Research Survey

Takes papers from paper-navigator and turns them into survey-grade literature reviews with proper taxonomies, comparison tables, and LaTeX formalizations. The pipeline is thorough: it generates a domain-specific outline (medical surveys look different from CS surveys), drafts with top papers, expands sections using all 30-120 papers to hit survey depth targets, then refines the abstract and intro based on what actually ended up in the body. Use this when you want a structured field overview or systematic synthesis, not for finding papers or writing a Related Work section for your own paper. The expansion stage is where it gets serious, targeting 6000+ words for methods chapters with technical narratives per paradigm.

skills.sh installs: 309
GitHub stars: 488
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add evoscientist/evoskills --skill research-survey --agent claude-code

Installs into .claude/skills of the current project.

Files

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.

SKILL.md on GitHub