playbook-lookalikes

Builds lookalike company lists by mining case-study attributes into database filters.

Updated May 28, 2025
One-click install
npx skills add https://github.com/meloShaya/insteltech --skill playbook-lookalikes-meloshaya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playbook-lookalikes
Source: https://github.com/meloShaya/insteltech/tree/main/crm/library/skills/playbooks/playbook-lookalikes
Command: npx skills add https://github.com/meloShaya/insteltech --skill playbook-lookalikes-meloshaya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Pasting a case-study company into a lookalike engine returns agencies, publishers, and blogs instead of real peers (measured 40% usable). This Skill decomposes why a case study resonates into testable attributes, converts them into database filters, and intersects them with a lookalike anchor to produce a precise prospect list. ## Core Features & Use Cases - Attribute decomposition: A locked prompt turns one case study into a JSON attribute card with resonance reasons, industry enum candidates, include/exclude keywords, headcount, geography, and a generic descriptor for cold copy. - Industry-enum bake-off: A free procedure that tests candidate industry filters against page-1 results, because databases often tag a software vendor by who it sells to. - Per-row judge and liveness check: A second prompt gates each company against every resonance reason, and a homepage liveness pass rejects dead or parked companies. - Use Case: A client has one flagship customer story. Run the decomposer once, bake off the industry enums, intersect filters with the lookalike anchor, then widen with the judge and snowball rounds until the segment reaches campaign volume. ## Quick Start Ask the AI to build a lookalike list from your best customer's case study by decomposing it into filterable attributes and judging each candidate company against them.

Frequently Asked Questions about playbook-lookalikes

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

FAQPage Schema
How do I build a lookalike list from a customer case study?

Decompose the case study into 2 to 5 testable resonance attributes, express each as a database filter, and intersect those filters with a lookalike anchor on the case-study company. Widen by dropping the anchor and judging every row with a model prompt.

Why does a lookalike engine return agencies and blogs instead of real peers?

Vector lookalikes match on surface topics like marketing, so they return agencies, publishers, and blogs alongside software vendors, measuring about 40% usable. Mining the attributes behind the story and intersecting them with the anchor fixes this.

Should I filter on the industry tag the database assigns to my case-study company?

No, treat it as a candidate only. Databases often tag a software vendor by who it sells to, so run the industry-enum bake-off: test each candidate enum with a page-1 search and keep the one whose results are the right company type.

Can I name the case-study company's brand in cold email copy?

Only with explicit client approval for a published case study. By default use a generic descriptor like a marketing platform about your size, which carries the same recognition without creating a permissions problem.

Why do dead companies end up in my qualified list?

Company databases keep descriptions for businesses that no longer trade, and a description-only judge qualifies them confidently. Run a liveness pass that fetches each homepage, classifies dead, parked, or live, and re-judges live sites on current content.

When should I not use case-study lookalike list building?

Skip it when you have no standout customer to anchor on and are building a market from a broad ICP sentence, or when you want to reference the prospect's own case studies, which is the opposite direction handled by a different playbook.