CL

clay-migration-deep-dive

A guide for migrating fragmented data enrichment pipelines into a unified Clay-based architecture.

Install

mkdir -p .claude/skills/clay-migration-deep-dive && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6323" && unzip -o skill.zip -d .claude/skills/clay-migration-deep-dive && rm skill.zip

Installs to .claude/skills/clay-migration-deep-dive

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Migrate to Clay from other enrichment tools or consolidate multiple
67 charsno explicit “when” trigger
Advanced

Key capabilities

  • Audit current enrichment tool subscriptions
  • Map legacy enrichment fields to Clay columns
  • Perform parallel data quality validation
  • Configure waterfall enrichment workflows
  • Consolidate multiple data providers

How it works

It uses a strangler fig pattern to audit existing enrichment stacks, map fields to Clay columns, and gradually shift traffic from legacy providers to Clay.

Inputs & outputs

You give it
Legacy enrichment data and provider API keys
You get back
Clay-based enrichment pipeline

When to use clay-migration-deep-dive

  • Migrate existing enrichment scripts to Clay
  • Consolidate multiple data providers into Clay
  • Audit current enrichment tool subscriptions
  • Perform a full GTM stack migration

About this skill

Clay Migration Deep Dive

Overview

Comprehensive guide for migrating from standalone enrichment tools (ZoomInfo, Apollo, Clearbit, Lusha) to Clay, or consolidating multiple tools into a single Clay-based pipeline. Clay replaces the need for individual provider subscriptions by aggregating 150+ providers into waterfall enrichment workflows.

Prerequisites

  • Current enrichment tool subscription(s) with data export capability
  • Clay account on Growth or Enterprise plan
  • Understanding of current enrichment volume and costs
  • CRM with existing enriched data

Migration Types

MigrationComplexityDurationRisk
Single provider -> ClayLow1-2 weeksLow
Multiple providers -> ClayMedium2-4 weeksMedium
Custom scripts -> ClayMedium2-4 weeksMedium
Full GTM stack migrationHigh1-2 monthsHigh

Instructions

Step 1: Audit Current Enrichment Stack (Week 1)

// migration/audit.ts — document your current enrichment setup
interface EnrichmentAudit {
  provider: string;
  monthlyVolume: number;
  monthlyCoost: number;
  dataFields: string[];
  hitRate: number;           // % of lookups that return data
  integrationMethod: string; // API, CSV, Zapier, native CRM
  canExportHistory: boolean;
}

const currentStack: EnrichmentAudit[] = [
  {
    provider: 'ZoomInfo',
    monthlyVolume: 5000,
    monthlyCoost: 15000,  // ZoomInfo is expensive
    dataFields: ['email', 'phone', 'title', 'company', 'revenue'],
    hitRate: 75,
    integrationMethod: 'API + Salesforce native',
    canExportHistory: true,
  },
  {
    provider: 'Apollo.io',
    monthlyVolume: 3000,
    monthlyCoost: 400,
    dataFields: ['email', 'title', 'company', 'linkedin'],
    hitRate: 65,
    integrationMethod: 'API',
    canExportHistory: true,
  },
  {
    provider: 'Custom Python scripts',
    monthlyVolume: 1000,
    monthlyCoost: 0,  // Just developer time
    dataFields: ['email', 'company_data'],
    hitRate: 40,
    integrationMethod: 'Cron job + DB',
    canExportHistory: true,
  },
];

function generateMigrationReport(stack: EnrichmentAudit[]): void {
  const totalCost = stack.reduce((s, p) => s + p.monthlyCoost, 0);
  const totalVolume = stack.reduce((s, p) => s + p.monthlyVolume, 0);
  console.log(`Current stack: ${stack.length} providers`);
  console.log(`Total monthly cost: $${totalCost}`);
  console.log(`Total monthly volume: ${totalVolume} lookups`);
  console.log(`Average hit rate: ${(stack.reduce((s, p) => s + p.hitRate, 0) / stack.length).toFixed(0)}%`);
  console.log(`\nClay equivalent (Growth plan): $495/mo + provider API keys`);
}

Step 2: Map Fields to Clay Columns (Week 1)

# migration/field-mapping.yaml
field_mapping:
  # Your current field -> Clay enrichment column
  email: "Work Email (Waterfall: Apollo > Hunter)"
  phone: "Phone Number (Apollo)"
  job_title: "Job Title (Apollo/PDL)"
  company_name: "Company Name (Clearbit)"
  company_revenue: "Revenue (Clearbit)"
  employee_count: "Employee Count (Clearbit)"
  industry: "Industry (Clearbit)"
  tech_stack: "Technologies (BuiltWith via Claygent)"
  linkedin: "LinkedIn URL (Apollo)"

  # Fields that don't have direct Clay equivalents:
  intent_signals: "Use Clay's Web Intent feature (Growth plan)"
  custom_research: "Claygent AI research column"

Step 3: Parallel Run (Week 2-3)

Run Clay alongside your existing tools to validate data quality:

// migration/parallel-run.ts
interface ComparisonResult {
  field: string;
  oldValue: string | null;
  clayValue: string | null;
  match: boolean;
}

async function compareEnrichment(
  email: string,
  oldData: Record<string, unknown>,
  clayData: Record<string, unknown>,
): Promise<ComparisonResult[]> {
  const fieldsToCompare = ['company_name', 'job_title', 'employee_count', 'industry'];

  return fieldsToCompare.map(field => ({
    field,
    oldValue: (oldData[field] as string) || null,
    clayValue: (clayData[field] as string) || null,
    match: String(oldData[field]).toLowerCase() === String(clayData[field]).toLowerCase(),
  }));
}

// Run on a sample of 500 contacts from your CRM
// Compare Clay's enrichment with your current provider's data
// Target: Clay should match or exceed current hit rates

Step 4: Configure Clay Table to Replace Current Stack (Week 3)

# Clay table configuration to replace multi-provider stack
replacement_table:
  name: "Outbound Leads (Migrated)"
  sources:
    - webhook (replaces API calls to ZoomInfo/Apollo)
    - CRM import (replaces native CRM enrichment)
    - CSV upload (replaces manual processes)

  enrichment_columns:
    1_company_lookup:
      provider: clearbit
      replaces: "ZoomInfo company data"
      own_api_key: true  # 0 Clay credits

    2_email_waterfall:
      providers: [apollo, hunter]
      replaces: "ZoomInfo email + Apollo email"
      own_api_keys: true

    3_person_enrichment:
      provider: apollo
      replaces: "Apollo person data"
      own_api_key: true

    4_ai_research:
      type: claygent
      replaces: "Custom Python research scripts"
      prompt: "Research {{Company Name}} for recent news and tech stack"

    5_icp_scoring:
      type: formula
      replaces: "Custom scoring in Python/SQL"

Step 5: Gradual Traffic Migration (Week 4)

// migration/traffic-shift.ts
interface MigrationConfig {
  clayPercentage: number;   // 0-100, gradually increase
  legacyEnabled: boolean;
}

class MigrationRouter {
  constructor(private config: MigrationConfig) {}

  shouldUseClay(): boolean {
    return Math.random() * 100 < this.config.clayPercentage;
  }

  async enrichLead(lead: Record<string, unknown>): Promise<Record<string, unknown>> {
    if (this.shouldUseClay()) {
      return this.enrichViaClay(lead);
    }
    return this.enrichViaLegacy(lead);
  }
}

// Migration schedule:
// Week 4, Day 1: 10% to Clay, 90% legacy
// Week 4, Day 3: 25% to Clay, 75% legacy
// Week 4, Day 5: 50% to Clay, 50% legacy
// Week 5, Day 1: 100% to Clay, legacy disabled

Step 6: Cancel Legacy Subscriptions

After full migration and 2-week monitoring:

  • Verify Clay hit rates match or exceed legacy providers
  • Confirm CRM sync working correctly
  • Export final data from legacy tools as backup
  • Cancel ZoomInfo/Apollo/Clearbit subscriptions
  • Remove legacy API keys from application code
  • Document Clay configuration for team

Error Handling

IssueCauseSolution
Lower hit rate on ClayDifferent provider coverageAdjust waterfall order, add providers
Missing fieldsClay uses different field namesUpdate field mapping
Data format mismatchDifferent date/number formatsAdd transformation in webhook handler
CRM duplicates during parallelBoth systems writingDeduplicate on email in CRM

Resources

Next Steps

For advanced troubleshooting, see clay-advanced-troubleshooting.

Prerequisites

Current enrichment tool subscriptionClay account on Growth or Enterprise plan

How it compares

It provides a structured migration path for consolidating fragmented enrichment workflows into a single waterfall-based pipeline.

Compared to similar skills

clay-migration-deep-dive side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
clay-migration-deep-dive (this skill)127dReviewAdvanced
json-render-core32moNo flagsAdvanced
azure-ai-document-intelligence-ts03moReviewIntermediate
openevidence-core-workflow-b027dReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

json-render-core

vercel-labs

Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.

323

azure-ai-document-intelligence-ts

microsoft

Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.

02

openevidence-core-workflow-b

jeremylongshore

Execute OpenEvidence DeepConsult workflow for comprehensive medical research. Use when implementing deep research synthesis, complex clinical questions, or when physicians need extensive literature review. Trigger with phrases like "openevidence deepconsult", "deep research", "comprehensive evidence", "literature synthesis".

00

langsmith-evaluator

dhar174

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run v

00

logging-best-practices

neondatabase

Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics

01

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

Search skills

Search the agent skills registry