:** [Method in one sentence]

**Main Findings:**
1. [Key result 1 with magnitude]
2. [Key result 2]
3. [Robustness/heterogeneity]

**Limitations:**
- [Main concern 1]
- [Main concern 2]

**Relevance to your project:** [One sentence on how it connects]

**Key quote:** "[Most important direct quote]" (p. XX)

Search Strategy Tips

Google Scholar Operators

  • "exact phrase" - Exact matching
  • author:surname - Papers by specific author
  • source:journal - Papers in specific journal
  • -exclude - Exclude terms
  • [year]..[year] - Date range

Finding Seminal Papers

  1. Check citations in recent survey papers
  2. Look for papers with 1000+ citations
  3. Check JEL codes in EconLit
  4. Review "related articles" in Google Scholar

Building Citation Networks

  1. Start with 2-3 seminal papers
  2. Check what recent papers cite them (forward citations)
  3. Check their references (backward citations)
  4. Identify clusters of related work

Best Practices

  1. Use reference managers (Zotero, Mendeley, BibDesk)
  2. Create annotated bibliographies as you read
  3. Track search queries for reproducibility
  4. Update regularly before submission
  5. Balance breadth and depth - cover field but focus on closest work

Common Pitfalls

  • ❌ Only citing papers that support your argument
  • ❌ Not engaging with contradictory findings
  • ❌ Confusing correlation with causation when summarizing
  • ❌ Citing papers you haven't actually read
  • ❌ Missing important recent papers

References

Changelog

v1.0.0

  • Initial release with templates and search strategies

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lit Review Assistant AI skill do?

Search, summarize, and synthesize economics literature

Why use Lit Review Assistant on TypingMind?

Because you install it once and use it with any model. Lit Review Assistant is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lit Review Assistant in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/09-meleantonio-awesome-econ-ai-stuff/_skills/literature/lit-review-assistant. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lit Review Assistant?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lit Review Assistant?

As many as you like. As long as a model supports skills, you can use Lit Review Assistant with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lit Review Assistant AI skill free?

It is published on GitHub by brycewang-stanford. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇