Email Marketing logo

Email Marketing

Community
shawnpang
email-marketing

When the user needs to design, write, or optimize email sequences -- including welcome series, nurture campaigns, re-engagement flows, onboarding emails, or newsletter strategy.

Overview

Publishershawnpang
Repositorystartup-founder-skills
Skill nameemail-marketing
Stars
368
Forks
43
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 shawnpang on GitHub. Read the source before you install it.

Installation

Install the Email Marketing 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.
    https://github.com/shawnpang/startup-founder-skills/tree/main/skills/email-marketing
  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/shawnpang/startup-founder-skills.git /tmp/startup-founder-skills
mkdir -p .claude/skills
cp -r /tmp/startup-founder-skills/skills/email-marketing .claude/skills/email-marketing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Email Marketing 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 Email Marketing 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 Email Marketing 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.

Email Marketing

When to Use

  • Building a welcome sequence for new signups or lead magnet downloads.
  • Designing a lead nurture sequence to move prospects toward conversion.
  • Creating a re-engagement campaign for inactive users or subscribers.
  • Writing an onboarding email series that drives product activation.
  • Planning a newsletter cadence and format.
  • Optimizing existing sequences for open rate, click rate, or conversion.

Context Required

  • From startup-context: product description, ICP, value proposition, tone of voice, current user journey stages, key activation metrics.
  • From the user: sequence type needed (welcome, nurture, re-engagement, onboarding, post-purchase, educational), audience context (who they are, what triggered entry, relationship stage), current email list size and segments, existing sequences (if optimizing), email platform in use, primary conversion action, any existing performance data.

Workflow

  1. Define the sequence goal -- Every sequence gets one job. Map it to a specific outcome:
    • Welcome: activate, build trust, convert
    • Nurture: educate, build desire, drive trial/demo/purchase
    • Re-engagement: reactivate or clean the list
    • Onboarding: drive users to key activation milestones (coordinate with in-app messaging -- email supports, does not duplicate)
    • Newsletter: maintain top-of-mind, drive traffic, build relationship
  2. Map the sequence arc -- Plan the emotional and logical progression across emails:
    • Welcome (5-7 emails, 12-14 days): Deliver value and quick win, origin story/connection, educational content on their pain, social proof/case study, address #1 objection, feature highlight, conversion ask with reason to act now.
    • Lead nurture (6-8 emails, 2-3 weeks): Lead magnet delivery, topic expansion, problem deepening, solution framework, case study, differentiation, objection handling, direct offer.
    • Re-engagement (3-4 emails, 2 weeks, triggered at 30-60 days inactivity): Check-in, value reminder, incentive, last chance and list cleanup.
    • Onboarding (5-7 emails, 14 days): Activate, guide to aha moment, feature education, milestone celebration, upgrade prompt.
  3. Write each email using One Email, One Job -- Each email has one primary message and one call to action. No competing CTAs, no kitchen-sink emails.
  4. Apply the email copy structure:
    • Hook (first 1-2 lines): Open with a question, surprising fact, or relatable scenario. This determines whether they keep reading.
    • Context (2-3 lines): Bridge from hook to value. Why does this matter to them right now?
    • Value (body): Deliver the insight, story, resource, or proof.
    • CTA (final 1-2 lines): Clear, specific, single action. Button for transactional CTAs, text link for content CTAs.
    • Formatting: Short paragraphs (1-3 sentences), generous whitespace, bullet points where helpful, mobile-first. Conversational tone, active voice.
  5. Optimize subject lines -- Write 3 variants per email:
    • Keep under 40-60 characters for mobile
    • Patterns: questions, how-tos, numbers, direct statements, story teases
    • Clear beats clever, specific beats vague
    • Avoid spam triggers (ALL CAPS, excessive punctuation, "free")
    • Preview text (90-140 characters) is the second subject line -- write it deliberately, do not repeat the subject
  6. Set timing and triggers -- Welcome email sends immediately. Early sequence emails 1-2 days apart. Nurture phase 2-4 days apart. Long-term weekly or bi-weekly. Define behavior-triggered branching where relevant.
  7. Plan measurement -- Define success metrics per email: open rate, click rate, reply rate, conversion rate. B2B SaaS benchmarks: 25-35% open, 3-5% click, 1-3% conversion.

Output Format

  • Sequence overview: name, entry trigger, goal, number of emails, timing, exit conditions.
  • Per-email detail: number/purpose, send timing, 3 subject line options, preview text, full body copy (50-500 words depending on type), CTA, segment/conditions.
  • Email length guidance: transactional 50-125 words, educational 150-300 words, story-driven 300-500 words. Anything over 500 words should be a blog post you link to.
  • Segmentation logic and branching paths if applicable.

Frameworks & Best Practices

  • One Email, One Job. The most common email mistake is trying to do too much. One message, one CTA. If you have two things to say, send two emails.
  • Value Before Ask. Lead with usefulness, build trust through content before making the conversion ask. The sequence arc should front-load value.
  • Relevance Over Volume. Fewer, better emails win. Segmentation by behavior (what they did) matters more than personalization by demographics (who they are).
  • Plain text outperforms HTML for B2B. For B2B audiences, plain text emails (or minimal HTML that looks like plain text) consistently outperform heavily designed emails. They feel personal, not promotional.
  • Send timing. Tuesday through Thursday, 9-11 AM in the recipient's timezone performs best on average, but the best send time is when your audience actually reads email. Test and adjust.
  • List hygiene. Remove unengaged subscribers (no opens in 90 days for weekly senders, 180 days for monthly) after a re-engagement attempt. A smaller, engaged list outperforms a large, dead one.
  • Reply-to matters. Use a real person's email as the reply-to address. Replies improve deliverability and create sales conversations.
  • Unsubscribe is not the enemy. Make unsubscribing easy and obvious. People who cannot leave will mark you as spam, which damages deliverability for everyone on your list.
  • Mobile-first writing. Over 60% of emails are opened on mobile. Short paragraphs, generous whitespace, thumb-sized buttons.

Related Skills

  • cold-outreach -- when emails are going to prospects who have not opted in (different rules, different approach)
  • content-strategy -- when email content needs to be part of a broader content distribution plan
  • onboarding-flow -- when the email sequence is part of product onboarding and needs to align with in-app messaging

Examples

Example 1: Welcome sequence for lead magnet

"We launched a free template as a lead magnet. Need a welcome sequence to convert downloads to free trial signups."

Good output: A 6-email sequence over 12 days. Email 1 delivers the template with a quick-start tip. Email 2 shares the founder story. Email 3 teaches a technique related to the template topic. Email 4 shares a customer case study. Email 5 addresses the "I don't have time for another tool" objection. Email 6 offers a free trial with a specific reason to start this week. Each email includes 3 subject line variants, full copy (100-400 words), and a single CTA.

Example 2: Re-engagement campaign

"We have 3,000 subscribers who haven't opened an email in 60 days. What do we do?"

Good output: A 3-email re-engagement sequence. Email 1 (day 0): "Still interested?" with a high-value resource, no hard sell. Email 2 (day 3): Direct question asking what content they want, reply-based engagement. Email 3 (day 7): "Last email unless you want to stay" with a clear re-opt-in link. Anyone who does not engage after email 3 goes to a suppression list. Includes list cleaning guidance and re-engagement benchmarks.

Frequently asked questions

What does the Email Marketing AI skill do?

When the user needs to design, write, or optimize email sequences -- including welcome series, nurture campaigns, re-engagement flows, onboarding emails, or newsletter strategy.

Why use Email Marketing on TypingMind?

Because you install it once and use it with any model. Email Marketing 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 Email Marketing in TypingMind?

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

Which AI models can use Email Marketing?

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 Email Marketing?

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

Is the Email Marketing AI skill free?

Yes. It is published on GitHub by shawnpang 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 👇