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

launch-campaign

Skill8 starsChanged 6 months agoMITView on GitHub

Pre-flight audit of a Smartlead campaign before going live, then start it. Verifies sequences, mailboxes, leads, schedule, warmup health, and tracking-domain CNAME. Refuses to launch with broken state. Use when the user says they want to launch, start, go live with, or kick off a campaign that's already configured.

7 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

10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run these in order. If any check fails, surface it and ASK before proceeding.

    line 19
  2. Very specific:

    If status is ACTIVE already, tell the user and stop.

    line 27
  3. Distinctive:

    Should return ≥1. Zero = won't send anything.

    line 35
  4. Distinctive:

    Should return ≥1. Zero = nothing to send from.

    line 43
  5. Distinctive:

    Should return ≥1. Zero = ask user if empty start is intentional.

    line 51
  6. Very specific:

    Should resolve to open.sleadtrack.com..

    line 73
  7. Very specific:

    If campaign timezone is America/New_York but lead list is heavy on EU domains, surface it.

    line 88
  8. Distinctive:

    After launch, tell the user to check back in 1-2 hours:

    line 107
  9. Distinctive:

    Bounce rate: if it crosses 5% in the first hour, PAUSE immediately and triage

    line 114
  10. Distinctive:

    Sends per hour: should match expected throughput from schedule + mailbox count

    line 115

“Common” is measured: kept by at least 6 in 10 of the 7 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.

/launch-campaign

You're doing pre-flight checks on a campaign that's been built, then starting it.

What you need from the user

  • Campaign ID to launch
  • (Optional) Permission to auto-fix obvious issues vs. just report them

Pre-flight checklist

Run these in order. If any check fails, surface it and ASK before proceeding.

Check 1 — Campaign exists and is in DRAFTING / PAUSED status

smartlead campaigns get <id> --output json | jq '{id, name, status}'

If status is ACTIVE already, tell the user and stop.

Check 2 — At least 1 sequence step

smartlead campaigns sequences <id> --output json | jq 'length'

Should return ≥1. Zero = won't send anything.

Check 3 — At least 1 mailbox assigned

smartlead campaigns email-accounts <id> --output json | jq 'length'

Should return ≥1. Zero = nothing to send from.

Check 4 — Leads uploaded

smartlead leads list <id> --output json | jq 'length'

Should return ≥1. Zero = ask user if empty start is intentional.

Check 5 — All assigned mailboxes are warmed up

smartlead campaigns email-accounts <id> --output json | \
  jq -r '.[].email_account_id' | \
  while read mb_id; do
    smartlead accounts get $mb_id --output json | \
      jq -r --arg id "$mb_id" '{id: $id, warmup: .warmup_details.status, reputation: .warmup_details.warmup_reputation}'
  done

Flag any mailbox with warmup.status != ENABLED or reputation < 80%.

Check 6 — Custom tracking domain CNAME resolves (if tracking is enabled)

For each mailbox with custom_tracking_domain set:

dig +short CNAME <tracking_domain>

Should resolve to open.sleadtrack.com.. If empty, link wrapping and open pixels will fail.

Check 7 — Settings sanity

smartlead campaigns get <id> --output json | jq '.settings'

Flag if:

  • enable_ai_esp_matching: true AND campaign has both Gmail+Outlook senders (see docs/learnings/esp-matching-analysis.md)
  • track_settings includes DONT_TRACK_* but recipient list looks audit-aware (Big Tech etc.)
  • Schedule looks wrong (sending on weekends, 24/7 window, etc.)

Check 8 — Schedule timezone matches recipient audience

If campaign timezone is America/New_York but lead list is heavy on EU domains, surface it. Sending at 9 AM ET = 3 PM CEST = late afternoon for EU recipients.

Launch decision

Once all checks pass (or user explicitly waves off warnings):

smartlead campaigns start <id>

Confirm activation:

smartlead campaigns get <id> --output json | jq '.status'
# Should now show "ACTIVE"

First-hour monitoring

After launch, tell the user to check back in 1-2 hours:

smartlead campaigns analytics <id>

What to watch:

  • Bounce rate: if it crosses 5% in the first hour, PAUSE immediately and triage
  • Sends per hour: should match expected throughput from schedule + mailbox count
  • Auto-replies / out-of-office: Smartlead handles these (stop-on-auto-reply default)

If something goes wrong post-launch

To stop sending (drains queued sends — this is what you usually want):

smartlead campaigns stop <id>

NOT pause — pause doesn't drain queued sends and the analytics endpoint lies about it (see docs/learnings/settings-api-quirks.md quirk 6).

Reference

  • docs/learnings/settings-api-quirks.md — campaign status verbs, pause-drain behavior
  • docs/learnings/esp-matching-analysis.md — why to disable AI ESP matching
  • docs/learnings/mailbox-warmup-best-practices.md — what "warmed up" actually means

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.