Research Ideation
Generate structured research questions, testable hypotheses, and empirical strategies from a topic, phenomenon, or dataset.
Input: $ARGUMENTS — a topic (e.g., "minimum wage effects on employment"), a phenomenon (e.g., "why do firms cluster geographically?"), or a dataset description (e.g., "panel of US counties with pollution and health outcomes, 2000-2020").
Steps
Understand the input. Read $ARGUMENTS and any referenced files. Check master_supporting_docs/ for related papers. Check .claude/rules/ for domain conventions.
Generate 3-5 research questions ordered from descriptive to causal:
- Descriptive: What are the patterns? (e.g., "How has X evolved over time?")
- Correlational: What factors are associated? (e.g., "Is X correlated with Y after controlling for Z?")
- Causal: What is the effect? (e.g., "What is the causal effect of X on Y?")
- Mechanism: Why does the effect exist? (e.g., "Through what channel does X affect Y?")
- Policy: What are the implications? (e.g., "Would policy X improve outcome Y?")
Tag each RQ with a likely paper type (drawn from methods-referee.md):
reduced-form (DiD, IV, RD, event study, synthetic control)
structural (estimation of a fully-specified model)
theory+empirics (formal model + empirical test of its predictions)
descriptive (measurement, data construction, pattern documentation)
formal-theory (pure theory, no empirical test in this paper)
survey-experiment (vignette, conjoint, list-experiment)
unsure (when multiple types are plausible — the user can pick later via /interview-me)
Use .claude/references/discipline-cards.md to bias the distribution by field (econ vs poli-sci default frequencies differ — e.g., poli-sci skews more toward survey-experiment and formal-theory than econ does).
For each research question, develop:
- Hypothesis: A testable prediction with expected sign/magnitude
- Identification strategy: How to establish causality (DiD, IV, RDD, synthetic control, etc.)
- Data requirements: What data would be needed? Is it available?
- Key assumptions: What must hold for the strategy to be valid?
- Potential pitfalls: Common threats to identification
- Related literature: 2-3 papers using similar approaches
Rank the questions by feasibility and contribution.
Save the output to quality_reports/research_ideation_[sanitized_topic].md
Output Format
# Research Ideation: [Topic]
**Date:** [YYYY-MM-DD]
**Input:** [Original input]
## Overview
[1-2 paragraphs situating the topic and why it matters]
## Research Questions
### RQ1: [Question] (Feasibility: High/Medium/Low)
**Type:** Descriptive / Correlational / Causal / Mechanism / Policy
**Paper type:** reduced-form / structural / theory+empirics / descriptive / formal-theory / survey-experiment / unsure
**Hypothesis:** [Testable prediction]
**Identification Strategy:**
- **Method:** [the identification approach you would defend in a seminar]
- **Treatment:** [What varies and when]
- **Control group:** [Comparison units]
- **Key assumption:** [the assumption the method's validity rests on, stated so it can be attacked]
**Data Requirements:**
- [Dataset 1 — what it provides]
- [Dataset 2 — what it provides]
**Potential Pitfalls:**
1. [Threat 1 and possible mitigation]
2. [Threat 2 and possible mitigation]
**Related Work:** [Author (Year)], [Author (Year)]
---
[Repeat for RQ2-RQ5]
## Ranking
| RQ | Feasibility | Contribution | Priority |
|----|-------------|-------------|----------|
| 1 | High | Medium | ... |
| 2 | Medium | High | ... |
## Suggested Next Steps
1. [Most promising direction and immediate action]
2. [Data to obtain]
3. [Literature to review deeper]
Post-Flight Verification (mandatory, CoVe)
Before returning the ideation report, run the Post-Flight Verification protocol from .claude/rules/post-flight-verification.md. Research ideation is hallucination-prone in three specific ways:
- Negative-literature claims — "no prior work studies X" is frequently wrong.
- Dataset structure claims — "The CPS contains field
educ_attain" can be confidently wrong about variable names, coverage years, or restricted-access status.
- Estimator feasibility claims — "this works with panel fixed effects" can misstate an identification assumption.
Steps
- Extract claims from the draft ideation report: each negative-literature claim, each named dataset with attributed fields, each claimed identification strategy + required data structure.
- Generate verification questions per claim. Example: "Has Card & Krueger, Autor, or anyone in the last 10 years studied X? Search Google Scholar + NBER working papers." / "Does IPUMS-CPS include the
educ_attain variable 1990–2024?"
- Spawn
claim-verifier via the Agent tool with subagent_type=claim-verifier and context=fork. Hand it claims + questions + source pointers (WebSearch allowed, NBER/SSRN URLs preferred, dataset codebooks preferred). Do NOT include the draft.
- Reconcile: PASS → attach green block; PARTIAL → mark uncertain RQs with flags; FAIL → rewrite the affected RQ/hypothesis/strategy.
Skip conditions
--no-verify flag
- User explicitly says "I'll verify the literature myself"
Principles
- Be creative but grounded. Push beyond obvious questions, but every suggestion must be empirically feasible.
- Think like a referee. For each causal question, immediately identify the identification challenge.
- Consider data availability. A brilliant question with no available data is not actionable.
- Suggest specific datasets where possible (FRED, Census, PSID, administrative data, etc.).
1---2name: research-ideation3description: Generate structured research questions, testable hypotheses, and candidate empirical strategies from a topic, phenomenon, or dataset description. Use when user says "give me research ideas on X", "brainstorm questions about Y", "what could I study with this data?", "I'm looking for a paper idea on...", "generate hypotheses for...". One-shot generation, not multi-turn. For idea-refinement use `/interview-me`.4argument-hint: "[topic, phenomenon, or dataset description] [--no-verify]"5allowed-tools: ["Read", "Grep", "Glob", "Write", "WebSearch", "WebFetch", "Agent", "Task"]6metadata:7 source: https://skillmd.com/skills/pedrohcgs/research-ideation8---910# Research Ideation1112Generate structured research questions, testable hypotheses, and empirical strategies from a topic, phenomenon, or dataset.1314**Input:** `$ARGUMENTS` — a topic (e.g., "minimum wage effects on employment"), a phenomenon (e.g., "why do firms cluster geographically?"), or a dataset description (e.g., "panel of US counties with pollution and health outcomes, 2000-2020").1516---1718## Steps19201. **Understand the input.** Read `$ARGUMENTS` and any referenced files. Check `master_supporting_docs/` for related papers. Check `.claude/rules/` for domain conventions.21222. **Generate 3-5 research questions** ordered from descriptive to causal:23 - **Descriptive:** What are the patterns? (e.g., "How has X evolved over time?")24 - **Correlational:** What factors are associated? (e.g., "Is X correlated with Y after controlling for Z?")25 - **Causal:** What is the effect? (e.g., "What is the causal effect of X on Y?")26 - **Mechanism:** Why does the effect exist? (e.g., "Through what channel does X affect Y?")27 - **Policy:** What are the implications? (e.g., "Would policy X improve outcome Y?")28293. **Tag each RQ with a likely paper type** (drawn from `methods-referee.md`):30 - `reduced-form` (DiD, IV, RD, event study, synthetic control)31 - `structural` (estimation of a fully-specified model)32 - `theory+empirics` (formal model + empirical test of its predictions)33 - `descriptive` (measurement, data construction, pattern documentation)34 - `formal-theory` (pure theory, no empirical test in this paper)35 - `survey-experiment` (vignette, conjoint, list-experiment)36 - `unsure` (when multiple types are plausible — the user can pick later via `/interview-me`)3738 Use `.claude/references/discipline-cards.md` to bias the distribution by field (econ vs poli-sci default frequencies differ — e.g., poli-sci skews more toward `survey-experiment` and `formal-theory` than econ does).39404. **For each research question, develop:**41 - **Hypothesis:** A testable prediction with expected sign/magnitude42 - **Identification strategy:** How to establish causality (DiD, IV, RDD, synthetic control, etc.)43 - **Data requirements:** What data would be needed? Is it available?44 - **Key assumptions:** What must hold for the strategy to be valid?45 - **Potential pitfalls:** Common threats to identification46 - **Related literature:** 2-3 papers using similar approaches47485. **Rank the questions** by feasibility and contribution.49506. **Save the output** to `quality_reports/research_ideation_[sanitized_topic].md`5152---5354## Output Format5556```markdown57# Research Ideation: [Topic]5859**Date:** [YYYY-MM-DD]60**Input:** [Original input]6162## Overview6364[1-2 paragraphs situating the topic and why it matters]6566## Research Questions6768### RQ1: [Question] (Feasibility: High/Medium/Low)6970**Type:** Descriptive / Correlational / Causal / Mechanism / Policy71**Paper type:** reduced-form / structural / theory+empirics / descriptive / formal-theory / survey-experiment / unsure7273**Hypothesis:** [Testable prediction]7475**Identification Strategy:**76- **Method:** [the identification approach you would defend in a seminar]77- **Treatment:** [What varies and when]78- **Control group:** [Comparison units]79- **Key assumption:** [the assumption the method's validity rests on, stated so it can be attacked]8081**Data Requirements:**82- [Dataset 1 — what it provides]83- [Dataset 2 — what it provides]8485**Potential Pitfalls:**861. [Threat 1 and possible mitigation]872. [Threat 2 and possible mitigation]8889**Related Work:** [Author (Year)], [Author (Year)]9091---9293[Repeat for RQ2-RQ5]9495## Ranking9697| RQ | Feasibility | Contribution | Priority |98|----|-------------|-------------|----------|99| 1 | High | Medium | ... |100| 2 | Medium | High | ... |101102## Suggested Next Steps1031041. [Most promising direction and immediate action]1052. [Data to obtain]1063. [Literature to review deeper]107```108109---110111## Post-Flight Verification (mandatory, CoVe)112113Before returning the ideation report, run the Post-Flight Verification protocol from [`.claude/rules/post-flight-verification.md`](../../rules/post-flight-verification.md). Research ideation is hallucination-prone in three specific ways:1141151. **Negative-literature claims** — "no prior work studies X" is frequently wrong.1162. **Dataset structure claims** — "The CPS contains field `educ_attain`" can be confidently wrong about variable names, coverage years, or restricted-access status.1173. **Estimator feasibility claims** — "this works with panel fixed effects" can misstate an identification assumption.118119### Steps1201211. **Extract claims** from the draft ideation report: each negative-literature claim, each named dataset with attributed fields, each claimed identification strategy + required data structure.1222. **Generate verification questions** per claim. Example: "Has Card & Krueger, Autor, or anyone in the last 10 years studied X? Search Google Scholar + NBER working papers." / "Does IPUMS-CPS include the `educ_attain` variable 1990–2024?"1233. **Spawn `claim-verifier`** via the `Agent` tool with `subagent_type=claim-verifier` and `context=fork`. Hand it claims + questions + source pointers (WebSearch allowed, NBER/SSRN URLs preferred, dataset codebooks preferred). Do NOT include the draft.1244. **Reconcile:** PASS → attach green block; PARTIAL → mark uncertain RQs with flags; FAIL → rewrite the affected RQ/hypothesis/strategy.125126### Skip conditions127128- `--no-verify` flag129- User explicitly says "I'll verify the literature myself"130131---132133## Principles134135- **Be creative but grounded.** Push beyond obvious questions, but every suggestion must be empirically feasible.136- **Think like a referee.** For each causal question, immediately identify the identification challenge.137- **Consider data availability.** A brilliant question with no available data is not actionable.138- **Suggest specific datasets** where possible (FRED, Census, PSID, administrative data, etc.).