literature-search

name	literature-search
description	Medium-depth literature search — read AI-summarized reports for every paper analyzed
type	sop
layer	sop
agents	["alphaxiv","semantic-scholar"]
tools	{"alphaxiv":["discover_papers","get_paper_content"],"semantic-scholar":["relevanceSearch","paper","paperBatch","citations","references"]}
input	query (string), scope (survey | gap-analysis | background)
output	PaperAnalysis[] with metadata + AI summary content
dependencies	{"sops":["literature-research"]}

Literature Search SOP

Layer Rules

• Layer: sop — wraps MCP tools directly
• Called by: Any tactic or strategy requiring literature survey with paper content reading
• Calls: alphaxiv MCP tools, semantic-scholar MCP tools (never calls other SOPs)

Purpose

Medium-depth reading. Understand methods, contributions, and findings via AI-generated summary reports. Suitable for literature surveys, gap analysis, and building background knowledge.

Use this when you need to:

• Conduct a literature survey on a topic
• Understand what methods exist and how they compare
• Identify gaps in current research
• Build background knowledge for a research project

This skill reads AI-summarized reports — not raw full text. For rigorous analysis requiring raw text, use literature-research.

Tools

Tool	Purpose	Returns
alphaxiv.discover_papers	Primary search — arXiv semantic search	Ranked paper list with metadata
ss.relevanceSearch	Supplementary search — non-arXiv papers	Title, abstract, authors, citationCount
ss.paper / ss.paperBatch	Metadata enrichment	Citation count, DOI, S2 ID, externalIds
ss.citations	Papers that cite this paper (incoming)	Citing paper list with context
ss.references	Papers this paper cites (outgoing)	Referenced paper list
alphaxiv.get_paper_content	AI summary report (fullText: false)	Structured AI-generated paper report

HARD-GATE

**Do NOT base analysis on abstracts or discover_papers snippets alone.**

For EVERY paper selected for analysis, you MUST call:

alphaxiv.get_paper_content(url: arxiv_url, fullText: false)

This returns an AI-generated summary report optimized for LLM consumption.

PROHIBITED:

• Completing a research task without reading paper content
• Using only abstracts from ss.relevanceSearch as your evidence