Kg Traverse

This is a pathfinding traversal tool for exploring knowledge graphs from a starting entity. It recursively expands through causal edges up to a configurable depth (default 3), scores each path by relevance using edge weights and keyword similarity, then prunes anything below 0.3 and ranks what's left. You get the top 10 paths with their entity chains, relation types, and a synthesized summary. Use it when you need to trace dependencies, run impact analysis, or map out how entities connect in your codebase. The scoring relies on pattern search for keyword matches since semantic routing is disabled in current AgentDB builds, which works fine for entity and relation lookups but isn't doing deep semantic similarity.

skills.sh installs: 728
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

KG Traverse

Perform pathfinder graph traversal starting from a seed entity. Expands outward through the graph's edges, scores paths by relevance, and prunes low-scoring branches.

When to use

When you need to explore the knowledge graph starting from a specific entity -- finding what depends on it, what it depends on, or discovering indirect relationships. Useful for impact analysis, dependency chains, and understanding code structure.