carte blanche preview

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.

by Corey Haines · Corey Haines, MIT · version 1 · license MIT

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.

“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?”

with the skill
**Yes. Don’t launch with that setup.** A new inbox sending 300 cold emails a day could damage your main domain’s reputation, including delivery of client emails and invoices. Open tracking adds risk without giving you reliable data. Here’s what I’d change: | Your plan | Safer approach | |---|---| | Send from your main domain | Use a clearly branded **secondary domain**, authenticated with SPF, DKIM, and DMARC. Redirect it to your main site. | | Start next week | Give new mailboxes **3–4 weeks to ramp up**, starting with legitimate correspondence and only small cold-email volumes later. Warmup isn’t a guarantee of inbox placement. | | Send 300/day from one inbox | Start cold sends around **5–10/day per mailbox**, then increase cautiously based on bounces, complaints, and inbox placement. Around **20–30/day** is a conservative planning range, not a guaranteed safe limit. Follow-ups count too. | | Keep open tracking on | **Disable open and click tracking.** Privacy features and bots distort opens; tracking can also hurt deliverability. Measure replies, positive replies, and meetings instead. | **Before the first send:** - Verify every address shortly before sending. Aim for **under 1% bounces**; pause and investigate if a campaign exceeds 2%. - Use short, plain-text emails without images, attachments, or first-touch links. - Include a simple opt-out and your postal address. Check the outreach rules that apply where your recipients are located. - Suppress opt-outs immediately, and stop automated follow-ups whenever someone replies. - Test inbox placement before launch and monitor it weekly. - If you bought the mailbox through a reseller, confirm it’s on a properly licensed Workspace tenant you control. At 25 sends per mailbox, **300 total sends/day would require roughly 12 mailboxes**, commonly across 4–6 secondary domains. That’s capacity planning, not a recommendation to start there or a way around provider policies.
Show the rest (1 more line)
**My recommendation:** use next week for setup and list verification, then launch a small, tightly targeted pilot after the ramp. Prove that the audience and offer generate positive replies before adding volume.
without
Yes—**I’d change the domain, volume, and tracking before launching.** A new inbox sending 300 cold emails a day next week could damage your main domain’s reputation, including delivery of client emails. ### What to change - **Protect your main domain.** Use a separate, clearly branded outreach domain—not a deceptive lookalike—and identify your agency accurately. A subdomain offers some separation, but don’t assume it fully isolates reputation. Don’t rotate domains to bypass filtering. - **Don’t jump straight to 300/day.** Start with a small, carefully selected batch—perhaps 10–20 relevant recipients per day—and increase gradually only if delivery, bounces, complaints, and recipient responses support it. That’s a cautious starting point, not a guaranteed “safe” volume. Google’s sending limits are ceilings, not deliverability recommendations. - **Turn off open tracking initially.** Tracking pixels add privacy concerns and can create deliverability friction. Opens are also unreliable because of image blocking, privacy proxies, and security scanners. Measure positive replies, qualified conversations, and booked meetings instead. - **Set up authentication first.** Confirm SPF, DKIM, and DMARC are configured correctly and aligned with your sending domain. Start DMARC with monitoring if needed, then tighten it after checking legitimate senders. - **Prioritize list quality and relevance.** Use a small, well-researched audience. Verify addresses, avoid scraped or purchased bulk lists, and suppress hard bounces and opt-outs immediately. Address verification does **not** establish consent. - **Make declining easy.** Clearly identify your business and include a simple opt-out that you actually honor. Check the rules where recipients are located: U.S. CAN-SPAM, Canadian CASL, and European/UK privacy and marketing rules differ; “B2B” isn’t a universal exemption. - **Keep the first message simple.** Use an honest subject line, a specific reason for contacting that person, and a
Show the rest (5 more lines)
low-pressure question. Avoid attachments, unnecessary links, and fake “Re:” subjects. Also check Google Workspace’s current acceptable-use rules—**being below a daily sending limit doesn’t mean unsolicited bulk outreach is permitted.** Avoid automated “warm-up” services that manufacture opens and replies; they don’t establish genuine demand or guarantee inbox placement. **For next week:** finish authentication and opt-out handling, turn tracking off, and run a small pilot rather than a 300/day launch. If replies show poor fit, bounces rise, or complaints appear, pause and fix the targeting before increasing volume.

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.