Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/14-luischanci-claude-code-research-starter/dot-claude/skills/research-ideation

research-ideation

Verified

Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset.

Research Ideation

Generate 3-5 research questions ordered from descriptive to causal.

Steps

  1. Understand context: Read CLAUDE.md and any relevant project files.

  2. 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?
  3. 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
  4. Rank questions by feasibility and contribution in a summary table.

  5. 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.)
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall