agentleFS
Barrios88Barrios88/barrios-skills/skills/research-tools/research-ideation/SKILL.md

research-ideation

Skill63 starsChanged 5 months agoMITView on GitHub

Generate research questions from economic phenomena

15 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, daily-coding and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 3 projects that use this

  • Google CloudSkill

    citation-verification

    Verify that citations in a document resolve to real records and that claimed titles match. Use before trusting a document's reference list.

    Also in 4 projects that use this

  • AnthropicSkill

    command-development

    This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

    Also in 3 projects that use this

  • +2 more from Clay-HHK

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do you have a phenomenon, puzzle, or data source in mind?

    line 40
  2. Distinctive:

    Question: Do workers who list specific skills on profiles earn wage premiums?

    line 100
  3. Distinctive:

    Use skill endorsements as validation

    line 106
  4. Distinctive:

    Question: Do men and women describe equivalent achievements differently?

    line 112
  5. Distinctive:

    For empirical work: Start with Idea #4 (clearest identification)

    line 144
  6. Distinctive:

    Start with an observation and drill down:

    line 154

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Barrios Skills — John Barrios's curated workflow for economists and accountants. Prioritize reproducible empirical work, clear identification language, and journal-ready output.

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

IdeaData FeasibilityIdentificationPolicy Relevance
Network effectsHighMedium (need IV)High
Skill signalingHighMediumMedium
Gender languageHighHigh (descriptive)High
Remote geographyHighHigh (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

Changelog

v1.0.0

  • Initial release with ideation frameworks

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.