Cold Email Writer logo

Cold Email Writer

CommunityPopular
Paramchoudhary
cold-email-writer

Write personalized cold outreach emails to hiring managers and founders — specific, human, not a pitch deck

Overview

PublisherParamchoudhary
RepositoryResumeSkills
Skill namecold-email-writer
Stars
2.3K
Forks
197
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Paramchoudhary on GitHub. Read the source before you install it.

Installation

Install the Cold Email Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Paramchoudhary/ResumeSkills.git /tmp/ResumeSkills
mkdir -p .claude/skills
cp -r /tmp/ResumeSkills/skills/cold-email-writer .claude/skills/cold-email-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cold Email Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cold Email Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cold Email Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cold Email Writer

When to Use This Skill

Use this skill when the user wants to:

  • Write a cold outreach email to a hiring manager, founder, or recruiter
  • Reach out about a job opening they weren't referred to
  • Introduce themselves to a company they want to work at
  • Mentions: "cold email", "reach out", "intro email", "outreach", "contact hiring manager"

Core Principle

Cold emails fail because they sound like cover letters. The goal is to sound like a smart person who genuinely noticed something specific about the company — not a candidate broadcasting their credentials.

The email should feel like: A colleague mentioning something interesting they read, not a sales pitch.

The Template Structure

Subject

Quick intro — [First Name Last Name]

Simple. No clickbait. No role title. Just a name.

Opening — The Hook (2-3 sentences)

Start with what genuinely pulled the candidate in. Must be specific to this company — not a generic compliment.

I just came across [Company] and ended up spending more time on it than I expected.
[One specific thing that caught their attention — a stat, a product decision, a market insight from the JD or website]

What makes a good hook:

  • A specific number or stat from the company's materials ("only 5% of the market is online")
  • A product decision that shows you understand the domain ("you're building from scratch alongside underwriters, not just distribution")
  • A technical insight from the JD ("improving the data infrastructure for LLM usage, not just the model layer")

What makes a bad hook:

  • Generic: "I love what you're building"
  • Vague: "Your mission resonates with me"
  • Flattering: "You're one of the most exciting companies in the space"

Location Disclosure (if international)

If the candidate is in a different country from the company, disclose it early and casually:

Before you read further, I should mention I'm based in [country]. But if we both
feel there's a strong fit, I'd be open to figuring things out.

Experience Gap (if applicable)

If the role lists more years than the candidate has, acknowledge it briefly and redirect:

The role mentions [X] years of experience — I'm at [Y], but the work I've
shipped is production-facing and I'd rather you judge that directly.

The Body — Who They Are (3-5 sentences)

Current role → relevant past → one or two projects. Keep it contextual, not a list.

A bit about me: I currently work at [Company], [one line on what the company does],
where I [what they actually do there — not a job title]. Before that I worked
with teams in [region], mostly around [relevant domain].

On the side I've been building [Project] ([link if applicable]) — [one line: what
it is and one proof point like "got to paying clients" or "20K downloads"].

Rules:

  • Mention work as context, not as proof of greatness
  • No achievement listings ("I increased X by Y%") — let the project speak
  • If current company is remote with a European/international team, say so explicitly
  • Keep project mentions to one or two max — the most relevant ones only

The Connection (1-2 sentences)

Bridge between their background and the specific role. Should feel like an observation, not a claim.

I think you're looking for [what the role actually wants] — that's the kind of
work I've been doing, and honestly I feel like I'd be a strong fit.

Or more specific:

My stack maps naturally to yours — [specific tech overlap]. But more than the
stack, it's the [domain/problem] that I'm genuinely interested in.

Portfolio Link

More about me: [portfolio URL]

One line. No elaboration.

Closing

End with low-pressure, confident energy. Not desperate, not corporate.

I'm currently at [Company] and open to what's next. I think my experience lends
nicely to what you're building — so I think we'd both get something out of a
conversation.

[First Name]
[email]

Avoid:

  • "I look forward to hearing from you"
  • "Please find attached my resume"
  • "I would love the opportunity to..."
  • "I am excited to potentially join..."

Research Before Writing

Before writing the email, gather:

  1. Company angle — read their website, JD, or About page. Find one specific thing worth mentioning.
  2. Recipient name — LinkedIn, team page, or AngelList. "Hi [Name]" beats "Hi Hiring Manager" every time.
  3. Relevant projects — match the candidate's most relevant work to the role domain.
  4. Stack overlap — mention it only if there's a genuine match.

If the user provides a JD but no company website, ask for it or fetch it before writing.

Length Guidelines

  • Ideal: 200–300 words
  • Maximum: 400 words
  • Minimum: 150 words (don't strip out substance for brevity)

Longer is fine if every sentence earns its place. Cut anything that could apply to any company.

Output Format

Always wrap the final email in a plain code block for clean copy-paste:

Subject: Quick intro — [Name]

Hi [Name],

[Email body]

[First Name]
[email]

Common Mistakes to Avoid

Too confident: ❌ "I would be an exceptional addition to your team" ❌ "My background uniquely positions me for this role" ✅ "I feel like I'd be a strong fit" — states a belief, doesn't claim certainty

Too humble: ❌ "I know I may not have all the experience you're looking for, but..." ❌ "I'm just reaching out on the off chance..." ✅ Acknowledge gaps directly and move on — don't apologize

Too long: ❌ Three paragraphs listing every achievement ✅ One paragraph on background, one on the connection

Too generic: ❌ Opening with "I am writing to express my interest in..." ✅ Opening with what specifically pulled them to this company

No research: ❌ "I love your product and mission" ✅ "The 5% stat — only 5% of a $25B market online — doesn't feel like a feature gap, it feels like an entire industry that hasn't digitised"

Example Email

Subject: Quick intro — Sarah Chen

Hi Marcus,

I just came across Meridian and spent more time on your site than I planned.
What pulled me in was the framing around your data infrastructure — you're not
just building an LLM layer on top of existing records, you're rethinking how
clinical data flows through the system in the first place. That's a harder
problem and a more interesting one.

I'm based in India, flagging that upfront. Happy to figure out the rest if
there's a real fit.

I currently work at Lune, a London-based climate intelligence company, where I
build event-driven data pipelines and agentic AI workflows for emissions
compliance — regulated, data-intensive systems where reliability isn't optional.
I also built Memos, a RAG system from scratch: hybrid retrieval, reranking,
ChromaDB, FastAPI. And InframetAI, an SDK for LLM cost and latency
observability that came out of seeing what breaks when the data layer isn't
designed around how models actually work.

I think you're looking for engineers who've actually built AI systems end to
end, not just wrapped APIs. That's the work I've been doing.

More about me: yourportfolio.com/about

I'm currently at Lune and open to what's next. I think my experience maps
closely to what you're building — so I think we'd both get something out of
a conversation.

Sarah
sarah@email.com

Frequently asked questions

What does the Cold Email Writer AI skill do?

Write personalized cold outreach emails to hiring managers and founders — specific, human, not a pitch deck

Why use Cold Email Writer on TypingMind?

Because you install it once and use it with any model. Cold Email Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cold Email Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Paramchoudhary/ResumeSkills/tree/main/skills/cold-email-writer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cold Email Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cold Email Writer?

As many as you like. As long as a model supports skills, you can use Cold Email Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cold Email Writer AI skill free?

Yes. It is published on GitHub by Paramchoudhary under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇