Back to library

Wholesale product data enrichment

Turns raw wholesale item data and supplier documents into normalized, catalog-ready product records with descriptions, attributes, units, and an explicit gap list. Use for distributor catalogs, item master cleanup, supplier onboarding, and product-information maintenance.

by adlass TemplatesVersion 1Uses adlass toolsUniversal

Published Aug 21, 2026 · Updated Aug 26, 2026

Helpful · 0View raw SKILL.md

Requirements

Add the item-master schema, category required fields, and unit dictionary. Define permitted manufacturer sources and web-research fields. Set duplicate, conflict, and confidence rules. Specify which product claims require specialist approval.

Skill document

The full SKILL.md your agent reads and follows.

Wholesale product data enrichment

Purpose

Improve item-master completeness and consistency while preserving the evidence and uncertainty behind each enriched field.

Scope

Wholesale product records, supplier data sheets, packaging information, and approved public manufacturer facts. Excluded: product certification, legal label approval, and automatic publication.

Data basis

  • Raw item records, supplier documents, catalog schema, existing item master, manufacturer sources, and category rules.
  • The fixed records, tables, or folders in the skill scope that hold the relevant history or schema.

Result

An enriched item sheet, description document, and unresolved-field list with source and confidence.

Quality criteria

  • Required fields are evaluated by product category.
  • Every populated non-derived field has a source or transformation basis.
  • Units, pack sizes, dimensions, and identifiers use the canonical schema.
  • Descriptions do not add unsupported claims.
  • Duplicates, conflicting supplier values, and missing fields are separately flagged.

Instructions

Map records to the existing item identifier before creating a new one. Preserve supplier wording where it is factual, then normalize terms and units into the schema. Use public research only for fields explicitly allowed by the company and cite the source and retrieval date. Never infer hazardous, regulatory, or performance attributes from marketing language. Keep confidence visible.

Adapt before use

Keep the source trail close to every conclusion and preserve the difference between a source fact, a calculated value, an assumption, and a recommendation. Use stable identifiers across the document and sheet so a reviewer can move from a summary statement to the underlying row and source. Prefer a complete, transparent partial result over a confident answer built on missing evidence.

  • Add the item-master schema, category required fields, and unit dictionary.
  • Define permitted manufacturer sources and web-research fields.
  • Set duplicate, conflict, and confidence rules.
  • Specify which product claims require specialist approval.

Related skills

  • Sync a spreadsheet into a record type

    Loads an uploaded spreadsheet into a record type of the workspace with the bulk sync tool, previewing the changes before writing. Use for master data imports, periodic refreshes of a table, or migrating a list from Excel into records.

  • Anomaly variance explanation

    Explains material changes in a business metric by decomposing period, volume, price, mix, and data-quality effects, then ranks evidence-backed causes in a cited analysis sheet and management memo. Use for KPI variance reviews, monthly business reviews, forecast misses, anomaly investigation, and driver analysis.

  • Data migration field mapping

    Maps source-system fields to a target data model for migration, documenting transformations, requiredness, value translations, identifiers, validation rules, and unresolved collisions. Use for CRM migrations, ERP imports, warehouse loads, application replacement, and controlled spreadsheet-to-system field mapping.

  • Dataset Quality Assessment

    Dataset Quality Assessment converts table schema, column types, null policy, primary and foreign keys into profiling report and defect register with field metrics, duplicate groups, invalid values, orphan keys, temporal gaps, and severity, with cited evidence, explicit rules, and unresolved exceptions. Use for dataset quality assessment, recurring review, and decision preparation.