Research IdeationSAFE

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: research-ideation
description: 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 mentions research project initiation phase. Provides comprehensive guidance for research startup workflow from idea generation to planning.
version: 0.1.0
---

# Research Ideation

Supports the complete workflow for the research project initiation phase, from vague idea to a traceable research contract: research question, hypothesis, evidence needs, falsification criteria, method selection, and next action.

## Core Features

### 1. Idea Brainstorming (5W1H Framework)

Systematically brainstorm research ideas using the 5W1H framework:
- **What**: What problem or phenomenon to study
- **Why**: Why this problem is important
- **Who**: Target audience and stakeholders
- **When**: Time scope and context of the research
- **Where**: Application scenarios and domains
- **How**: Preliminary research methodology ideas

**Integration with superpowers:brainstorming**: Can invoke the superpowers:brainstorming skill for interactive brainstorming to help rapidly generate and evaluate research ideas.

### 2. Literature Review

Systematically search, analyze, and synthesize related literature:
- Build effective search keywords
- Search via WebSearch across academic databases (arXiv, Google Scholar, etc.)
- Screen and evaluate paper quality
- Identify research trends and gaps
- Generate structured literature reviews from evidence-labeled sources
- **Zotero Integration**: Papers are automatically added to Zotero via DOI, organized into topic-based collections, and open-access PDFs are auto-attached for full-text reading

### 3. Gap Analysis

Systematically identify and evaluate research gaps:
- **Literature gaps**: Identify topics or questions not yet sufficiently studied
- **Methodological gaps**: Discover limitations and improvement opportunities in existing methods
- **Application gaps**: Identify opportunities for theory-to-practice transfer
- **Interdisciplinary gaps**: Discover research opportunities at the intersection of different fields
- **Temporal gaps**: Identify new research needs arising from changes over time

**Analysis Dimensions:**
- Coverage of research topics
- Comparison of strengths and weaknesses of existing methods
- Completeness of experimental setups
- Availability of datasets and benchmarks
- Gap between theory and practice

### 4. Research Question Definition

Formulate specific research questions based on literature analysis:
- Identify research gaps and opportunities
- Apply SMART principles to formulate questions
- Evaluate importance, novelty, and feasibility
- Define research objectives and expected contributions
- Write a `Research Question Card` that states the hypothesis, current evidence, missing evidence, support criteria, falsification criteria, and minimal next action
- Apply the proposal readiness gate before turning a card into a polished proposal

### 5. Method Selection

Select appropriate research methods:
- Analyze strengths and weaknesses of existing methods
- Evaluate method applicability
- Identify required technologies and resources
- Consider method feasibility

### 6. Research Planning

Develop detailed research plans:
- Plan research timeline
- Define milestones and deliverables
- Identify potential risks
- Assess resource requirements

## When to Use

### Scenarios for This Skill

Use the research-ideation skill in the following situations:

1. **Starting a new research project** - Have research interests but no clear research question yet
2. **Literature review** - Need to systematically understand a research field
3. **Research question formulation** - Need to transform vague ideas into specific research questions
4. **Method selection** - Need to choose appropriate research methods and technical approaches
5. **Research planning** - Need to plan research timeline and resources

### Typical Workflow

```
Research interest → Idea brainstorming (5W1H) → Research Question Card → Evidence Records → Gap analysis → Proposal readiness gate → Select method or experiment → Decision
```

**Conditional Outputs:**
- `research-question-card.md` - Always generate this for research startup or intake.
- `literature-review.md` - Generate only when evidence-labeled sources are sufficient for synthesis.
- `research-proposal.md` - Generate only when a selected Research Question Card passes the evidence gate.
- `references.bib` - Generate only when reliable citation metadata exists.
- Zotero collection with organized papers and PDFs - Create only when Zotero is configured, writable, and the user is not asking for dry-run/audit mode.

## Integration with Other Systems

### Complete Research Workflow

```
research-ideation (Research initiation)
    ↓
Experiment execution (completed by user)
    ↓
results-analysis (Results analysis)
    ↓
ml-paper-writing (Paper writing)
```

### Data Flow

- **Research Question Card** → Guides literature scope, experiment design, and method selection
- **Evidence Records** → Carry source type, claim strength, and allowed/forbidden wording into literature synthesis, project knowledge, and later claim audit
- **Proposal Readiness Gate** → Prevents abstract-only or webpage-placeholder evidence from becoming a polished proposal
- **Experimental results** → results-analysis for statistical analysis and claim candidates
- **Analysis results** → results-report and ml-paper-writing with explicit evidence limits

### Zotero Integration

Through the Zotero MCP server, the research-ideation workflow automates literature management:

- **Paper Discovery**: WebSearch finds relevant papers across academic databases
- **Auto-Import**: Extract DOI / arXiv ID / landing-page URLs from search results, then use `zotero_add_items_by_identifier` t

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.