Kg Extract

Extracts entities like classes, functions, and modules from your source code and stores them as a knowledge graph in AgentDB, complete with weighted relationships. The real value is in how it handles TypeScript imports: it correctly distinguishes between type-only imports (which are compile-time only) and value imports, avoiding phantom runtime dependency cycles that can mess up impact analysis. Use it when you need to understand codebase structure, trace dependencies, or figure out what breaks when you change something. It scans files, identifies entities, maps their relationships with different weights, then stores everything so you can query it later. Beats manually grepping through imports to understand how your modules actually connect.

skills.sh installs: 731
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill kg-extract --agent claude-code

Installs into .claude/skills of the current project.

Files

KG Extract

Extract entities (classes, functions, modules, types, concepts) and their relations (imports, extends, implements, depends-on, calls) from source files, then store them as a knowledge graph in AgentDB.

When to use

When you need to build or update a knowledge graph from source code or documentation. Useful for understanding codebase structure, dependency analysis, and impact assessment.