Identity Graph Operator

Resolve records against a shared identity graph using blocking, scoring, and clustering.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/hiktan44/deer-flow --skill identity-graph-operator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Identity Graph Operator
Source: https://github.com/hiktan44/deer-flow/tree/main/skills/public/identity-graph-operator
Command: npx skills add https://github.com/hiktan44/deer-flow --skill identity-graph-operator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures that multiple AI agents in a system consistently identify and refer to the same real-world entities (people, companies, products), preventing data duplication and conflicting actions.

Core Features & Use Cases

  • Deterministic Identity Resolution: Guarantees that the same entity always resolves to the same canonical ID across all agents.
  • Evidence-Based Matching: Uses configurable rules and scoring to match entities, providing clear reasoning for each decision.
  • Merge & Split Coordination: Facilitates safe merging or splitting of entities, with proposals for review when confidence is not absolute.
  • Use Case: In a sales and support system, when the sales agent creates a new lead and the support agent later encounters the same person, this Skill ensures both agents refer to the same customer record, preventing duplicate outreach or service issues.

Quick Start

Use the Identity Graph Operator skill to resolve the provided customer record against the shared identity graph.

Frequently Asked Questions about Identity Graph Operator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ensure consistent entity resolution across multiple AI agents?

Consistent entity resolution across multiple AI agents is achieved by operating a shared identity graph that matches records against a canonical identity layer. This ensures all agents deterministically resolve the same entity to an identical canonical ID, preventing conflicting actions and data duplication.

What is the best way to handle fuzzy matching and data deduplication in multi-agent systems?

Fuzzy matching and deduplication are handled by a robust matching engine that evaluates per-field evidence. It proposes safe merges or splits when confidence is not absolute, maintaining graph integrity while providing an audit trail for data governance.

How does an identity graph manage merge and split proposals for entity matching?

An identity graph manages entity matching by coordinating safe merges and splits. When match confidence is not absolute, it generates proposals for review, ensuring data governance and graph integrity through evidence-based scoring and an audit trail.

Do I need tenant isolation to run a shared identity graph for entity resolution?

Yes, tenant isolation is required to run a shared identity graph for entity resolution. The system explicitly relies on tenant isolation to maintain deterministic matching, per-field evidence scoring, and graph integrity across multiple agents securely.