agentleFS
MattSezginMattSezgin/unofficial-smartlead-cli/.claude/skills/create-campaign/SKILL.md

create-campaign

Skill8 starsChanged 6 months agoMITView on GitHub

Create a new Smartlead campaign from scratch — name, schedule, settings, sequences, sender mailboxes, and leads. Walks the user through the 6 setup steps interactively, with sane defaults for cold email. Use when the user says they want to create / launch / start a new campaign, set up an outbound campaign, or build something from scratch in Smartlead.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask these one at a time (don't overwhelm with a 10-question form):

    line 14
  2. Distinctive:

    Stop on reply → don't keep emailing people who already replied

    line 62
  3. Distinctive:

    Ask the user if they want to override any of these.

    line 64
  4. Distinctive:

    Ask the user for their sequence — usually 2-4 emails.

    line 68
  5. Very specific:

    If the user has a CSV ready, invoke /upload-leads to handle this step.

    line 101
  6. Very specific:

    Before invoking smartlead campaigns start <id>, verify:

    line 105
  7. Distinctive:

    If any check fails, surface it.

    line 112
  8. Distinctive:

    If bounce rate >5% in the first day, pause and triage.

    line 134

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Before running: verify exact flag names with smartlead <command> --help. Flag shapes shown below are illustrative — confirm against the actual CLI.

/create-campaign

You're walking the user through creating a brand-new Smartlead campaign end-to-end.

What you need from the user

Ask these one at a time (don't overwhelm with a 10-question form):

  1. Campaign name — e.g., "Q1 Founders Outbound"
  2. Client (optional) — if they run a multi-tenant Smartlead account, which client this campaign belongs to. Skip if not applicable.
  3. Target audience size — rough lead count. Drives mailbox sizing.
  4. Lead source — do they have a CSV ready, or should we set up the campaign empty?
  5. Sender mailboxes — by tag, by ID, or "use all my warmed-up mailboxes"
  6. Schedule — timezone, sending window (default: 9-5 weekdays in the user's TZ)

The 6 setup steps

Step 1 — Create the campaign shell

smartlead campaigns create --name "<name>" \
  ${CLIENT_ID:+--client-id $CLIENT_ID}

Save the returned campaign_id.

Step 2 — Set the schedule

smartlead campaigns schedule <campaign_id> \
  --timezone "America/New_York" \
  --days 1,2,3,4,5 \
  --start-hour 09:00 \
  --end-hour 17:00 \
  --min-time-between-emails 10 \
  --max-new-leads-per-day 50

Defaults to weekday business hours unless the user specifies otherwise. days: 0=Sunday through 6=Saturday.

Step 3 — Settings (deliverability-safe defaults)

smartlead campaigns settings <campaign_id> \
  --no-track-email-open \
  --no-track-link-click \
  --no-ai-esp-matching \
  --stop-on-reply \
  --stop-on-auto-reply

Why these defaults:

  • Open/click tracking OFF → plain-text feel, fewer spam signals (see docs/learnings/mailbox-warmup-best-practices.md)
  • AI ESP matching OFF → it routes Google recipients wrong (see docs/learnings/esp-matching-analysis.md)
  • Stop on reply → don't keep emailing people who already replied

Ask the user if they want to override any of these.

Step 4 — Add the email sequence

Ask the user for their sequence — usually 2-4 emails. If they have a draft, paste it. Otherwise offer a starter template.

smartlead campaigns sequences <campaign_id> --add-step \
  --seq-number 1 \
  --subject "{{personalization_hook}}" \
  --body @email1.html \
  --delay-days 0

smartlead campaigns sequences <campaign_id> --add-step \
  --seq-number 2 \
  --subject "Re: {{previous_subject}}" \
  --body @email2.html \
  --delay-days 4

(Same for each follow-up step.)

Step 5 — Assign sender mailboxes

# By IDs
smartlead campaigns email-accounts <campaign_id> --add --ids <id1>,<id2>,<id3>

# Or by tag
smartlead accounts tags get --tag-id <tag_id> --output json | jq -r '.[].id' > mailboxes.txt
smartlead campaigns email-accounts <campaign_id> --add --ids-file mailboxes.txt

Sizing rule of thumb: at golden config (15 sends/mailbox/day), 1 mailbox can handle ~75 leads/week. For 1,000 leads, plan ~15 mailboxes.

Step 6 — Upload leads

If the user has a CSV ready, invoke /upload-leads to handle this step. Otherwise leave the campaign without leads — they can add them later.

Pre-launch checklist (before starting)

Before invoking smartlead campaigns start <id>, verify:

  • ✅ At least 1 sequence step exists
  • ✅ At least 1 mailbox assigned
  • ✅ Leads uploaded (or user confirms empty start is OK)
  • ✅ Schedule + settings are sane
  • ✅ All assigned mailboxes have completed warmup (/audit-mailbox-config)

If any check fails, surface it. Don't auto-fix without asking.

Start the campaign

smartlead campaigns start <campaign_id>

Or if they want to schedule a future start:

smartlead campaigns schedule <campaign_id> --schedule-start-time "2026-06-01T13:00:00Z"
smartlead campaigns start <campaign_id>

After launch — what to monitor

Tell the user to check back in 24-48 hours with:

  • smartlead campaigns analytics <campaign_id> — sends + bounce rate
  • /check-deliverability <campaign_id> — full audit

If bounce rate >5% in the first day, pause and triage.

Reference

  • docs/learnings/campaign-cloning-runbook.md — full 6-step API details
  • docs/learnings/settings-api-quirks.md — field translation gotchas
  • docs/learnings/mailbox-warmup-best-practices.md — sender pool health

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.