kg-traverse
Pathfinder traversal of the knowledge graph starting from a seed entity
How do I install this agent skill?
npx skills add https://github.com/ruvnet/ruflo --skill kg-traverseIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill is a technical procedure for performing knowledge graph traversals using specialized database tools. It contains references to an external CLI package and identifies a potential surface for indirect prompt injection from the graph data it processes.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
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.
Steps
- Seed -- call
mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-recallto look up the target entity by name (one word is the most reliable query: the recall matches the whole query as a substring). Graph node ids are domain-prefixed, for exampleentity:router-account. - Expand -- call
mcp__plugin_ruflo-core_ruflo__agentdb_graph-querywith{ nodeId: "entity:NAME", mode: "k-hop", depth: N }(default depth 3, the SQL path applies at most 3 and reportsappliedDepthandtruncated; addrelationto filter by relation type).agentdb_causal-edgeonly records an edge, never use it to read one. - Score and rank -- call
mcp__plugin_ruflo-core_ruflo__agentdb_graph-pathfinderwith{ seedNodeId: "entity:NAME", query: "<what the user wants to know>", depth: N, threshold: 0.3, topK: 10 }. It expands from the seed, scores each path by cumulative relevance, drops paths under the threshold and returns the top paths. If it returns nothing useful, score the k-hop neighbours yourself withmcp__plugin_ruflo-core_ruflo__agentdb_pattern-searchon entity names and relation types (thesemanticRoutercontroller isenabled: falsein current AgentDB builds; see ruvnet/ruflo#2049). - Synthesize -- write the summary yourself from the returned paths. Do not call
agentdb_context-synthesize: it summarizes validated task episodes and answersno-eligible-episodesfor entity records written bykg-extract. - Report -- display the top 10 paths with: path (entity chain), relation types, cumulative score, and your summary.
When the graph cannot be read
With CLAUDE_FLOW_ENCRYPT_AT_REST=1 the graph read tools answer graph_edges DB is encrypted at rest (RFE1) (#2889, #4135): edges recorded by kg-extract are stored but cannot be read back yet. Say so in the report. Your data is intact: do not run memory init. Fall back to the entity records only (agentdb_hierarchical-recall) and tell the user that relations are unavailable. An agentdb_causal-edge result with readable: false already warns about this at write time.
CLI alternative
npx @claude-flow/cli@latest memory search --query "relations for ENTITY_NAME" --namespace knowledge-graph
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/ruvnet/ruflo/kg-traverse">View kg-traverse on skillZs</a>