- Home
- Skills
- Sales & Lead Gen
- Cold Email Outbound Playbook
More screenshots
Works with the AI Agents you already use
Cold Email Outbound Playbook
Write B2B cold emails that sound like a real person wrote them - research first, 50-125 words, follow-ups that add something new instead of bumping.
$5
Cold Email Outbound Playbook
Example session with this skill installed
Write me a cold email to the Head of Talent at a 120-person startup that's hiring six engineers this quarter. We sell interview scheduling software. Keep it short, no pitch deck, I just want replies.
- Read your context and instructions
- Compiled the cold email outbound
Diagnosis first: your bottleneck isn't the email, it's the ask. A first touch that asks for a 30-minute call gets deleted. This email asks for a one-word reply instead.
The email:
Subject: eng hiring
Noticed you're hiring six engineers this quarter — that's a serious ramp.
Usually at that pace, scheduling starts eating the recruiters' week — panels, reschedules, the works. We cut interview scheduling to about 20 minutes a week for two startups at your stage last year.
Worth a quick look?
Why it's built this way:
- The opening is specific (six engineers, this quarter) — it couldn't be sent to anyone else, which is what earns the read.
- The bridge names the pain that pace causes, in their words, not product language.
- The proof is one line: two similar companies, one concrete number. No feature list.
- The ask needs a one-word answer from a phone. The meeting gets earned in the reply, not demanded in the email.
- 78 words total. Everything that didn't serve the reply got cut.
Follow-up (day 4, adds something new instead of "just bumping"):
Subject: re: eng hiring
One thing I should've sent the first time — a one-page breakdown of how [similar startup] handled panel scheduling at 40 interviews a week. Want me to send it over?
If they reply "not now": log it, set a 60-day re-touch tied to their next hiring signal (new role posted = new pain), and move on. Timing beats persistence.
Connects securely to your tools. The creator never sees your data.
About this skill
I kept seeing the same four failures in cold outreach: it opens with the sender, reads like a template with a name field, asks for too much, and lands in spam anyway. This skill fixes all four, in that order of importance.
It starts with a diagnosis - is your problem relevance, opens, meetings, or deliverability? Then signal-based research to earn the right to send: their own words about the problem, events that create the pain, structural fit. Then the email itself, built on a strict anatomy: a specific observation that could not be sent to anyone else, a bridge to the problem, one line of proof, and one low-friction ask the reader can answer in one sentence from their phone.
Also covered: follow-up sequences where every touch adds something new, sending-infrastructure and deliverability basics (secondary domains, warm-up, why you turn open tracking off), and reply triage - including how to handle "not now" without burning the contact.
Includes worked examples throughout, including a full first-touch + follow-up pair. This is a workflow and copy skill - it does not send email or connect to your inbox, it makes what you send worth replying to.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Sales & Lead Gen.
Advice and copy only - it does not send email, access your inbox or CRM, or guarantee replies. Results depend on your list quality, offer, and domain setup.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 25 days ago
Permissions
No special permissions declared or detected