Why Use This This skill provides specialized capabilities for jeremylongshore's codebase.
Use Cases Developing new features in the jeremylongshore repository Refactoring existing code to follow jeremylongshore standards Understanding and working with jeremylongshore's codebase structure
Install Guide 2 steps 1 2 Install inside Ananke
Click Install Skill, paste the link below, then press Install.
https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/main/plugins/saas-packs/retellai-pack/skills/retellai-migration-deep-dive Skill Snapshot Auto scan of skill assets. Informational only.
Valid SKILL.md Checks against SKILL.md specification
Source & Community
Updated At Jan 6, 2026, 06:42 AM
Skill Stats
SKILL.md 244 Lines
Total Files 1
Total Size 6.9 KB
License MIT
---
name: retellai-migration-deep-dive
description: |
Execute Retell AI major re-architecture and migration strategies with strangler fig pattern.
Use when migrating to or from Retell AI, performing major version upgrades,
or re-platforming existing integrations to Retell AI.
Trigger with phrases like "migrate retellai", "retellai migration",
"switch to retellai", "retellai replatform", "retellai upgrade major".
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(node:*), Bash(kubectl:*)
version: 1.0.0
license: MIT
author: Jeremy Longshore <[email protected] >
---
# Retell AI Migration Deep Dive
## Overview
Comprehensive guide for migrating to or from Retell AI, or major version upgrades.
## Prerequisites
- Current system documentation
- Retell AI SDK installed
- Feature flag infrastructure
- Rollback strategy tested
## Migration Types
| Type | Complexity | Duration | Risk |
|------|-----------|----------|------|
| Fresh install | Low | Days | Low |
| From competitor | Medium | Weeks | Medium |
| Major version | Medium | Weeks | Medium |
| Full replatform | High | Months | High |
## Pre-Migration Assessment
### Step 1: Current State Analysis
```bash
# Document current implementation
find . -name "*.ts" -o -name "*.py" | xargs grep -l "retellai" > retellai-files.txt
# Count integration points
wc -l retellai-files.txt
# Identify dependencies
npm list | grep retellai
pip freeze | grep retellai
```
### Step 2: Data Inventory
```typescript
interface MigrationInventory {
dataTypes: string[];
recordCounts: Record<string, number>;
dependencies: string[];
integrationPoints: string[];
customizations: string[];
}
async function assessRetell AIMigration(): Promise<MigrationInventory> {
return {
dataTypes: await getDataTypes(),
recordCounts: await getRecordCounts(),
dependencies: await analyzeDependencies(),
integrationPoints: await findIntegrationPoints(),
customizations: await documentCustomizations(),
};
}
```
## Migration Strategy: Strangler Fig Pattern
```
Phase 1: Parallel Run
┌─────────────┐ ┌─────────────┐
│ Old │ │ New │
│ System │ ──▶ │ Retell AI │
│ (100%) │ │ (0%) │
└─────────────┘ └─────────────┘
Phase 2: Gradual Shift
┌─────────────┐ ┌─────────────┐
│ Old │ │ New │
│ (50%) │ ──▶ │ (50%) │
└─────────────┘ └─────────────┘
Phase 3: Complete
┌─────────────┐ ┌─────────────┐
│ Old │ │ New │
│ (0%) │ ──▶ │ (100%) │
└─────────────┘ └─────────────┘
```
## Implementation Plan
### Phase 1: Setup (Week 1-2)
```bash
# Install Retell AI SDK
npm install @retellai/sdk
# Configure credentials
cp .env.example .env.retellai
# Edit with new credentials
# Verify connectivity
node -e "require('@retellai/sdk').ping()"
```
### Phase 2: Adapter Layer (Week 3-4)
```typescript
// src/adapters/retellai.ts
interface ServiceAdapter {
create(data: CreateInput): Promise<Resource>;
read(id: string): Promise<Resource>;
update(id: string, data: UpdateInput): Promise<Resource>;
delete(id: string): Promise<void>;
}
class Retell AIAdapter implements ServiceAdapter {
async create(data: CreateInput): Promise<Resource> {
const retellaiData = this.transform(data);
return retellaiClient.create(retellaiData);
}
private transform(data: CreateInput): Retell AIInput {
// Map from old format to Retell AI format
}
}
```
### Phase 3: Data Migration (Week 5-6)
```typescript
async function migrateRetell AIData(): Promise<MigrationResult> {
const batchSize = 100;
let processed = 0;
let errors: MigrationError[] = [];
for await (const batch of oldSystem.iterateBatches(batchSize)) {
try {
const transformed = batch.map(transform);
await retellaiClient.batchCreate(transformed);
processed += batch.length;
} catch (error) {
errors.push({ batch, error });
}
// Progress update
console.log(`Migrated ${processed} records`);
}
return { processed, errors };
}
```
### Phase 4: Traffic Shift (Week 7-8)
```typescript
// Feature flag controlled traffic split
function getServiceAdapter(): ServiceAdapter {
const retellaiPercentage = getFeatureFlag('retellai_migration_percentage');
if (Math.random() * 100 < retellaiPercentage) {
return new Retell AIAdapter();
}
return new LegacyAdapter();
}
```
## Rollback Plan
```bash
# Immediate rollback
kubectl set env deployment/app RETELLAI_ENABLED=false
kubectl rollout restart deployment/app
# Data rollback (if needed)
./scripts/restore-from-backup.sh --date YYYY-MM-DD
# Verify rollback
curl https://app.yourcompany.com/health | jq '.services.retellai'
```
## Post-Migration Validation
```typescript
async function validateRetell AIMigration(): Promise<ValidationReport> {
const checks = [
{ name: 'Data count match', fn: checkDataCounts },
{ name: 'API functionality', fn: checkApiFunctionality },
{ name: 'Performance baseline', fn: checkPerformance },
{ name: 'Error rates', fn: checkErrorRates },
];
const results = await Promise.all(
checks.map(async c => ({ name: c.name, result: await c.fn() }))
);
return { checks: results, passed: results.every(r => r.result.success) };
}
```
## Instructions
### Step 1: Assess Current State
Document existing implementation and data inventory.
### Step 2: Build Adapter Layer
Create abstraction layer for gradual migration.
### Step 3: Migrate Data
Run batch data migration with error handling.
### Step 4: Shift Traffic
Gradually route traffic to new Retell AI integration.
## Output
- Migration assessment complete
- Adapter layer implemented
- Data migrated successfully
- Traffic fully shifted to Retell AI
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Data mismatch | Transform errors | Validate transform logic |
| Performance drop | No caching | Add caching layer |
| Rollback triggered | Errors spiked | Reduce traffic percentage |
| Validation failed | Missing data | Check batch processing |
## Examples
### Quick Migration Status
```typescript
const status = await validateRetell AIMigration();
console.log(`Migration ${status.passed ? 'PASSED' : 'FAILED'}`);
status.checks.forEach(c => console.log(` ${c.name}: ${c.result.success}`));
```
## Resources
- [Strangler Fig Pattern](https://martinfowler.com/bliki/StranglerFigApplication.html)
- [Retell AI Migration Guide](https://docs.retellai.com/migration)
## Flagship+ Skills
For advanced troubleshooting, see `retellai-advanced-troubleshooting`.