skills.rest
growthenginenowoslawski
growthenginenowoslawskiCOMMUNITY
Explore all skills by this author →
GitHub

playbook-company-name-cleaning

Converts raw CRM company-name strings into short spoken-form names for cold email copy.

678|243|Updated Mar 10, 2026
Search Tags:#cold email#data normalization#clay#lead enrichment#email personalization#gpt-4o-mini#company name cleaning
One-click install
npx skills add https://github.com/growthenginenowoslawski/coldoutboundskills --skill playbook-company-name-cleaning
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: playbook-company-name-cleaning
Source: https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/playbooks/playbook-company-name-cleaning
Command: npx skills add https://github.com/growthenginenowoslawski/coldoutboundskills --skill playbook-company-name-cleaning

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Lead databases store company names the way registrars and scrapers found them — with legal suffixes, taglines, dba entities, parenthetical descriptors, and shouting capitals — and pasting those strings into cold email copy reads like an obvious mail merge that kills reply rates.

Core Features & Use Cases

  • Default free normalization: Uses Clay's built-in Normalize Company Name action as the default, with a three-condition test for when to switch on the AI toggle.
  • Locked AI prompt with deterministic guards: A benchmarked gpt-4o-mini prompt (98/100 on a 100-row sample) that strips suffixes, taglines, and second-language duplicates, plus a placeholder blocklist and a substring guard that catches invented words for free.
  • Abstain and downstream gating: Junk strings like "Self-employed" or "N/A" return an empty value that excludes the row from campaigns naming the company, instead of substituting generic copy.
  • Use Case: A list of 5,000 leads contains strings like "AMTC TECH GROUP LLC" and "318, Inc dba Hamiltons Bud and Bloom"; run this playbook to produce "AMTC Tech Group" and "Hamiltons Bud and Bloom" as a sendable {{company_clean}} variable.

Quick Start

Ask Claude to clean the company names in your lead list using the company name cleaning playbook and output a company_clean variable for each row.

Frequently Asked Questions about playbook-company-name-cleaning

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

FAQPage Schema
How do I clean company names for cold email personalization?▼

Start with Clay's free Normalize Company Name action, which handles suffix and casing issues for most lists. If a 20-row sample still shows more than about 2 values you would edit, switch on the AI toggle using the locked gpt-4o-mini prompt to handle taglines, dba entities, and second-language duplicates.

What is the best way to strip LLC and Inc from company names?▼

Clay's built-in Normalize Company Name action with titleCase enabled strips legal suffixes for free and is the recommended default. A regex stripper scores 89/100 and an AI prompt scores 98/100, but the AI path is only worth enabling when copy prominently names the company.

Should I use gpt-4o-mini or a nano-class model for company name cleaning?▼

Both score 98/100 on the benchmark, but gpt-4o-mini costs about $0.15 per 1,000 rows versus $0.30 for nano. However, mini only abstains correctly on 7 of 10 junk strings, so the deterministic placeholder guard is mandatory when using it.

Why does the AI return empty results for real company names?▼

Empty results with finish_reason=length mean the token cap is too low — a nano-class reasoning model needs max_completion_tokens of 2000, not the 200 used for mini. Retry with a larger cap and never record these rows as abstains.

What happens to rows where the company name is a placeholder like N/A?▼

The playbook abstains with an empty company_clean value, and the downstream gate excludes those rows from any campaign whose copy names the company. Generic substitutes like "your team" are explicitly rejected because they send a worse email to a suspect address.

Related Skills

Explore More Marketing & Sales Skills→
luis2404123luis2404123

lead-generation-pipeline

Scrape Google Maps, directories, and LinkedIn to build CRM-ready lead lists.

Community
Advanced
Othmane-KhadriOthmane-Khadri
277

send-cold-email

Draft multi-touch cold email sequences and send them via Instantly.

Community
Intermediate
growthenginenowoslawskigrowthenginenowoslawski
601

list-quality-scorecard

Scores and pre-validates lead lists for Smartlead upload via markdown report.

Community
Intermediate
refly-airefly-ai
199

hunter

Find and verify professional email addresses using Hunter.io for company domains.

Official
Intermediate