Relationship-aware retrieval using graph traversal, entity anchors, community expansion, and hybrid vector plus graph search. Use when chunk similarity alone misses paths, entities, or subsystem context.
npx claudepluginhub v1truv1us/ai-eng-system --plugin ai-eng-learningThis skill uses the workspace's default tool permissions.
Use graph-native retrieval when the answer depends on relationships, not just similar text. Graph RAG works well for entity-heavy systems, architecture questions, causal chains, and multi-hop queries that plain vector retrieval often misses.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Use graph-native retrieval when the answer depends on relationships, not just similar text. Graph RAG works well for entity-heavy systems, architecture questions, causal chains, and multi-hop queries that plain vector retrieval often misses.
Resolve the question to known entities first, then retrieve around them.
Expand one or two hops across relevant relations only.
Find the path between two anchors when the question is about connection or causality.
Pull the subsystem or cluster around the anchor when local context matters more than one edge.
Use vector search to find candidate anchors, then use the graph to expand and explain.
Graph RAG is a fit when the question is one of these:
If the question is simple lookup, plain retrieval may be enough.
Identify entities, files, symbols, tables, or services named in the question.
If anchor resolution is fuzzy:
Expand only across relations that matter to the question:
Bound the retrieval:
Assemble context as structured evidence, not a raw graph dump:
## Anchors
- AuthController
- SessionToken
## Relevant Path
AuthController -> AuthService -> TokenStore -> sessions table
## Supporting Evidence
- src/auth/controller.ts:42
- src/auth/service.ts:88
- src/data/token-store.ts:21
- docs/decisions/2026-01-15-auth.md:12
The answer should explain:
| Question Shape | Retrieval Strategy |
|---|---|
| direct lookup | vector or keyword only |
| entity + neighbors | anchor + neighborhood expansion |
| how A connects to B | anchor + path retrieval |
| subsystem overview | anchor + community retrieval |
| fuzzy question with named concepts | hybrid vector + graph |
| Rationalization | Reality |
|---|---|
| "Vector search already found the files" | File relevance is not the same as relationship explanation. |
| "Dump the whole graph into the prompt" | Large raw graphs waste context and hide the important path. |
| "More hops is better" | Unbounded traversal quickly turns into noise. |