GraphRAG Skill

The graph-rag skill provides structured methods for building and querying Knowledge Graphs (KG) from text and code. Unlike standard RAG, which relies on vector similarity, GraphRAG leverages structural relationships between entities to answer complex, multi-hop, and global queries.

When to Use This Skill

• When you need to understand the "big picture" of a massive repository or documentation set.
• When standard semantic search (vector-only) fails to retrieve relevant information for relational or aggregate questions (e.g., "What are the common design patterns used in this project?").
• When you need to trace dependencies across codebases for safe refactoring.
• When you need to generate high-quality summaries of knowledge clusters (communities).

Limitations of Standard Vector-Only RAG

Standard RAG (Retrieval-Augmented Generation) has significant blind spots:

1. Global Aggregation: It cannot easily answer questions requiring knowledge synthesis across the entire corpus (e.g., "Summarize all major architectural decisions").
2. Relational Depth: Vector similarity often misses multi-hop relationships between disparate files or concepts.
3. Information Density: Vector chunking can lose the context of how entities are linked, leading to hallucinated or fragmented answers.

Core Capabilities