personalization-subagent-pattern

Orchestrate parallel Claude Code Task sub-agents for per-lead personalization with an approval loop.

601|215|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/growthenginenowoslawski/coldoutboundskills --skill personalization-subagent-pattern
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: personalization-subagent-pattern
Source: https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/personalization-subagent-pattern
Command: npx skills add https://github.com/growthenginenowoslawski/coldoutboundskills --skill personalization-subagent-pattern

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents. Shows the user 1 sample personalization, collects feedback, runs 10 more, approves, runs 10 more — stops when 2 consecutive rounds have zero edits, then scales to the full list. ALWAYS uses Claude Code Task tool sub-agents — never an external Anthropic/OpenAI API key. Use when any skill needs per-lead custom variables (situation lines, value lines, CTAs).

Core Features & Use Cases

  • Parallel fan-out using Claude Code Task tool to run per-lead personalization tasks.
  • Incremental tuning loop with rounds for feedback, scaling from a sample to full batch.
  • Self-contained workflow that avoids external API keys and supports scaling across 50+ leads.

Quick Start

Run the pattern to orchestrate parallel lead personalization with an approval loop.

Frequently Asked Questions about personalization-subagent-pattern

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate lead personalization for a large batch of prospects?

Parallel lead personalization uses Claude Code Task sub-agents to fan out per-lead customization tasks concurrently. An approval loop shows a sample, collects feedback, and scales incrementally to the full batch once consecutive rounds require zero edits.

How does the approval loop work for scaling campaign personalization?

The approval loop shows 1 sample personalization, collects feedback, runs 10 more, and repeats. Scaling to the full list happens automatically when 2 consecutive rounds have zero edits, ensuring quality control before full batch execution.

Can I run per-lead personalization without an external API key?

Yes, this pattern uses Claude Code Task tool sub-agents exclusively and never requires an external Anthropic or OpenAI API key. Built-in guardrails prevent API key exposure during the parallel processing workflow.

What is the minimum number of leads needed to use parallel personalization?

This parallel personalization pattern applies when 50 or more leads require per-lead customization and iterative feedback. It scales from a small sample to a full batch using the incremental approval loop.

How do I add custom variables like situation lines and CTAs to lead outreach?

You can generate per-lead custom variables such as situation lines, value lines, and CTAs by running parallel Task sub-agents. The approval loop iteratively tunes these variables based on your feedback before scaling.