new-project

New Research Project

Formalize a research idea into a concrete project specification with testable hypotheses and empirical strategies.

Input: $ARGUMENTS — a topic, phenomenon, dataset, or "start fresh" for open-ended exploration.

This skill runs in three phases. Phase 1 is conversational — ask one or two questions at a time and wait for responses. Phases 2 and 3 run automatically after the interview.

For complex or ambiguous project-scoping requests, read ${CLAUDE_PLUGIN_ROOT}/skills/new-project/references/plan-first-workflow.md before Phase 1.

Phase 1: Research Interview

Goal: Draw out the researcher's thinking and establish a clear research question.

Ask questions one or two at a time. Build on each answer before moving to the next phase. Do NOT use AskUserQuestion — ask directly in your response. A good interview runs 4–6 exchanges.

Question Bank (select and adapt based on context)

The Puzzle (start here):

• "What phenomenon or puzzle are you trying to understand?"
• "What do you observe in the data / world that doesn't fit the standard explanation?"

Why It Matters:

• "Why does this matter? Who should care about the answer?"
• "Is there a policy lever here, or is this more about understanding a mechanism?"

Theoretical Motivation:

• "What's your intuition for why X happens — what's the mechanism?"
• "What would standard theory predict? Do you expect to find something different, and why?"

Data and Setting:

• "Do you have data in mind, or are you open on the data source?"
• "Is there a specific context, time period, country, or institutional setting you're focused on?"

Identification:

• "Is there a natural experiment, policy change, or discontinuity you could exploit?"
• "What's the biggest threat to a causal interpretation — what would a skeptic say?"

Expected Results + Contribution:

• "What would you expect to find? What would genuinely surprise you?"
• "What existing papers are closest to this? What gap does yours fill?"