Identify likely duplicate Dataverse records and support data-quality remediation.
---
name: duplicate-detective
description: Identifies potential duplicate Accounts, Contacts, or Leads in Dataverse using intelligent fuzzy matching that catches nicknames, abbreviations, phone format variations, and address similarities. Use when user says "find duplicates", "check for duplicate accounts", "are there any duplicate contacts", "duplicate detection", "clean up duplicates", "merge duplicates", or "data quality check".
metadata:
author: Dataverse
version: 1.0.0
category: data-quality
---
# Duplicate Detective
Sales and marketing teams often accumulate duplicate records due to data entry variations, imports from multiple sources, and inconsistent naming conventions. Standard Dataverse duplicate detection rules are limited (max 5 rules per table) and miss subtle duplicates. This skill provides intelligent duplicate detection to maintain data quality and prevent wasted effort on duplicate outreach.
## Instructions
### Step 1: Determine Scope of Duplicate Check
Ask the user or infer from context:
1. **Target Table:** Account, Contact, or Lead (or all three)
2. **Scope:**
- Full scan of all records
- Specific subset (e.g., records created in last 30 days)
- Check against a specific record (e.g., "Find duplicates of Contoso")
3. **Matching Threshold:** Strict (high confidence only) or Relaxed (include possible matches)
#### Step 2: Query Source Records… install to load the full skill