Smartlead Workflow Setup

Smartlead workflows

by LeadMagic · MIT license · ★ 62 on GitHub

Sets up and runs Smartlead: mailbox connection and auto-rotation, A/B testing, the master inbox, and AI reply categorization. Use when the user is configuring Smartlead, adding mailboxes, or optimizing Smartlead campaigns.

---
name: smartlead-workflows
description: >-
  Sets up and runs Smartlead: mailbox connection and auto-rotation, A/B testing,
  the master inbox, and AI reply categorization. Use when the user is
  configuring Smartlead, adding mailboxes, or optimizing Smartlead campaigns.
  Triggers on: "Smartlead", "Smartlead setup", "Smartlead campaigns", "unlimited
  mailboxes".
license: MIT
compatibility: Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Goose, Hermes, Windsurf, Zed
metadata:
  version: "1.0.0"
  author: LeadMagic
  category: tools
  tags: [smartlead, cold-email, mailboxes, auto-rotation, outbound]
  frameworks:
    - "Smartlead Help Center"
    - "Eric Nowoslawski — Cold email infrastructure"

Overview

Before delivering, verify: - [ ] All required sections are complete - [ ] Output matches the user's stated need - [ ] Named frameworks are cited for key recommendations - [ ] No vague claims — every recommendation has a specific action - [ ] Deliverable is ready for operational use, not just conceptual

Manual install (npx, ZIP)

Claude Codenpx skills add LeadMagic/gtm-skills --skill smartlead-workflows -g -a claude-code

Claude Code (degit)npx degit LeadMagic/gtm-skills/skills/tools/smartlead-workflows#main ~/.claude/skills/smartlead-workflows

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md7.4 KB

Read SKILL.md here

LeadMagic/main1 file shown

SKILL.md7.4 KB

Browse every file on GitHub↗

SKILL.md

Show the full text154 lines

Smartlead Workflows

Overview

Smartlead is the cold email platform of choice for high-volume senders. Its killer features: unlimited mailboxes, automatic mailbox rotation, AI reply categorization, and a unified master inbox. This skill covers setup from 0 to sending at scale.

Authoritative Foundations

Smartlead Help Center — Connect mailboxes, enable warmup, set per-mailbox limits and rotation, and route replies to the master inbox.
Eric Nowoslawski — Cold email infrastructure — Cold email infra at scale — 2 inboxes/domain, backup inboxes, Creative Ideas testing.
Google and Yahoo — Bulk sender requirements (2024) — Authenticate with SPF, DKIM, and DMARC, keep spam complaints below 0.3%, and honor unsubscribes quickly.

When to Use

"Set up Smartlead"
"Smartlead campaign setup"
"Add mailboxes to Smartlead"
"Smartlead optimization"

Step-by-Step Process

Phase 1: Infrastructure Setup

Before creating a single campaign:

Connect 3-5 sending domains per client (secondary domains, not primary)
Add 2-3 mailboxes per domain (Google Workspace or M365)
Verify DNS: SPF, DKIM, DMARC, custom tracking domain
Warm up each mailbox 2-3 weeks before sending (start 5/day, ramp to 50/day)
Set up master inbox: unified view of all replies across all mailboxes

Phase 2: Campaign Creation

Per campaign:

Lead list: Upload CSV, map fields, segment by persona
Sequence: 3-5 step sequence, plain text only, no images/HTML
Mailbox assignment: Auto-rotate across 15-25 mailboxes, max 30-50 emails/day/mailbox
Sending window: Mon-Thu 6am-8pm prospect timezone, 45-90 second delay between sends
Tracking: Open tracking OFF (hurts deliverability in 2026), reply tracking ON

Phase 3: AI Reply Categorization

Train Smartlead's AI to categorize replies:

Positive: "Interested," "Let's talk," "Send more info" → label INTERESTED
Neutral: "Not now," "Maybe next quarter" → label NOT NOW
OOO: Auto-replies, vacation → label OOO, auto-pause
Negative: "Stop emailing," "Remove me" → label UNSUBSCRIBE, auto-block
Wrong person: "I'm not the right person" → label WRONG CONTACT, flag for update

Phase 4: A/B Testing

Test at campaign level:

Subject line: 2-4 variants, rotate evenly, measure reply rate
Opener: Different hook patterns, same body
CTA: Soft vs direct, measure meeting rate
Send time: Morning vs afternoon by timezone, auto-optimize

Phase 5: Analytics & Optimization

Campaign health: Reply rate (>2% healthy), bounce rate (<3% healthy), spam rate (<0.1%)
Mailbox health: Per-mailbox bounce and spam rates, rotate out unhealthy mailboxes
Sequence optimization: Which step drives most replies, trim low-performing steps
A/B winner declaration: After 500+ sends per variant, declare winner and auto-apply

Output Format

Smartlead setup playbook with: infrastructure checklist, campaign configuration, AI categorization rules, A/B test plan, and optimization cadence.

Quality Check

Before delivering, verify:

All required sections are complete
Output matches the user's stated need
Named frameworks are cited for key recommendations
No vague claims — every recommendation has a specific action
Deliverable is ready for operational use, not just conceptual

Common Pitfalls

Skipping research. Building output without understanding the specific context. Fix: always gather required inputs before producing deliverables.
Generic output. "Improve your process" without concrete steps. Fix: every recommendation must include a specific action, timeline, and owner.
Missing framework citations. Advice without named authorities. Fix: ground every recommendation in a cited framework from a recognized authority.

Execution Artifacts

references/framework-notes.md — Eric Smartlead scale, Pat verify gate, AI categorization
templates/output-template.md — infrastructure + AI labels + Clay gate deliverable
scripts/check-output.py — local checklist validator This skill includes lightweight artifacts the agent can load on demand:
references/clay-enrollment-handoff.md — Clay/loops → Smartlead push + custom variables
references/eric-nowoslawski-outbound.md — Eric Nowoslawski agency infra (canonical Smartlead operator)
references/pat-spielmann-outbound-copy.md — verify-before-send (Pat Spielmann)
references/leadmagic-waterfall.md — loop enrich chain before push
references/cli-workflow-patterns.md — lm integrations smartlead push
references/gtm-experts-outbound-index.md — expert router Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.

Implementation Depth

Use this section when the user asks for a finished asset, not a high-level explanation.

Diagnostic Questions

What is the primary motion: founder-led, sales-led, product-led, partner-led, or lifecycle-led?
Which ICP tier is the output for: small business, mid-market, enterprise, or mixed?
What proof is available today: customer stories, usage data, third-party validation, screenshots, or none?
What system will execute the work: CRM, sequencer, warehouse, support desk, product analytics, or manual workflow?
What decision will the user make from this output: launch, prioritize, route, rewrite, score, coach, or measure?

Framework Application

Map the recommendation explicitly to the named frameworks in this skill:

Smartlead Best Practices: apply only the part that directly improves the requested deliverable.
Eric Nowoslawski Cold Email Infrastructure: apply only the part that directly improves the requested deliverable.
Outreach — Sales Engagement Cadence Design: apply only the part that directly improves the requested deliverable.

Deliverable Standard

A strong output from this skill includes:

A crisp diagnosis of the current situation
A recommended path with tradeoffs, not a generic list
A concrete artifact the user can use immediately: table, script, checklist, scorecard, sequence, dashboard spec, or implementation plan
A measurement plan with leading and lagging indicators
Risks and edge cases called out before execution

Adaptation Rules

For small business: reduce complexity, shorten time-to-value, and prioritize owner/operator clarity.
For mid-market: include workflow ownership, handoffs, integrations, and enablement assets.
For enterprise: include governance, risk, procurement, stakeholder mapping, and proof requirements.

email-deliverability, domain-infrastructure, inbox-setup, cold-email-strategy, cold-email-copywriting

1	---
2	name: smartlead-workflows
3	description: >-
4	Sets up and runs Smartlead: mailbox connection and auto-rotation, A/B testing,
5	the master inbox, and AI reply categorization. Use when the user is
6	configuring Smartlead, adding mailboxes, or optimizing Smartlead campaigns.
7	Triggers on: "Smartlead", "Smartlead setup", "Smartlead campaigns", "unlimited
8	mailboxes".
9	license: MIT
10	compatibility: Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Goose, Hermes, Windsurf, Zed
11	metadata:
12	version: "1.0.0"
13	author: LeadMagic
14	category: tools
15	tags: [smartlead, cold-email, mailboxes, auto-rotation, outbound]
16	frameworks:
17	- "Smartlead Help Center"
18	- "Eric Nowoslawski — Cold email infrastructure"
19	- "Google and Yahoo — Bulk sender requirements (2024)"
20	---
21
22	# Smartlead Workflows
23
24	## Overview
25	Smartlead is the cold email platform of choice for high-volume senders.
26	Its killer features: unlimited mailboxes, automatic mailbox rotation, AI reply
27	categorization, and a unified master inbox. This skill covers setup from 0 to
28	sending at scale.
29
30	## Authoritative Foundations
31	- Smartlead Help Center — Connect mailboxes, enable warmup, set per-mailbox limits and rotation, and route replies to the master inbox.
32	- Eric Nowoslawski — Cold email infrastructure — Cold email infra at scale — 2 inboxes/domain, backup inboxes, Creative Ideas testing.
33	- Google and Yahoo — Bulk sender requirements (2024) — Authenticate with SPF, DKIM, and DMARC, keep spam complaints below 0.3%, and honor unsubscribes quickly.
34
35	## When to Use
36	- "Set up Smartlead"
37	- "Smartlead campaign setup"
38	- "Add mailboxes to Smartlead"
39	- "Smartlead optimization"
40
41	## Step-by-Step Process
42
43	### Phase 1: Infrastructure Setup
44	Before creating a single campaign:
45	- Connect 3-5 sending domains per client (secondary domains, not primary)
46	- Add 2-3 mailboxes per domain (Google Workspace or M365)
47	- Verify DNS: SPF, DKIM, DMARC, custom tracking domain
48	- Warm up each mailbox 2-3 weeks before sending (start 5/day, ramp to 50/day)
49	- Set up master inbox: unified view of all replies across all mailboxes
50
51	### Phase 2: Campaign Creation
52	Per campaign:
53	- Lead list: Upload CSV, map fields, segment by persona
54	- Sequence: 3-5 step sequence, plain text only, no images/HTML
55	- Mailbox assignment: Auto-rotate across 15-25 mailboxes, max 30-50 emails/day/mailbox
56	- Sending window: Mon-Thu 6am-8pm prospect timezone, 45-90 second delay between sends
57	- Tracking: Open tracking OFF (hurts deliverability in 2026), reply tracking ON
58
59	### Phase 3: AI Reply Categorization
60	Train Smartlead's AI to categorize replies:
61	- Positive: "Interested," "Let's talk," "Send more info" → label INTERESTED
62	- Neutral: "Not now," "Maybe next quarter" → label NOT NOW
63	- OOO: Auto-replies, vacation → label OOO, auto-pause
64	- Negative: "Stop emailing," "Remove me" → label UNSUBSCRIBE, auto-block
65	- Wrong person: "I'm not the right person" → label WRONG CONTACT, flag for update
66
67	### Phase 4: A/B Testing
68	Test at campaign level:
69	- Subject line: 2-4 variants, rotate evenly, measure reply rate
70	- Opener: Different hook patterns, same body
71	- CTA: Soft vs direct, measure meeting rate
72	- Send time: Morning vs afternoon by timezone, auto-optimize
73
74	### Phase 5: Analytics & Optimization
75	- Campaign health: Reply rate (>2% healthy), bounce rate (<3% healthy), spam rate (<0.1%)
76	- Mailbox health: Per-mailbox bounce and spam rates, rotate out unhealthy mailboxes
77	- Sequence optimization: Which step drives most replies, trim low-performing steps
78	- A/B winner declaration: After 500+ sends per variant, declare winner and auto-apply
79
80	## Output Format
81	Smartlead setup playbook with: infrastructure checklist, campaign configuration,
82	AI categorization rules, A/B test plan, and optimization cadence.
83
84
85
86	## Quality Check
87
88	Before delivering, verify:
89	- [ ] All required sections are complete
90	- [ ] Output matches the user's stated need
91	- [ ] Named frameworks are cited for key recommendations
92	- [ ] No vague claims — every recommendation has a specific action
93	- [ ] Deliverable is ready for operational use, not just conceptual
94
95	## Common Pitfalls
96
97	1. Skipping research. Building output without understanding the specific context. Fix: always gather required inputs before producing deliverables.
98	2. Generic output. "Improve your process" without concrete steps. Fix: every recommendation must include a specific action, timeline, and owner.
99	3. Missing framework citations. Advice without named authorities. Fix: ground every recommendation in a cited framework from a recognized authority.
100
101	## Execution Artifacts
102
103	- `references/framework-notes.md` — Eric Smartlead scale, Pat verify gate, AI categorization
104	- `templates/output-template.md` — infrastructure + AI labels + Clay gate deliverable
105	- `scripts/check-output.py` — local checklist validator
106	This skill includes lightweight artifacts the agent can load on demand:
107	- `references/clay-enrollment-handoff.md` — Clay/loops → Smartlead push + custom variables
108	- `references/eric-nowoslawski-outbound.md` — Eric Nowoslawski agency infra (canonical Smartlead operator)
109	- `references/pat-spielmann-outbound-copy.md` — verify-before-send (Pat Spielmann)
110	- `references/leadmagic-waterfall.md` — loop enrich chain before push
111	- `references/cli-workflow-patterns.md` — `lm integrations smartlead push`
112	- `references/gtm-experts-outbound-index.md` — expert router
113	Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.
114
115	## Implementation Depth
116
117	Use this section when the user asks for a finished asset, not a high-level explanation.
118
119	### Diagnostic Questions
120
121	1. What is the primary motion: founder-led, sales-led, product-led, partner-led, or lifecycle-led?
122	2. Which ICP tier is the output for: small business, mid-market, enterprise, or mixed?
123	3. What proof is available today: customer stories, usage data, third-party validation, screenshots, or none?
124	4. What system will execute the work: CRM, sequencer, warehouse, support desk, product analytics, or manual workflow?
125	5. What decision will the user make from this output: launch, prioritize, route, rewrite, score, coach, or measure?
126
127	### Framework Application
128
129	Map the recommendation explicitly to the named frameworks in this skill:
130
131	- Smartlead Best Practices: apply only the part that directly improves the requested deliverable.
132	- Eric Nowoslawski Cold Email Infrastructure: apply only the part that directly improves the requested deliverable.
133	- Outreach — Sales Engagement Cadence Design: apply only the part that directly improves the requested deliverable.
134
135	### Deliverable Standard
136
137	A strong output from this skill includes:
138
139	- A crisp diagnosis of the current situation
140	- A recommended path with tradeoffs, not a generic list
141	- A concrete artifact the user can use immediately: table, script, checklist, scorecard, sequence, dashboard spec, or implementation plan
142	- A measurement plan with leading and lagging indicators
143	- Risks and edge cases called out before execution
144
145	### Adaptation Rules
146
147	- For small business: reduce complexity, shorten time-to-value, and prioritize owner/operator clarity.
148	- For mid-market: include workflow ownership, handoffs, integrations, and enablement assets.
149	- For enterprise: include governance, risk, procurement, stakeholder mapping, and proof requirements.
150
151
152	## Related Skills
153	- email-deliverability, domain-infrastructure, inbox-setup, cold-email-strategy, cold-email-copywriting
154