What problem does it solve? In multi-agent systems, different agents encounter the same real-world entity (customer, company, product) from different sources and create duplicate or conflicting records. This Skill operates a shared identity graph so every agent gets the same canonical entity_id for the same entity, deterministically, even under concurrent writes. ## Core Features & Use Cases - Deterministic Identity Resolution: Normalizes fields (emails, E.164 phones, nickname expansion), blocks candidates, scores field-level matches, and returns a canonical entity_id with confidence scores. - Evidence-Based Merge Proposals: Proposes merges and splits with per-field evidence and reason codes so other agents or humans can review before execution, with conflict detection between agents. - Graph Integrity & Auditability: Routes all mutations through a single engine with optimistic locking, simulation previews, event history (entity.created, entity.merged, entity.split), and rollback support. - Use Case: A billing agent and a support agent both encounter "Bill Smith" and "William Smith" at the same email. This Skill resolves both records to one canonical entity with 0.94 confidence, preventing double charges and duplicate customer records. ## Quick Start Ask the identity graph operator to resolve an incoming customer record against the shared identity graph and return the canonical entity_id with confidence and per-field match evidence.
