catalog-sku-matcher-india

What This Skill Does

The catalog-sku-matcher-india skill is a specialized agentic tool designed to tackle the complexities of e-commerce data normalization within the Indian market. It provides a structured, layered matching strategy to resolve product identity across disparate retailer catalogs. By parsing unstructured or semi-structured product listings, the skill reconciles different nomenclature, formatting quirks, and variant definitions—such as distinct RAM, storage, or color configurations—into a unified, normalized SKU format. This is critical for businesses performing cross-platform price monitoring, competitive intelligence, or inventory synchronization where inaccurate matches can lead to flawed business insights or incorrect automated purchasing decisions.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal:

clawhub install openclaw/skills/skills/anugotta/catalog-sku-matcher-india

Post-installation, ensure you have configured your normalization dictionaries in setup.md as outlined in the documentation to ensure the engine understands your specific brand and product taxonomy.

Use Cases

• Price Comparison Engines: Automatically aggregating identical product listings across Flipkart, Amazon India, and Myntra to provide the lowest price to customers.
• Inventory Management: Aligning product databases for dropshippers who need to map supplier IDs to their internal store SKUs.
• Market Analysis: Generating competitive insights by normalizing large-scale product dumps from various Indian e-commerce portals to identify pricing trends by exact product variant.

Example Prompts

1. "Match the listings in the 'mobiles-input.csv' file against the master catalog in 'master-inventory.json' and output a report of high-confidence matches."
2. "Review the low-confidence queue for the latest batch of electronics and identify which products were rejected due to storage variant mismatches."
3. "Normalize the product titles for the current household appliance dataset using the India-specific brand dictionary, ensuring all bundle offers are flagged for manual review."

Tips & Limitations

This skill uses a rigorous guardrail system to prevent false matches, specifically prohibiting the alignment of different storage or RAM variants as the same SKU. Because it relies heavily on local dictionaries, ensure your normalization tables are updated frequently to account for new product releases. Always perform a test run using the validation checklist before deploying to large-scale production datasets. Note that while the tool minimizes errors, it is designed as an assistant; all 'medium' confidence matches must be periodically audited by human staff to maintain high data integrity.