Identity Graph Operator

Resolve entity records to canonical entity_ids with evidence-based matching.

110|18|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/TravisLeeeeee/awesome-openclaw-personas --skill identity-graph-operator-travisleeeeee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Identity Graph Operator
Source: https://github.com/TravisLeeeeee/awesome-openclaw-personas/tree/main/personas/specialized/identity-graph-operator
Command: npx skills add https://github.com/TravisLeeeeee/awesome-openclaw-personas --skill identity-graph-operator-travisleeeeee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents duplicate and conflicting records by deterministically resolving incoming entity records to the correct canonical entity_id using evidence-based, field-level matching.

Core Features & Use Cases

  • Deterministic identity resolution: Produces the same canonical entity_id for the same real-world entity even across concurrent writes and multi-agent access.
  • Evidence-based fuzzy matching: Uses blocking plus field-level scoring (including nickname normalization and E.164 phone formatting) and explains results with confidence and per-field evidence.
  • Merge governance with audit trails: Proposes merges (rather than directly mutating) with per-field scores and reasoning to support multi-agent review, conflict handling, and event-history integrity.
  • Tenant isolation & privacy safety: Scopes all queries per tenant and masks PII by default, revealing it only when explicitly authorized.

Quick Start

Copy the identity-graph-operator persona into your OpenClaw workspace, then ask it to resolve a new customer record into a canonical entity_id using blocking, normalization, scoring, and evidence-backed merge proposals when needed.

Frequently Asked Questions about Identity Graph Operator

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

FAQPage Schema
How do I resolve duplicate customer records to a single canonical ID?

Identity resolution maps duplicate customer records to deterministic canonical entity_ids by using blocking-based candidate retrieval and field-level scoring to eliminate conflicting multi-agent decisions.

How does fuzzy entity matching handle different phone and name formats?

Fuzzy entity matching normalizes inputs using E.164 phone formatting and nickname normalization, then applies field-level scoring with confidence thresholds to produce evidence-backed match results.

What is the best way to prevent conflicting merges during concurrent identity reconciliation?

Identity reconciliation prevents conflicts by proposing merges with audit trails and optimistic locking rather than directly mutating records, ensuring event-history integrity during concurrent writes.

Can I use this identity resolution approach for multi-tenant systems with PII data?

Yes, identity resolution supports multi-tenant systems by scoping all queries per tenant and masking PII by default, revealing sensitive data only when explicitly authorized.

When should I use evidence-based merge proposals instead of direct record mutation?

Evidence-based merge proposals are necessary for multi-agent review and conflict handling, providing per-field scores and reasoning to maintain audit trails and prevent unauthorized data mutation.

Does entity matching across heterogeneous sources require blocking-based candidate retrieval?

Yes, entity matching across heterogeneous sources requires blocking-based candidate retrieval to efficiently narrow potential matches before applying field-level scoring and confidence thresholds.