This skill guides evaluating GraphRAG systems across KG quality, retrieval, accuracy, and reasoning with structured metrics and testing protocols.
npx playbooks add skill lyndonkl/claude --skill graphrag-evaluation
This skill guides evaluating GraphRAG systems across KG quality, retrieval, accuracy, and reasoning with structured metrics and testing protocols.. This skill provides a specialized system prompt that configures your AI coding agent as a graphrag evaluation expert, with detailed methodology and structured output formats.
Compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any agent that supports custom system prompts.
This skill guides evaluating GraphRAG systems across KG quality, retrieval, accuracy, and reasoning with structured metrics and testing protocols.