Literature Review

This generates a literature review by simulating conversations between different expert personas who each ask questions from their angle, then grounds the answers in actual papers pulled from Semantic Scholar, OpenAlex, and arXiv. It's inspired by STORM's multi-perspective dialogue approach. You create 3-5 personas like "ML systems researcher focused on efficiency" or "theoretical statistician," run multi-turn Q&A sessions for each, then synthesize everything into a structured review with citations. Best for kicking off a new research project or writing a survey section when you need breadth across different perspectives. The key idea is that diverse personas surface different aspects of a topic that you'd miss with straightforward keyword searches.

skills.sh installs: 4.1K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill literature-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Literature Review

Conduct deep literature reviews through multi-perspective dialogue and systematic search.

Input

$0 — Research topic or question
$1 — Optional: specific focus or angle

References

Multi-perspective dialogue prompts (STORM): ~/.claude/skills/literature-review/references/dialogue-prompts.md
Literature review workflow (AgentLaboratory): ~/.claude/skills/literature-review/references/review-workflow.md

Scripts (from literature-search skill)

# Search Semantic Scholar
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py --query "topic" --max-results 20

# Search OpenAlex
python ~/.claude/skills/literature-search/scripts/search_openalex.py --query "topic" --max-results 20

# Search arXiv
python ~/.claude/skills/deep-research/scripts/search_arxiv.py --query "topic" --max-results 10