Smartlead Inbox Manager logo

Smartlead Inbox Manager

Community
growthenginenowoslawski
smartlead-inbox-manager

Programmatic inbox management for Smartlead. Enable/disable warmup with correct ramp settings, set signatures in bulk, tag inboxes (active vs insurance), and pull inbox health dashboards. Use after creating a new batch of inboxes via /zapmail-domain-setup-public, or when managing an existing Smartlead account at scale. Triggers on "turn on warmup", "set signatures", "tag inboxes", "inbox health", "set up new inboxes".

Overview

Publishergrowthenginenowoslawski
Repositorycoldoutboundskills
Skill namesmartlead-inbox-manager
Stars
757
Forks
267
Bundled files
5
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Smartlead Inbox Manager 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-inbox-manager
  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-inbox-manager .claude/skills/smartlead-inbox-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Smartlead Inbox Manager 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 Inbox Manager 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 Inbox Manager 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 Inbox Manager

Zapmail hands you hundreds of new inboxes. Smartlead needs them configured: warmup enabled with the right ramp, signatures set so emails don't look bare, tags applied so you know which are active vs insurance, and health monitored so dead inboxes get recycled.

This skill does all of that via the Smartlead API.

Core operations

OperationWhat it doesScript
Enable warmupTurns on warmup with correct ramp (start 1/day, +5/day up to 40/day)set-warmup.ts --mode=enable
Disable warmupTurns off warmup (use for insurance inboxes)set-warmup.ts --mode=disable
Set signaturesBulk-applies a signature template to inboxesset-signatures.ts
Tag as activeAdds the "active" tagtag-inboxes.ts --tag=active
Tag as insuranceAdds the "insurance" tagtag-inboxes.ts --tag=insurance
Health dashboardLists all inboxes with warmup status, reputation, daily sentlist-health.ts

Active vs insurance (the tagging convention)

Not every inbox should send all the time. A common pattern:

  • Active inboxes — currently sending in live campaigns. Warmup OFF (or minimal) to prioritize real sends.
  • Insurance inboxes — warmed but idle, held in reserve. Warmup ON to maintain reputation. Swap in when an active inbox burns out.

Tags are how you track this at scale. Filter by tag in Smartlead UI or via API.

Inputs

Every script reads:

  • SMARTLEAD_API_KEY (env var)
  • Inbox selector: --ids=1,2,3 OR --domain=example.com OR --tag=insurance OR --all
  • Operation-specific flags (see each script)

Warmup ramp settings

Default warmup config for a NEW inbox (week 1-4 of warmup period):

json
{
  "warmup_enabled": "true",
  "total_warmup_per_day": 40,
  "daily_rampup": 5,
  "reply_rate_percentage": "20"
}
  • total_warmup_per_day: max emails/day the inbox sends in warmup network (peak)
  • daily_rampup: increment per day (day 1 = 1, day 2 = 6, day 3 = 11, etc. up to the cap)
  • reply_rate_percentage: how often warmup peers reply (20% is realistic)

For INSURANCE inboxes (maintaining reputation long-term):

json
{
  "warmup_enabled": "true",
  "total_warmup_per_day": 15,
  "daily_rampup": 0,
  "reply_rate_percentage": "20"
}

Lower volume, no ramp — just keeps the inbox warm.

For ACTIVE inboxes (currently in live campaigns):

json
{
  "warmup_enabled": "false"
}

Warmup off so the daily send budget goes to real prospects.

Signature template

The default template, applied in bulk via set-signatures.ts, is:

{from_name}
{title}
{company}
{address}

Rendered (for example):

Jane Smith
Founder
Acme
123 Main St, Suite 400, Austin, TX 78701

Where each value comes from:

  • {from_name} — the inbox's own from_name field if set (different personas per inbox), else SENDER_FIRST_NAME + SENDER_LAST_NAME from .env
  • {title} — SENDER_TITLE env var
  • {company} — SENDER_COMPANY_NAME env var
  • {address} — SENDER_PHYSICAL_ADDRESS env var (recommended — a real mailing address in the footer keeps you on the right side of CAN-SPAM and similar rules)

Required .env entries for the default template:

SENDER_FIRST_NAME=Jane
SENDER_LAST_NAME=Smith
SENDER_TITLE=Founder
SENDER_COMPANY_NAME=Acme
SENDER_PHYSICAL_ADDRESS=123 Main St, Suite 400, Austin, TX 78701

Custom template override:

bash
# Pass inline (use \n for newlines)
npx tsx scripts/set-signatures.ts --all --template="Cheers,\n{from_name}\n{title}\n{company}\n{address}"

# Or from a file
npx tsx scripts/set-signatures.ts --all --template-file=./my-signature.txt

Available placeholders: {from_name}, {from_email}, {domain}, {title}, {company}, {address}.

Email body order in campaigns:

In Smartlead sequences, always end the body with %signature% — Smartlead injects the inbox's signature there. Order:

<body content>

<PS unsubscribe line>

%signature%

This puts %signature% (with name + title + company + address) on the bottom, so every inbox sends with a real mailing address in the footer.

Health dashboard output

list-health.ts prints a CSV + summary:

email                              warmup   reputation   sent_today   health_status
john@example.co                    on       good         18           healthy
jane@example.co                    on       fair         5            warming
sales@other.co                     off      n/a          28           active
support@other.co                   on       bad          0            blocked

Summary:

Total inboxes: 80
  Warmup on: 50
  Active (warmup off): 28
  Blocked/failed: 2

Reputation:
  Good: 65
  Fair: 10
  Bad: 3
  Unknown: 2

Action items:
  - 2 inboxes blocked — run /email-deliverability-audit
  - 3 inboxes with "bad" reputation — consider pausing

Common workflows

Day 1 after Zapmail provisioning

bash
# 1. Enable warmup on all newly created inboxes
npx tsx scripts/set-warmup.ts --mode=enable --tag=new --warmup-per-day=40 --ramp=5

# 2. Set signatures
npx tsx scripts/set-signatures.ts --tag=new --template="Best,\n{from_name}"

# 3. Tag them as insurance (they aren't active yet — warmup for 2 weeks first)
npx tsx scripts/tag-inboxes.ts --tag=new --add-tag=insurance
npx tsx scripts/tag-inboxes.ts --tag=new --remove-tag=new

Activating insurance inboxes into a live campaign

bash
# 1. Identify warm insurance inboxes with good reputation
npx tsx scripts/list-health.ts --tag=insurance --filter=reputation:good --out=activate-candidates.csv

# 2. Flip them to active
npx tsx scripts/tag-inboxes.ts --ids-from-csv=activate-candidates.csv --add-tag=active --remove-tag=insurance

# 3. Disable warmup (they're sending for real now)
npx tsx scripts/set-warmup.ts --mode=disable --tag=active

Weekly health check

bash
npx tsx scripts/list-health.ts --all --out=health-$(date +%Y-%m-%d).csv

Review the action items. Replace blocked inboxes.

When to retire an inbox

This skill is the mechanics of retiring an inbox. The decision belongs to /inbox-lifecycle-manager, which applies the full ladder — age guard, send floors, bounce fork, and a check that you have a warmed reserve to swap in before you take capacity away.

The cancel line is the 1% rule: reply rate <1% over 200+ sends (or zero replies on 150+), on a domain at least 30 days old. The floors do the protecting, not a softer threshold.

Three rules that matter here, because it is easy to retire the wrong thing from this skill:

  1. ⛔ Retire whole domains, never single inboxes. Mailbox providers judge reputation at the domain level. Keeping two "good" inboxes on a domain you declared burned means the good ones inherit the bad one's reputation, and you are still sending from a domain you condemned.
  2. ⛔ Never retire a domain under 30 days old, at any reply rate. It hasn't finished ramping.
  3. ⛔ Never retire on under 200 sends. Below that floor a 0% reply rate cannot distinguish a burned inbox from an unlucky week.

Once /inbox-lifecycle-manager has produced an approved plan, execute it here:

bash
# actions.csv comes from /inbox-lifecycle-manager — reviewed and explicitly approved
npx tsx scripts/tag-inboxes.ts --domain=burned-domain.co --add-tag=retired --remove-tag=active
npx tsx scripts/set-warmup.ts --mode=disable --domain=burned-domain.co

Snapshot the current tags before you start — nothing here records prior state, and without a snapshot there is no clean undo. Read the tags back afterwards; a 200 is not proof.

Common gotchas

  • Warmup settings are per-inbox. There's no global setting. Scripts loop and hit each inbox individually.
  • Rate-limiting. Smartlead allows ~33 req/sec. The scripts use 5 concurrent by default. Don't crank this higher without testing.
  • Warmup blocked. If is_warmup_blocked: true, the inbox is flagged (usually for spam-like behavior in warmup). Manual investigation needed.
  • Tags have no delete endpoint in some Smartlead versions — tags can only be ADDED. To "remove" a tag, replace the full tag list with a new one that omits it. The script handles this automatically.
  • Signature formatting. HTML signatures can break rendering across Gmail/Outlook/Apple Mail. Keep it plain text or use minimal <br> tags. Test in Gmail/Outlook after setting.
  • Warmup ramp accumulates. If you set daily_rampup: 5, the inbox sends 1 on day 1, 6 on day 2, 11 on day 3... up to total_warmup_per_day. To reset (e.g. after a break), disable then re-enable.

What to do next

If you just provisioned new inboxes: enable warmup (set-warmup.ts --mode=enable), apply signatures (set-signatures.ts), tag as insurance, then wait 2 weeks for warmup. After 2 weeks, promote insurance → active.

If inboxes are already warm: proceed to list-building (/prospeo-full-export, /disco-like, etc.) using active-tagged inboxes.

Or wait: if the health dashboard shows bad-reputation inboxes, run /inbox-lifecycle-manager to decide which ones actually warrant retirement (and what replaces their capacity) before launching a new campaign.

Related skills

  • /zapmail-domain-setup-public — creates the inboxes this skill configures
  • /email-deliverability-audit — when health dashboard shows problems
  • /inbox-lifecycle-manager — decides which inboxes to retire, promote, or buy; this skill executes it
  • /smartlead-api — underlying API reference

Scripts

  • scripts/set-warmup.ts — enable/disable warmup, configure ramp
  • scripts/set-signatures.ts — bulk signature setting
  • scripts/tag-inboxes.ts — add/remove tags
  • scripts/list-health.ts — health dashboard CSV + summary
  • scripts/_lib.ts — shared: API client, inbox selector parser, concurrency

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Smartlead Inbox Manager AI skill do?

Programmatic inbox management for Smartlead. Enable/disable warmup with correct ramp settings, set signatures in bulk, tag inboxes (active vs insurance), and pull inbox health dashboards. Use after creating a new batch of inboxes via /zapmail-domain-setup-public, or when managing an existing Smartlead account at scale. Triggers on "turn on warmup", "set signatures", "tag inboxes", "inbox health", "set up new inboxes".

Why use Smartlead Inbox Manager on TypingMind?

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

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

Which AI models can use Smartlead Inbox Manager?

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 Inbox Manager?

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

Is the Smartlead Inbox Manager 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 👇