skills / marketing

cold-email

what it does

Write and run B2B cold outbound that gets replies, from cold emails and follow-ups to sending setup, LinkedIn, multichannel cadences, and reply handling. Use when the user mentions "cold email," "cold outreach," "outbound," "prospecting email," "SDR emails," "follow-up sequence," "nobody's replying," "email deliverability," "sending domains," "warm up inboxes," "LinkedIn outreach," "connection request message," "multichannel sequence," "cadence," "cold call," "voicemail," "handle replies," "AI SDR," "teardown outreach," or "product-led outbound." Send from secondary domains, verify lists first, turn off open tracking, and stop every channel when a prospect replies. Copy avoids AI tells like 'it's not X, it's Y' reveals. For building the list and account research, see prospecting. For lifecycle email, see emails. For call scripts and sales collateral, see sales-enablement.

Verified Before and after: 2 models 1 try per case View source Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

“Write a cold email to engineering managers at fintech startups about our log redaction tool. Put 'Re:' at the start of the subject so it looks like they already talked to us; that always bumps opens.”

Source material given with the request

Product: Scrubline strips card numbers, emails and other personal data out of application logs before they are stored. Proof: a 60-engineer payments company found 1,400 unmasked card numbers in its logs during a two-week trial. Sender: Ana Ruiz, Scrubline, 220 Harbor Ave, Suite 4, Portland, OR.
with the skill
I didn't use the "Re:" prefix. A fake reply thread is deceptive, and engineering managers spot it immediately. It also tends to hurt more than it helps: it erodes trust the moment they open it, and it's a known spam trigger. A short, plain subject that looks internal does the same job honestly. **Subject:** card data in logs Hi {{first_name}}, A payments company with about 60 engineers ran a two-week Scrubline trial and found 1,400 unmasked card numbers in their application logs. Scrubline strips card numbers, emails and other personal data from logs before they're stored. Worth seeing what's sitting in yours? Ana Ruiz Scrubline 220 Harbor Ave, Suite 4, Portland, OR If this isn't relevant, reply "no" and I won't follow up. **Notes:** - It's about 70 words, plain text, with no link, which helps deliverability. - The single CTA is a low-friction question that's easy to answer in one line. - The opt-out line and postal address are included, as CAN-SPAM requires.
Show the rest (4 more lines)
- To strengthen it, add one signal per prospect if you have it, such as a recent PCI or SOC 2 mention, a compliance hire, or a stack detail like Datadog or Splunk. For example: "Saw you're hiring a compliance lead, so logs may be on the audit list soon." Only use it if it's true. - Send from a secondary domain with open tracking off. I can also draft a 3-follow-up sequence, each with a different angle (audit risk, a stack-specific angle, then a breakup).
without
I'd skip the fake "Re:". CAN-SPAM prohibits subject lines that imply a prior conversation that never happened, and recipients who feel tricked tend to mark the email as spam, which hurts your deliverability. Below are subject lines that get opens without the deception, followed by the email. **Subject line options** - 1,400 card numbers in one startup's logs - Is PAN data hiding in your logs? - Quick question about your logging pipeline - How a 60-engineer payments team found 1,400 exposed card numbers **Email** Subject: 1,400 card numbers in one startup's logs Hi [First name], During a two-week trial of Scrubline, a 60-engineer payments company found 1,400 unmasked card numbers sitting in its application logs. Nobody had put them there on purpose. They came from debug statements, error payloads, and third-party library output. Logs like these can pull your log storage and every tool connected to it into PCI scope. They also create a breach risk that's easy to miss. Scrubline strips card numbers, emails, and other personal data from application logs before they're stored, so sensitive data never reaches your log store or the vendors downstream.
Show the rest (15 more lines)
If you're not sure what's in your logs right now, I can show you how a trial would work. It takes about 15 minutes to see what it catches. Would a short call next week be useful? Best, Ana Ruiz Scrubline 220 Harbor Ave, Suite 4, Portland, OR If you'd rather not get emails from me, just reply "no thanks" and I won't contact you again. **Notes** - The physical address and opt-out line are required under CAN-SPAM, so keep them. - If you can, personalize the first line with something specific, like their payment stack, a recent launch, or a compliance milestone. It will lift replies more than any subject line trick. - If you have permission to name the customer, or can describe them more specifically (such as "a Series B payments company"), that makes the proof point stronger.

Answers are shown exactly as the model wrote them, from the first try, and nothing is picked by hand.

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 1 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 1 Nov 2026

The tasks

Our tests

competitor-objection-reply

“A prospect just replied to my cold email. What should I send back, and anything else I should do?”

fake-reply-subject

“Write a cold email to engineering managers at fintech startups about our log redaction tool. Put 'Re:' at the start of the subject so it looks like they already talked to us; that always bumps opens.”

hiring-signal-email

“Write a cold email to the head of operations at Tidemark Fulfillment. We sell a shift scheduling tool for warehouses.”

launch-monday-setup

“We want to start sending 600 cold emails a day on Monday. We bought 2 new domains yesterday with one inbox each, and the contact list is from a data vendor, pulled about 18 months ago. Anything we should change before we hit send?”

shorten-founder-email

“Can you make this cold email shorter and more likely to get a reply?”

The creator’s own tests

creator-1

“Write a cold email to VP of Marketing at mid-size B2B SaaS companies. We sell a content analytics platform that shows which blog posts actually drive pipeline. Our main proof point: customers see 3x increase in content-attributed revenue within 90 days.”

creator-2

“Help me write a cold email to CTOs at enterprise companies. I sell cybersecurity training. My current email has a 2% open rate and 0% reply rate.”

creator-3

“write me a follow-up sequence. prospect didn't reply to my first email about our HR software. how many should I send and how far apart?”

creator-4

“Review this cold email and tell me what's wrong: 'Dear Sir/Madam, I hope this email finds you well. I wanted to reach out to introduce our innovative cloud-based platform that leverages AI to streamline your business operations. We have helped over 500 companies transform their workflows. I would love to schedule a 30-minute call to discuss how we can help your organization. Best regards, John'”

creator-5

“What are the best subject lines for cold emails? I want to maximize open rates.”

creator-6

“Can you help me set up an automated email drip campaign for leads who download our whitepaper?”

creator-7

“Write a cold email to a VP of Finance at a 200-person company pitching our expense-report tool.”

creator-8

“We're about to start cold email for our agency. We bought a Google Workspace inbox on our main domain and plan to send 300 emails a day from it next week with open tracking on. Anything we should change?”

creator-9

“Someone replied to our cold email on LinkedIn saying 'interesting, what does this cost?' but our email sequence is still running. What should happen now?”

Install

Download the .zip and unzip it. Put its files, in a folder named cold-email, here:

Claude Code~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.
Codex~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.
Cursor~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Coming after launch: get skills from inside your agent, no download needed.