Skip to main content
skill CX Codex

research-ideation · meleantonio — Claude Code skill: what it does, how to install

research-ideation guides economists from raw observations or datasets to testable research questions. Useful when starting dissertation projects or designing policy evaluations.

CC0-1.0 196 installs ★ 675 updated 2026-09-26

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add meleantonio/awesome-econ-ai-stuff --skill research-ideation -a claude-code
Open on GitHub

What research-ideation does

This skill structures economic brainstorms through a three-step workflow. First, the assistant asks about your subfield, methodological preferences (theory, empirical, or structural), and data constraints. Next, it applies structured frameworks. These examine empirical puzzles, unexploited natural experiments, newly linked datasets, or extensions to seminal papers.

The result comes with an evaluation matrix checking data feasibility, identification credibility, and academic contribution. Without clean identification, research ideas quickly fall into pitfalls like questions that lack data or remain too broad.

What it helps with

  • formulate testable hypotheses for an economics dissertation
  • design an empirical project around newly acquired datasets
  • find unexploited natural experiments for policy evaluation
  • transfer econometric methods across subfields

Example prompts for the agent

  • I study labor economics and have access to LinkedIn data. Help me generate research questions.
  • Help me find a research topic applying industrial organization methods to wage setting.
  • We observed slowing productivity despite rising tech adoption. Run a 5 Whys analysis to find a testable hypothesis.

How to install research-ideation

1Skills CLI (Vercel)

npx skills add meleantonio/awesome-econ-ai-stuff --skill research-ideation -a claude-code

2Manually: put the files in place

~/.claude/skills/research-ideation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/research-ideation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about research-ideation

How to install research-ideation in Claude Code?

Run npx skills add meleantonio/awesome-econ-ai-stuff --skill research-ideation -a claude-code. The skill file will be placed in ~/.claude/skills/research-ideation/SKILL.md.

What does research-ideation do?

It guides researchers through economic ideation frameworks to convert puzzles, observations, or data sources into structured, testable hypotheses.

How does the skill evaluate research ideas?

It builds an evaluation matrix assessing feasibility, novelty of contribution, target audience interest, and credibility of empirical identification.

Source text

SKILL.md · CC0-1.0
---
name: research-ideation
description: Generate research questions from economic phenomena
workflow_stage: ideation
compatibility:
  - claude-code
  - cursor
  - codex
  - gemini-cli
author: Awesome Econ AI Community
version: 1.0.0
tags:
  - research
  - ideation
  - hypothesis
  - brainstorming
---

# Research Ideation

## Purpose

This skill helps economists generate and refine research questions by applying economic thinking frameworks. It guides the process from observing phenomena to formulating testable hypotheses.

## When to Use

- Starting a new research project
- Brainstorming dissertation topics
- Finding angles for policy analysis
- Developing extensions of existing work

## Instructions

### Step 1: Understand the Starting Point

Ask the user:
1. Do you have a phenomenon, puzzle, or data source in mind?
2. What field/subfield of economics?
3. What's your methodological preference? (Theory, empirical, structural)
4. Any constraints? (Data access, timeline, etc.)

### Step 2: Apply Ideation Frameworks

Use these approaches:

**1. The Puzzle Approach**
- What's surprising about current patterns?
- What contradicts conventional economic wisdom?
- Where do standard models fail?

**2. The Policy Approach**
- What policies lack rigorous evaluation?
- What natural experiments remain unexploited?
- What interventions might solve important problems?

**3. The Data Approach**
- What new data sources have become available?
- What can existing data tell us that hasn't been explored?
- What linkages between datasets are possible?

**4. The Extension Approach**
- How can seminal papers be extended?
- What mechanisms remain unexplored?
- Can methods from one field apply to another?

### Step 3: Evaluate and Refine

For each idea, assess:
- **Feasibility**: Can this be done with available data/methods?
- **Contribution**: What's new here?
- **Interest**: Who cares about this question?
- **Identification**: Can effects be credibly estimated?

## Example Interaction

**User Query:** "I'm interested in labor economics and have access to LinkedIn data"

**Generated Response:**

## Research Ideas: LinkedIn Data × Labor Economics

### 1. Network Effects in Job Search
**Question:** How do professional networks affect job transitions and wage changes?

**Puzzle:** Standard search models assume random matching, but most jobs come through networks. How much do networks matter for outcomes?

**Approach:**
- Track profile updates signaling job changes
- Measure network overlap between current/future employers
- Instrument with exogenous network shocks (school alumni connections)

**Contribution:** Quantify the causal role of networks vs. unobserved ability

---

### 2. Skill Signaling and Returns
**Question:** Do workers who list specific skills on profiles earn wage premiums?

**Puzzle:** Are listed skills signals of ability, or just cheap talk? What's the return to skill acquisition vs. skill signaling?

**Approach:**
- Compare wages before/after workers add skills
- Use skill endorsements as validation
- Exploit skill assessment features as quasi-experiments

---

### 3. Gender Gaps in Self-Promotion
**Question:** Do men and women describe equivalent achievements differently?

**Puzzle:** Lab evidence shows women understate accomplishments. Does this appear in real profiles and affect outcomes?

**Approach:**
- NLP analysis of profile language (adjectives, quantification)
- Compare language for workers in same role/company
- Link to recruiter contact rates if available

---

### 4. Remote Work and Labor Market Geography
**Question:** How has remote work changed the geographic reach of job matching?

**Approach:**
- Compare pre/post-2020 job applications by distance
- Measure changes in location signals on profiles
- Study wage convergence across cities

---

## Evaluation Matrix

| Idea | Data Feasibility | Identification | Policy Relevance |
|------|-----------------|----------------|------------------|
| Network effects | High | Medium (need IV) | High |
| Skill signaling | High | Medium | Medium |
| Gender language | High | High (descriptive) | High |
| Remote geography | High | High (COVID natural experiment) | High |

## Recommended Next Steps

1. **For empirical work:** Start with Idea #4 (clearest identification)
2. **For policy impact:** Idea #1 has most implications for job matching platforms
3. **For methodological novelty:** Idea #3 combines NLP with quasi-experimental methods

---

## Frameworks for Generating Questions

### The "5 Whys" for Economics

Start with an observation and drill down:
1. GDP growth is slowing → Why?
2. Productivity is stagnant → Why?
3. Investment is low → Why?
4. Uncertainty is high → Why?
5. Policy is unpredictable → **Testable: Does policy uncertainty cause low investment?**

### The "What If" Generator

- What if [policy X] were implemented?
- What if [technology Y] became widespread?
- What if [assumption Z] were relaxed?

### The Cross-Field Pollinator

Take a method from one field and apply to another:
- IO techniques → Labor markets (how do firms choose wages like prices?)
- Finance models → Education (returns to schooling as asset pricing)
- Macro shocks → Micro outcomes (firm-level effects of exchange rate changes)

## Common Pitfalls

- ❌ Questions that are too broad ("What causes inequality?")
- ❌ Questions without clean identification ("Does education cause income?")
- ❌ Questions without data ("Were medieval peasants happy?")
- ❌ Questions already well-answered

## References

- [Shapiro (2022) How to Get Started on Research in Economics](https://www.brown.edu/Research/Shapiro/pdfs/research.pdf)
- [Angrist & Pischke on Mostly Harmless research design](https://www.mostlyharmlesseconometrics.com/)
- [AEA Research Pipelines](https://www.aeaweb.org/rfe/)

## Changelog

### v1.0.0
- Initial release with ideation frameworks

© Awesome Econ AI Community · CC0-1.0 · meleantonio/awesome-econ-ai-stuff

Similar skills

All skills for Science and research →

research-ideation by other authors comes first.

research-ideation Galaxy-Dawn research-ideation guides the research project kickoff by framing questions through 5W1H, mapping literature gaps, and organizing papers in Zotero. CX Codex +1 586installs research-ideation EvoScientist Guides research ideation from literature grounding and multi-persona brainstorming to ELO ranking and structured research proposals. CX Codex +1 502installs research-ideation pedrohcgs The research-ideation skill turns a topic, phenomenon, or dataset description into research questions, testable hypotheses, and possible empirical designs. CX Codex +1 ★ 1,729repo stars scientific-brainstorming davila7 scientific-brainstorming turns Claude Code into a research partner for scientific ideation. Useful when formulating novel hypotheses or spotting cross-disciplinary links. CX Codex +1 345installs brainstorming-research-ideas Orchestra Research brainstorming-research-ideas — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that walks researchers through ten structured ideation frameworks. CX Codex +1 1,400installs idea-generation-and-ideation social-media-skills idea-generation-and-ideation runs an audience-driven content ideation system using the SPARK framework. Builds a scored bank of 100+ ideas from raw customer signals instead of generic AI brainstorming. CX Codex +1 1,300installs qcsd-ideation-swarm proffesor-for-testing qcsd-ideation-swarm runs Quality Criteria sessions during PI or sprint planning using HTSM v6.3 and Risk Storming. Delivers a GO, CONDITIONAL, or NO-GO verdict before development begins. CX Codex +1 107installs collaborative-ideation qodex-ai collaborative-ideation runs the brainstorm step by step: one question at a time, a few approaches, a design in sections, then a committed file under docs/plans/. CX Codex +1 154installs llm-research-workflow franklee16 llm-research-workflow enforces a structured methodology for extracting, classifying, and validating empirical variables in economics and finance research with LLMs. CX Codex +1 ★ 240repo stars

From the same set12

The whole set →
r-econometrics r-econometrics generates R code for causal inference and panel data using fixest, complete with diagnostics and publication tables. Useful for IV, DiD, and RDD research designs. CX Codex +1 340installs beamer-presentation beamer-presentation is a Claude Code skill that builds academic Beamer decks from a paper or project, with timed structure, themes, charts, and tables. CX Codex +1 285installs lit-review-assistant lit-review-assistant structures economics literature reviews, crafts database queries, and tracks research gaps. Helps synthesize empirical papers into standardized markdown templates. CX Codex +1 241installs api-data-fetcher The api-data-fetcher skill helps an agent pull economic indicators from FRED, World Bank, and other APIs. Use it for datasets, recurring updates, or cross-country panels. CX Codex +1 208installs econ-visualization econ-visualization generates publication-ready figures and charts for economics research in R or Python. CX Codex +1 202installs python-panel-data python-panel-data is a Claude Code skill that generates Python code for panel-data analysis, including fixed- and random-effects models, difference-in-differences, and regression tables. CX Codex +1 163installs latex-econ-model latex-econ-model typesets economic theory models in LaTeX using standard academic notation, from utility optimization to dynamic programming setups. CX Codex +1 147installs latex-tables Creates clean LaTeX tables for regression results and summary statistics using academic formatting standards. Use it when you need to format statistical output for journal submission. CX Codex +1 128installs

Project sponsors

Companies that keep this analytics open