Start a fresh conversation. Replace the highlighted placeholders.
Use research-ideation to develop and rank 3–5 research questions for [topic or dataset], each with a testable hypothesis, identification strategy, data needs, assumptions, pitfalls, and related papers.
Required inputs
[topic or dataset]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: research-ideationdescription: Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset.disable-model-invocation: trueargument-hint: "[topic, phenomenon, or dataset description]"allowed-tools: ["Read", "Grep", "Glob", "Write"]
Research Ideation
Generate 3-5 research questions ordered from descriptive to causal.
Steps
Understand context: Read CLAUDE.md and any relevant project files.
Generate 3-5 research questions ordered by type:
Descriptive: What are the stylized facts?
Correlational: What patterns exist in the data?
Causal: What is the effect of X on Y?
Mechanism: Through what channel does X affect Y?
Policy: What are the policy implications?
For each question, develop:
Testable hypothesis with expected sign/magnitude
Identification strategy (DiD, IV, RDD, synthetic control, matching, etc.)
Data requirements with availability assessment
Key assumptions and their plausibility
Potential pitfalls and how to address them
2-3 related papers
Rank questions by feasibility and contribution in a summary table.
Save output to quality_reports/research_ideation_[sanitized_topic].md.
Principles
Be creative but grounded in what's feasible
Think like a referee: what would make this convincing?
Consider data availability realistically
Suggest specific datasets (FRED, Census, PSID, BLS, central bank data, etc.)