Can I use this for international B2B data?

Yes, the skill includes guidance on selecting providers based on their geographic strengths and weaknesses, helping you navigate coverage gaps in different regions.

How does this skill help reduce data costs?

It implements credit optimization strategies like smart caching, multi-tier cost waterfalls, and batch processing to ensure you only pay for high-value enrichment when necessary.

Which providers does this skill support?

It provides frameworks for over 150 sources, including Apollo, ZoomInfo, Hunter, Clearbit, BuiltWith, and specialized industry providers like PitchBook, Crunchbase, or Store Leads.

What is 'Waterfall Logic' in this context?

Waterfall logic is a sequential process where the system attempts to find data using cheaper or more likely sources first, only moving to premium providers if the initial attempts fail, maximizing hit rates at the lowest cost.

Data Sourcing & Provider Optimization

Name: Data Sourcing & Provider Optimization
Author: Microck

byMicrock

•

マーケティングオートメーション

Optimizes B2B data enrichment by selecting, routing, and managing 150+ intelligence providers to maximize data quality and minimize credit costs.

概要

This skill transforms Claude into a RevOps and GTM data expert, capable of designing sophisticated enrichment workflows across 150+ sources. It provides structured frameworks for selecting the best providers for email discovery, company intelligence, and technographics while implementing cost-saving strategies like waterfall routing and caching logic. Whether building a lead generation pipeline or auditing credit consumption, this skill ensures data engineering and GTM teams achieve maximum hit rates with predictable spending through advanced multi-source orchestration.

主な機能

Intelligent waterfall routing for 150+ data providers
Cost-optimized credit usage and tier management
Industry-specific provider selection (SaaS, Healthcare, E-commerce)
Quality scoring framework for data validation
Progressive and hybrid enrichment implementation patterns
81 GitHub stars

ユースケース

Building automated GTM enrichment pipelines for RevOps teams
Optimizing API credit consumption for large-scale data sourcing
Designing multi-source email and phone discovery sequences