What problem does it solve?
Flat similarity search cannot tell you that one document overrules, distinguishes, or relies on another. This Skill builds a typed reference graph over an ingested corpus so you can trace arguments and authority relationships across documents instead of just fuzzy-matching them.
Core Features & Use Cases
- Typed edge extraction: Detects inter-document references mechanically, then uses model judgment to classify each edge as overrules, distinguishes, relies_on, extends, refutes, supersedes, or cites.
- Native graph storage: Writes edges via
gbrain link with link_source=citation-graph provenance, making them queryable with gbrain graph-query --type and bulk-removable without touching other writers' edges.
- Verified runs: Requires a successful
graph-query walk from a hub document before reporting success, and is idempotent so re-runs skip duplicates.
- Use Case: Ingest a case-law corpus as a gbrain source, run the pipeline, then ask
gbrain graph-query doc-a --type overrules --direction in to learn that doc A was overruled by doc C — something vector search alone cannot answer.
Quick Start
Build a typed citation graph over my ingested case-law source so I can see which documents overrule or rely on each other.
