Skip to content
Skills Library
Science & research · Planning

new-project

/new-project

Start a new research project. Structured interview formalizes the idea; generates research questions with identification strategies and a project spec. Use when developing or documenting a new research idea, not searching literature or data.

Licence
MIT
Last repository change
06.07.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 06.07.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Start a new research project. Structured interview formalizes the idea; generates research questions with identification strategies and a project spec. Use when developing or documenting a new research idea, not searching literature or data.

Arguments

/new-project [brief topic or 'start fresh']
Original author description

Start a new research project. Structured interview formalizes the idea; generates research questions with identification strategies and a project spec. Use when developing or documenting a new research idea, not searching literature or data.

How it works

  1. Phase 1: Research Interview
  2. Phase 2: Research Ideation
  3. Phase 3: Save Project Spec
  4. After Saving
Original SKILL.md headings · 166 lines, 882 words
SKILL.md preview
---
name: new-project
description: "Start a new research project. Structured interview formalizes the idea; generates research questions with identification strategies and a project spec. Use when developing or documenting a new research idea, not searching literature or data."
when_to_use: "new project, start research, I have an idea, help develop this, I want to study X, formalize this idea, what's my research question, what identification strategy, write up project idea, turn topic into paper"
argument-hint: "[brief topic or 'start fresh']"
allowed-tools: ["Read", "Grep", "Glob", "Write"]
---

# 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?"

### When to Stop Interviewing
Move to Phase 2 when you have:
- A clear research question (one sentence)
- At least one plausible identification strategy
- Some sense of what data exists or is needed
- The motivation / contribution

If after 3 exchanges the user keeps giving vague answers, move to Phase 2 anyway and flag the open questions.


## Phase 2: Research Ideation

**Goal:** Generate 3–5 structured research questions covering the full range from descriptive to causal.

Announce the transition: *"Great — I have enough to generate a structured set of research questions. Let me build that out now."*

Then generate **3–5 research questions** ordered by type:

| Type | What It Asks |
|------|-------------|
| **Descriptive** | What are the patterns? How has X evolved? |
| **Correlational** | What factors are associated with X, controlling for Z? |
| **Causal** | What is the causal effect of X on Y? |
| **Mechanism** | Through what channel does X affect Y? |
| **Policy** | Would intervention X improve outcome Y? |

**For each RQ, develop:**
- **Hypothesis** — testable prediction with expected direction/magnitude
- **Identification Strategy:**
  - Method (DiD, RDD, IV, synthetic control, etc.)
  - Treatment (what varies, when, where)
  - Control group (comparison units)
  - Key assumption (parallel trends, exclusion restriction, etc.)
  - Main robustness checks (pre-trends test, placebo, etc.)
- **Data requirements** — what variables, time period, geography, unit of observation
- **Key pitfalls** — 2 main threats to identification + mitigations
- **Related work** — 2-3 papers using similar approaches (name only, no fabrication)

**Rank the questions** by feasibility × contribution:

| RQ | Feasibility | Contribution | Priority |
|----|-------------|-------------|----------|
| 1  | High | High | ★★★ |
| 2  | High | Medium | ★★ |
| ... | ... | ... | ... |


## Phase 3: Save Project Spec

Produce the unified project spec document and save it.

**Save to:** `quality_reports/project_spec_[sanitized_topic].md`

```markdown
# Research Project: [Working Title]

**Date:** [YYYY-MM-DD]
**Researcher:** [from CLAUDE.md if available]


## Research Question

[Single clear sentence]

## Motivation

[2–3 paragraphs: why this matters, theoretical context, policy relevance, what the answer would change]

## Research Questions

### RQ1: [Question] — Priority: ★★★ (Feasibility: High / Contribution: High)

**Type:** Causal

**Hypothesis:** [Testable prediction with expected sign]

**Identification Strategy:**
- **Method:** [e.g., Staggered DiD with Sun–Abraham estimator]
- **Treatment:** [What varies and when]
- **Control group:** [Comparison units]
- **Key assumption:** [e.g., Parallel pre-trends conditional on controls]
- **Robustness:** [Pre-trends test, placebo outcomes, alternative control groups]

**Data Requirements:**
- [Dataset or data type needed]
- [Key variables: treatment proxy, outcome, controls]
- [Time period and geography]

**Key Pitfalls:**
1. [Threat + mitigation]
2. [Threat + mitigation]

**Related Work:** [Author (Year)], [Author (Year)]


[Repeat for RQ2–RQ5]


## Priority Empirical Strategy

[1 paragraph recommending the single highest-priority RQ and why, with the specific identification approach]

## Open Questions

[Issues raised in the interview that need further thought before committing to a strategy]


## Suggested Next Steps

1. **`/lit-review [topic]`** — Search the literature for related work and citation chains
2. **`/data-finder [topic]`** — Find and assess datasets for the priority RQ
3. Once data is secured: **`/data-analysis`** to begin analysis
```


## After Saving

Tell the user:
- The spec is saved to `quality_reports/project_spec_[topic].md`
- Recommended next step: `/lit-review [topic]` to build the literature foundation
- Then: `/data-finder [topic]` to identify and assess data sources
Files in this package (3)
  • SKILL.md 6 KB
  • assets/requirements-spec.md 1 KB
  • references/plan-first-workflow.md 2 KB

Versions

RepositoryScoreLicence
This page · felpix-studios/social-science-research100MIT
rstrlnkv/CoreKit100MIT
NoviaIntSysGroup/visual-core100MIT
jmagly/aiwg100MIT
jmagly/aiwg100MIT
JoaoCarlos134/claude-kit100MIT
jcottam/agent-resources100MIT
peterbamuhigire/chwezi-dev-engine100MIT
summerengine/summer100MIT

Database snapshot: 13.11.2026 · package version c7cb89eb20da (SHA-256 digest of the entire package)

Downloads in the last 30 days: 1 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100interview-me
    Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy). Use when user says "interview me", "help me think through this idea", "I have a half-baked idea", "formalize this into a project",…
  • 100interview-me
    通过互动访谈,把模糊的研究想法整理成结构化研究需求说明,涵盖研究问题、假设、识别、数据需求和实证策略。用户说 "interview me"、"help me think through this idea"、"I have a half-baked idea"、"formalize this into a project"、"walk me through framing a study"、"访谈我"、"帮我理清研究想法" 或 "把想法变成研究方案"…
  • 90research-start
    Start a research project, investigate a new research idea, or decide where to begin a data-science/ML study. Use for requests such as start research, explore an idea, plan a study, or define the research pipeline. Route clarification, component structure and planning before implementation.
  • 100research-ideation
    This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research gaps", "conduct gap analysis", "start research project", "conduct literature review", "define research question", "select research method", "plan research", or…
  • 100academic-research-companion
    Guide a research project through the full academic lifecycle — from raw idea to concrete research question, literature grounding, methodology, writing, feedback, and publication. Use this skill whenever the user shares a research idea, asks to "flesh out" a topic, wants sources…
  • 100research-ideation
    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…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.