Cold Email
Write and optimize B2B cold outreach email sequences.
$skillfish add ~skills/cold-email Real Conversations
See how the Cold Email skill responds to actual requests. These are representative examples of what your AI agent will produce.
We want to do cold outbound for Nucleus PM targeting VPs of Engineering at B2B SaaS companies with 50–200 employees. These people get a ton of cold email. We're trying to get them to book a 20-minute demo. Write a 3-email sequence.
Here's a 3-email sequence — written for the inbox of someone who deletes cold email fast:
Email 1 — Day 1
Subject: Sprint planning at [Company]
To: [First name]
[First name],
Quick question — how long does sprint planning take your team right now?
I ask because most eng managers I talk to say it's 2–3 hours per sprint. At a 50-person company, that's one of your most expensive recurring meetings.
We built Nucleus PM to cut that time in half. AI suggests story points before the estimation debate starts — teams average 40% less planning time in the first sprint.
Worth a 20-minute look? [Calendly link]
[Your name], Nucleus PM
Email 2 — Day 4 (no reply)
Subject: Re: Sprint planning at [Company]
[First name],
Following up in case this got buried.
We're not a Jira replacement — Nucleus PM is built specifically for engineering teams that want AI-assisted planning without the Atlassian overhead.
Setup is 15 minutes (we've timed it). Here's a [2-min demo video] if you'd rather watch than read.
Happy to work around your schedule: [Calendly link]
[Your name]
Email 3 — Day 9 (no reply)
Subject: Closing the loop
[First name],
I'll stop following up after this — I know your inbox is real estate.
If sprint planning time is actually a problem for your team, I'm happy to show you how we approach it. If it's not on your radar right now, totally understood.
[Book a time if ever relevant] — or just let me know if there's a better time to reach out.
[Your name]
Personalization layer (add to Email 1 for best results):
- If they recently posted on LinkedIn about engineering process: reference the specific post
- If their company recently raised funding: "Saw the Series B — congrats. Growing eng teams usually feel sprint planning pain right around this stage."
- If they use Jira (from tech stack lookup): "Saw you're on Jira — a lot of teams use Nucleus PM alongside it for the AI features Jira doesn't have yet."
Expected benchmarks: 40–55% open rate (subject line specificity), 3–6% reply rate, 1–2% demo booking rate on a well-targeted list.
Get Started
How to install and use this skill in your preferred environment.
Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.
Models & Context
Which AI models and context windows work best with this skill.
Recommended Models
Larger models produce more detailed, production-ready outputs.
Context Window
This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.
All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.
Pro tips for best results
Be specific
Include numbers — users, budget, RPS — so the skill can size the architecture.
Share constraints
Compliance needs, team size, and existing stack all improve the output.
Iterate
Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.
Combine skills
Pair with companion skills below for end-to-end coverage.
Ready to try Cold Email?
Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.
$skillfish add ~skills/cold-email