Smartlead Spintax logo

Smartlead Spintax

Community
growthenginenowoslawski
smartlead-spintax

Adds Smartlead-compatible spintax to cold email sequences for deliverability. Use this skill whenever the user asks to add spintax, spin text, add variations, or improve deliverability of email copy — especially when they mention Smartlead, cold email sequences, or paste HTML email content. Also trigger when the user says "spintax", "spin", "variations", "deliverability spintax", or references adding randomized alternatives to email copy. Works with both plain text and HTML input.

Overview

Publishergrowthenginenowoslawski
Repositorycoldoutboundskills
Skill namesmartlead-spintax
Stars
757
Forks
267
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 growthenginenowoslawski on GitHub. Read the source before you install it.

Installation

Install the Smartlead Spintax 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/growthenginenowoslawski/coldoutboundskills/tree/main/skills/smartlead-spintax
  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/growthenginenowoslawski/coldoutboundskills.git /tmp/coldoutboundskills
mkdir -p .claude/skills
cp -r /tmp/coldoutboundskills/skills/smartlead-spintax .claude/skills/smartlead-spintax
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Smartlead Spintax 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 Smartlead Spintax 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 Smartlead Spintax 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.

Smartlead Spintax Skill

Add deliverability-improving spintax to cold email sequences using Smartlead's syntax, without changing the meaning or tone of the original messaging.

Core Concept

Spintax lets Smartlead randomly pick one option per send, so no two emails are identical. This reduces pattern detection by spam filters and improves deliverability.

Smartlead syntax: {option1|option2|option3}

Each option inside the curly braces is separated by a pipe |. Smartlead picks one at random per email send.


Input Handling

HTML Input (preferred workflow)

Users often paste HTML from Smartlead because copy-pasting plain text loses formatting (spaces, line breaks). When the user provides HTML:

  1. Mentally parse the text content from the HTML
  2. Add spintax to the text content
  3. Return the full HTML with spintax baked in, preserving all HTML tags, <br>, <div>, structure exactly as received
  4. Output as a code block so the user can copy-paste straight back into Smartlead

Plain Text Input

If the user pastes plain text, add spintax and return plain text.


The Golden Rule: No Broken Combinations

Every possible combination that Smartlead could randomly assemble MUST read as a natural, grammatically correct, complete sentence. This is the single most important rule.

What "broken combo" means

When spintax options are placed near each other, every possible pairing across adjacent spintax blocks must work together. If option A from block 1 combines with option B from block 2 to form a weird or ungrammatical sentence, that's a broken combo.

How to prevent broken combos

Make each spintax block a self-contained phrase. The options within one block should be interchangeable without depending on what another nearby block picks.

BAD — dependent blocks that can break:

{let me know if|would} {{employeeline}} {would be better to speak to|be a better person to chat with}

Problem: "would" + "would be better to speak to" = "would {{name}} would be better to speak to" — broken.

GOOD — each option is a full standalone phrase:

{let me know if {{employeeline}} would be better to speak to about this?|would {{employeeline}} be a better person to chat with about this?|should I be reaching out to {{employeeline}} about this instead?}

Each option is a complete sentence on its own. No cross-block dependency.

Verification step

After adding spintax, mentally walk through every combination across adjacent blocks. If any pairing sounds off, restructure so each block is independent. When the sentence structure makes independent blocks risky, wrap the entire sentence in one spintax block with full sentence alternatives.


What to Spin

Add 2-3 options per spintax block. Target these elements:

Always spin

  • Greetings: {Hey|Hi} — simple, always safe
  • Opt-out / unsubscribe lines: These are repetitive across emails and easy to spin without tone change
  • CTAs: Different phrasings of the same ask
  • Transition words and connectors: "just", "also", "actually", etc.

Spin when natural

  • Verb choices: {help|work with}, {built|made}, {handles|manages|tackles}
  • Descriptors: {completely free|on us|100% free}
  • Sentence-level rephrasings: When a line can be said 2-3 different ways without changing meaning

Never spin

  • Smartlead variables: {{first_name}}, {{company_name}}, {{custom_variable}} — leave these exactly as-is
  • Signature placeholders: %signature% — never touch
  • Specific data points: Numbers, stats, brand names, product names, pricing
  • Technical terms or product descriptions that need to be precise

Tone Preservation

The spintax options must match the tone and register of the original. If the original is casual, all options should be casual. If it's direct, keep all options direct. Don't introduce formality where there was none, and don't add slang where the original was professional.

Original tone: casual/direct

  • ✅ {Worth a shot?|Want to give it a try?|Open to trying it out?}
  • ❌ {Would you be amenable to a trial?|Worth a shot?} — register mismatch

Output Format

For HTML input

Return the spintaxed HTML inside a code block:

html
{Hey|Hi} {{first_name}}, {open to a free backlink on|interested in a free backlink from} Forbes, WSJ, or Tech Times for {{company_name}}?
<br>
<br>{We work with|We partner with} a network of over 1,200 publishers...

For plain text input

Return the spintaxed text inside a code block:

{Hey|Hi} {{first_name}}, {open to a free backlink on|interested in a free backlink from} Forbes, WSJ, or Tech Times for {{company_name}}?

After each email

State: "All combos clean." — confirming you verified every combination. If you found and fixed something, note what you changed and why.

Then ask: "Next?" or "Drop the next one." to keep the flow moving.


Multi-Email Sequences

When the user is doing a full sequence, process one email at a time. After each:

  1. Output the spintaxed version
  2. Confirm combos are clean
  3. Prompt for the next email

Keep a mental count of which email in the sequence you're on (Email 1, Email 2, etc.) so you can reference them if the user asks.


Flagging Issues

If you spot something in the original copy that's awkward or could be improved (independent of spintax), flag it briefly after the spintax output. For example:

One small flag: "does QA differently" reads a bit awkward — consider swapping to {handles|approaches|tackles} instead.

Keep flags minimal. Only flag things that would actually hurt the email's performance. Don't rewrite their copy unless asked.


Quick Reference

ElementExample
Syntax{option1|option2|option3}
Greeting{Hey|Hi}
Verb swap{help|work with|partner with}
Full sentence{Is this worth exploring?|Want to give it a try?|Open to a quick chat?}
Opt-out{If this isn't relevant, just reply and I won't follow up.|Not relevant? Just reply and I won't reach out again.}
Never touch{{first_name}}, {{company_name}}, %signature%

What to do next

Launch the spintaxed copy via /smartlead-campaign-upload-public — the spintax gets embedded in the variants.yaml body fields and renders per-recipient on send.

Or wait: skip this skill until your copy is final. Spintax complicates later debugging.

Related skills

  • /campaign-copywriting — writes the base copy this skill varies
  • /smartlead-campaign-upload-public — launches the spintaxed campaign

Frequently asked questions

What does the Smartlead Spintax AI skill do?

Adds Smartlead-compatible spintax to cold email sequences for deliverability. Use this skill whenever the user asks to add spintax, spin text, add variations, or improve deliverability of email copy — especially when they mention Smartlead, cold email sequences, or paste HTML email content. Also trigger when the user says "spintax", "spin", "variations", "deliverability spintax", or references adding randomized alternatives to email copy. Works with both plain text and HTML input.

Why use Smartlead Spintax on TypingMind?

Because you install it once and use it with any model. Smartlead Spintax 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 Smartlead Spintax in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/smartlead-spintax. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Smartlead Spintax?

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 Smartlead Spintax?

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

Is the Smartlead Spintax AI skill free?

Yes. It is published on GitHub by growthenginenowoslawski 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 👇