research-survey

Files (4)

• SKILL.md
• survey-template.md · assets/
• section-quality-checklist.md · references/
• survey-methodology.md · references/

SKILL.md (first lines)

# Research Survey

Generates high-quality, survey-grade literature reviews from papers collected by `paper-navigator`.

```
paper-navigator (collect 30-120 papers)
    ↓
Stage 1: Generate Outline (query-type adaptive structure)
    ↓
Stage 2: Draft Survey (outline + top-30 papers)
    ↓
Stage 3: Expand Sections (draft + all papers, section-by-section)
    ↓
Stage 4: Generate Section Summaries
    ↓
Stage 5: Refine Summary Sections (Abstract/Intro/Conclusion)
    ↓
Stage 6: Assemble + References
```

## When to Use

- User asks for a "literature review", "survey", "field overview", or "systematic review"
- User has collected papers and wants them synthesized into a structured report
- User wants to understand the full landscape of a research field

## When NOT to Use

- **Finding papers** → use `paper-navigator` first, then come here
- **Generating research ideas** → use `research-ideation`
- **Writing a Related Work section for a paper** → use `paper-writing`

## Dependency: paper-navigator

This skill requires papers as input. If the user hasn't provided papers, **first invoke `paper-navigator`** (Workflow 1, target 30-120 papers) to collect them.

**CRITICAL: All paper discovery MUST use the `paper-navigator` skill and its scripts (scholar_search, citation_traverse, arxiv_monitor, recommend, etc.). Using WebSearch, WebFetch, or any generic web search tool for finding papers is PROHIBITED.** Generic web search cannot access Semantic Scholar, citation graphs, or academic recommendation systems. Only `paper-navigator` provides the academic search infrastructure needed for survey-quality literature collection.

---

## Stage 1: Generate Outline

**This is a two-phase process.** Different fields have different survey conventions — a clinical systematic review looks nothing like a CS methods survey. First generate a domain-appropriate template, then create the detailed outline.

### Phase 1A: Generate Domain-Specific Survey Template

Before outlining, identify the field and adapt the structure:

1. **Identify the field** from the user's goal and collected papers
2. **Select section names and organization logic** using the field-specific conventions in `assets/survey-template.md` (e.g., medicine organizes by intervention type and follows PRISMA; chemistry organizes by reaction class; social sciences organize by theoretical perspective)
3. **Add field-specific sections** (e.g., Risk of Bias Assessment for medicine, Structure-Property Relationships for materials, Ethical Considerations for human-subjects research)
4. **Determine comparison table dimensions** appropriate to the field

### Phase 1B: Create Detailed Outline

With the domain-specific template as the framework, generate the outline:

#### Query Type Classification

| Type | Example | Structure |
|------|---------|-----------|
| **A: Single-topic deep dive** | "Catalyst design for electrochemical CO2 reduction" | Intro → Problem Definition → **Methods (by mechanism/approach)** → Evaluation → Challenges → Conclusion |
| **B: Multi-topic parallel** | "Drug resistance mechanisms and therapeutic strategies in cancer immunotherapy" | Intro → **Topic 1 (definition + methods)** → **Topic 2 (definition + methods)** → Evaluation → Challenges → Conclusion |
| **C: Pipeline/stage-based** | "From sample preparation to data analysis in single-cell RNA sequencing" | Chapters organized by workflow stages |

#### Outline Requirements

The outline is NOT a simple heading list — it's a **blueprint with meta-instructions** for each section. For each `## Section`:

- Include `[Instruction: ...]` specifying what the section must contain
- Specify required tables with field-appropriate columns
- For main body sections: mandate taxonomy by underlying principle/mechanism, NOT chronology
- Include any field-required elements (e.g., PRISMA flowchart for medical systematic reviews, mathematical formalism for physics)

See `references/survey-methodology.md` for full outline generation rules and `assets/survey-template.md` for field-specific conventions.

---

## Stage 2: Draft Survey

Generate a complete draft from the outline using the **top-30 most relevant papers**.

- Use numbered citations [1], [2, 3] throughout
- Follow the outline's meta-instructions strictly
- Each methods section must build a taxonomy and include comparison tables
- Problem definition must include LaTeX formalization (`$$...$$`)

---

## Stage 3: Expand Sections

Expand each non-summary section using **all collected papers** (30-120). This is where survey-grade depth is achieved.

### Section Expansion Targets

| Section Type | Target Length | Focus |
|---|---|---|
| **Methods** | 6000+ words per paradigm chapter | Technical narratives, mechanism analysis, comparison tables |
| **Evaluation** | 3500+ words | Benchmark taxonomy, metric analysis, SOTA summary |
| **Challenges** | 3000+ words | Problem definition + evidence + opportunity per challenge |
| **Applications** | 3000+ words | Real-world use cases with specific achievements |
| **Problem Definition** | 2000+ words | LaTeX formalization, constraints, assumptions |
| **Other** | 2500+ words | Default |

### Expansion Rules

1. **Thematic coherence**: Keep same themes and narrative flow as draft — don't introduce unrelated topics
2. **Cite comprehensively**: Use as many relevant papers from the full collection as possible
3. **Survey-grade depth**: Multi-paragraph technical narratives per method family, not shallow bullet points
4. **For each paradigm/method family, include**:
   - Technical narrative: How it works, theoretical assumptions, nuances between papers
   - Critical analysis: Why effective, trade-offs, failure modes
   - Comparative analysis table: Method | Core Mechanism | Key Advantage | Limitation | Performance

---

## Stage 4: Generate Section Summaries

After all content sections are expanded, generate a condensed summary for each major section:

From KalarisLabs/Skill-Doctor, Apache-2.0.

More from KalarisLabs/Skill-Doctor