agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/launch-campaign/SKILL.md

launch-campaign

Skill1 starsChanged 3 months agoMITView on GitHub

Run a campaign end-to-end — brief, assets, tool configuration, approvals, launch, monitoring, close-out — for email, social, or paid channels. Run whenever strategy calls for a time-bounded push or a standing email program.

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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Launch: Run templates/launch-checklist.md — every box.

    line 19

“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

/launch-campaign — Brief to Close-Out

Inputs: knowledge/strategy.md (the campaign must serve it), knowledge/offer.md, knowledge/audience-profiles.md, knowledge/tool-registry.md. Agents: campaign-manager leads; copywriter writes; funnel-builder preps destinations; tools-operator executes; growth-analyst instruments. Method: knowledge/methods/digital-channel-strategy.md, knowledge/methods/persuasion-principles.md (within ethics), knowledge/methods/funnel-and-measurement.md.

Steps

  1. Brief. templates/campaign-brief.md: one message, one audience, one action; success metric and kill threshold set before anything is built. Match message to traffic temperature (cold = value/introduction, warm = proof/offer, hot = ask/true urgency).
  2. Confirm the destination. Where does the click land, and does it message-match? If missing or weak → /build-funnel first.
  3. Produce assets. Copywriter drafts (2–3 angles where testing is possible); visuals per brand; every asset passes voice + compliance including the Claims Review Checklist. Pull real proof from knowledge/research/social-proof.md where claims need backing. Paid ad campaigns: the mechanics (account structure, bidding, pacing, kill rules) belong to /run-ads — this skill briefs it, it executes.
  4. Configure the tool. tools-operator sets up the campaign in the platform (MCP → browser → guided): list/segment, schedule, tracking (UTMs, conversion events). Test send/preview verified.
  5. Approvals, batched. One approval request covering what applies: spend (budget cap), outbound (templates + list), publishing (the asset batch). Refs logged; nothing fires without them.
  6. Launch. Run templates/launch-checklist.md — every box. Go live. First-hour check: delivering/serving, no errors.
  7. Monitor at the brief's cadence. Paid: watch cost-per-result daily at first; kill at threshold without sentiment. Email sequences: monitor deliverability and replies; route replies (B2B positives → sales-developer/deal-closer).
  8. Close out. At end date or kill: final numbers vs target, learning, do-differently — filled into the brief. Feed the weekly scorecard.

Before you start

  1. Required inputs: knowledge/strategy.md approved (active) — the master gate; knowledge/offer.md at seeded+; a live destination (else /build-funnel first).
  2. Scan knowledge/decision-log.md for tags channel, budget, content — respect prior kill decisions on this channel/angle.
  3. Gate check: batch the applicable gates in one request (step 5); verify budget headroom in knowledge/budget.md before requesting spend.

If things go wrong

  • Approval doesn't arrive by the planned launch date → slide the date; park in knowledge/pending.md. Never launch on an assumed yes.
  • Platform/tool failure mid-flight → tools-operator ladder; if sends/spend can't be verified, pause the campaign rather than fly blind.
  • Metrics hit the kill threshold → execute the pre-committed kill without renegotiating it mid-flight; log honestly.

Outputs

A launched (and eventually closed-out) campaign at knowledge/campaigns/YYYY-MM-<slug>.md (one campaign = one file; assets inline or in an adjacent YYYY-MM-<slug>-assets/ folder). Close with the report per templates/skill-report.md.

Writeback

Campaign file; approvals to knowledge/approvals-log.md; results to knowledge/results-history.md; spend to knowledge/budget.md; learnings to knowledge/decision-log.md (tag: channel) when they change how we operate.

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.