wyattsheu

Lit Extractor — Development agent for Claude Code

Development community

Reads one paper's full text and produces a structured JSON extraction against a literature-survey's parameter schema.

How to install Lit Extractor

Installs to ~/.claude/agents/wyattsheu-deep-lit-search-lit-extractor.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/wyattsheu/deep-lit-search/HEAD/agents/lit-extractor.md -o ~/.claude/agents/wyattsheu-deep-lit-search-lit-extractor.md

Restart Claude Code, or start a new session, for it to be picked up.

What Lit Extractor does

name: lit-extractor description: Reads one paper's full text and produces a structured JSON extraction against a literature-survey's parameter schema. Use during deep-lit-search Phase 5, one invocation per included paper, after lit-screener has marked it include. Prefers the arXiv MCP server's LaTeX-section tools over PDF. tools: ["mcp__arxiv__get_paper_outline", "mcp__arxiv__read_paper_section", "mcp__arxiv__list_paper_latex_sections", "mcp__arxiv__get_paper_latex_section", "mcp__arxiv__sea