literature-review

Conduct literature reviews via multi-persona dialogue simulation and grounded paper search.

Updated May 27, 2026
One-click install
npx skills add https://github.com/baljinnyamday/autonomous-red-team-agent --skill literature-review-baljinnyamday
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: literature-review
Source: https://github.com/baljinnyamday/autonomous-red-team-agent/tree/main/.agents/skills/literature-review
Command: npx skills add https://github.com/baljinnyamday/autonomous-red-team-agent --skill literature-review-baljinnyamday

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Writing a comprehensive literature review requires searching multiple academic databases, reading dozens of papers, and synthesizing diverse perspectives into a coherent narrative, which is slow and prone to narrow coverage. ## Core Features & Use Cases - Multi-Perspective Dialogue Simulation: Generates 3-5 expert personas (based on STORM) that ask questions from different research angles, with each answer grounded in retrieved papers. - Multi-Source Paper Search: Searches Semantic Scholar, OpenAlex, and arXiv via provided scripts to gather relevant publications. - Structured Synthesis: Combines persona conversations into an outline, a cited review, a paper database, and identified knowledge gaps. - Use Case: Starting a dissertation on multi-agent systems, run this Skill to automatically gather recent and foundational papers, simulate expert Q&A from systems and theory perspectives, and produce a cited survey draft. ## Quick Start Ask the agent to conduct a literature review on your research topic, for example by saying: run a literature review on retrieval-augmented generation for code.

Frequently Asked Questions about literature-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I conduct an automated literature review with AI?

Provide a research topic and the Skill generates 3-5 expert personas, simulates multi-turn Q&A dialogues per persona, searches academic databases for each question, and synthesizes everything into a cited, structured review with an outline and paper database.

What academic databases does literature search support?

The workflow searches Semantic Scholar, OpenAlex, and arXiv through dedicated Python scripts. Each script accepts a query string and a max-results parameter to control how many papers are returned.

How does multi-perspective dialogue improve a literature review?

Each persona represents a different research angle, such as a systems researcher or a theoretician, and asks questions from that viewpoint. This broadens coverage beyond the most popular papers and surfaces diverse approaches and contradictory positions.

Can I control how many papers are collected in the review?

Yes. The workflow parameters include a target paper count (default 5-10), maximum search iterations, and results per query. Dialogue turns per persona and number of personas are also configurable between 3 and 5.

What are the limitations of dialogue-based literature review?

The review only covers papers retrievable from the supported databases, so paywalled or very recent preprints may be missed. Every claim must be grounded in retrieved results, so topics with sparse literature will produce explicit gap statements rather than full sections.