---
name: lead-enrichment-normalization
description: Cleans and enriches a lead list by standardising identities, resolving duplicates, and filling business context from available records and public sources. Use for lead enrichment, contact data cleanup, prospect list preparation, firmographic enrichment, or CRM import review.
license: Apache-2.0
metadata:
  adlass.categories: "sales-crm/lead-research, sales-crm/lead-qualification"
  adlass.industries: ""
  adlass.tags: "lead-enrichment, data-cleanup, deduplication, firmographics, crm, prospect-list"
  adlass.adaptation: "mapping"
  adlass.source: "n8n:1296, n8n:2318, n8n:3616"
  adlass.version: "1"
---

# Lead enrichment normalization

## Purpose

Turn an inconsistent lead list into a usable, traceable prospect dataset. Standardise names and contact fields, resolve likely duplicates, add business context, and expose records that need review instead of fabricating values.

## Scope

Lead and account identity, company domain, role, location, firmographic fields, source, confidence, and enrichment status.

**Excluded:** sending messages, creating CRM records, purchasing data, and unverifiable personal attributes.

## Data basis

- Lead table supplied in the skill scope.
- Existing account and contact tables for matching.
- Public company sources when web search is enabled.
- Field mapping and allowed value lists in scope.

## Result

A normalised lead sheet, a duplicate-review sheet, and an enrichment exceptions report.

## Quality criteria

- Original values remain available beside normalised values.
- Each enrichment has a source and confidence.
- No two rows are merged without a match rationale.
- Invalid or missing values are flagged, not silently replaced.
- Row counts reconcile to the input population.

## Instructions

Preserve provenance for every changed field. Prefer exact domain and email matches, then conservative combinations of company name, person name, and role. Use standardised casing and the mapping in scope. Do not infer an email address or seniority from a name alone. Keep unresolved records in the output with an explicit reason.

## Adapt before use
Keep a clear audit trail throughout the run. Use the source wording and field values that support each material conclusion, and retain uncertainty when the evidence does not decide the issue. Separate a missing record from a negative result and a contradictory record from an exception. Prefer a short, prioritised result over unsupported completeness. Check that counts, identifiers, dates, and labels agree across the written result and the structured output. When a rule, source, or mapping is unavailable, name the limitation and explain how it affects interpretation. Do not silently infer ownership, approval, timing, or business intent.

- Map source columns to the target lead schema.
- Define allowed values, country and language conventions.
- Set acceptable enrichment sources and confidence labels.