brycewang-stanford/Auto-Empirical-Research-Skills / skills/14-luischanci-claude-code-research-starter/dot-claude/skills/interview-me
interview-me
VerifiedInteractive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy.
Research Interview
Conduct a structured interview through 6 phases to formalize a research idea.
Interview Phases
- The Big Picture -- What phenomenon or puzzle are you investigating? Why does it matter?
- Theoretical Motivation -- What's your intuition for the mechanism? What does theory predict?
- Data and Setting -- What data do you have? What specific context or time period?
- Identification -- Any natural experiments or policy changes? What are the threats to causality?
- Expected Results -- What do you predict? What are the implications for policy or theory?
- Contribution -- How does this differ from existing work? What's the value-added?
Protocol
- Ask questions one at a time (no multi-question dumps)
- Probe deeper based on answers -- follow up on weak spots
- Be curious, not prescriptive
- Know when to stop (after 5-8 meaningful exchanges)
Output
After the interview, produce a Research Specification Document:
# Research Specification: [Topic]
## Research Question
[Clear, specific, answerable]
## Motivation
[Why this matters -- policy relevance, theoretical gap, empirical puzzle]
## Hypothesis
[Testable prediction with expected sign/magnitude]
## Empirical Strategy
- **Method:** [DiD, IV, RDD, etc.]
- **Treatment/Variation:** [What provides identification]
- **Control group:** [Comparison group]
- **Identifying assumption:** [What must hold]
- **Robustness checks:** [Planned sensitivity analyses]
## Data
[Sources, sample, key variables, time period]
## Expected Results
[What you expect to find and why]
## Contribution
[How this advances the literature]
## Open Questions
[What remains uncertain]
Save to quality_reports/research_spec_[sanitized_topic].md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |