Subagent-Driven Literature Review

What problem does it solves? Manually screening hundreds of papers or performing deep dives on many relevant articles is slow and can overwhelm a single AI's context window. This skill leverages parallel subagents to dramatically speed up large-scale literature reviews, allowing you to get results faster.

Core Features & Use Cases

• Parallel Screening: Dispatches multiple AI subagents to screen large batches of papers simultaneously, drastically reducing review time.
• Deep Dive Analysis: Assigns individual subagents to perform detailed data extraction from priority papers, ensuring thoroughness.
• Citation Network Exploration: Uses subagents to efficiently explore forward and backward citation networks, expanding your research scope.
• Use Case: When facing a literature review of 100+ papers, simply ask Claude to "screen these 150 papers for relevance." This skill will then dispatch multiple AI subagents to work in parallel, screening papers and extracting data simultaneously, delivering consolidated results much faster than a single agent could.

Quick Start

Example: Initiate parallel screening for a large list of papers

"Screen these 100 papers in parallel for relevance to [your query]."