agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/plan-campaign/SKILL.md

plan-campaign

Skill14 starsChanged 3 months agoMITView on GitHub

Plan an executable product launch or growth campaign. Use for go-to-market plans, Product Hunt or community launches, channel strategy, campaign sequencing, growth experiments, budget allocation, lifecycle, referral, event plans, or turning a product goal into a focused campaign with assets and measurement.

2 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

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create the smallest campaign package that can ship, learn, and compound.

    line 11
  2. Distinctive:

    If the spine cannot fit in a short paragraph, narrow the campaign.

    line 26
  3. Distinctive:

    keep, revise, or stop rule.

    line 54
  4. Distinctive:

    must-have assets, with finished primary assets when possible.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Plan an executable campaign

Create the smallest campaign package that can ship, learn, and compound.

Write the campaign spine

Define:

  • Outcome: the observable business change.
  • Audience: one primary audience for this campaign.
  • Moment: why they care now.
  • Promise: the credible change.
  • Proof: what makes the promise believable.
  • Objection: the main reason they will not act.
  • Action: one proportionate next step.
  • Measurement: one primary signal and a small diagnostic set.

If the spine cannot fit in a short paragraph, narrow the campaign.

Choose channels by fit

Select the smallest channel set that covers the job:

  • Existing demand: search, comparison pages, marketplaces, launch directories.
  • Borrowed trust: communities, partners, creators, advocates.
  • Direct access: email, outreach, sales-assisted conversations.
  • Compounding attention: useful content, social distribution, owned audience.
  • Paid acceleration: only when message and conversion path are testable.

Choose from audience habitat, native format, proof, operator capacity, feedback speed, and destination readiness. For a named platform, verify current rules and norms when they affect the plan. Do not recommend a channel because it is fashionable.

Rank bets and budget learning

Force-rank opportunities before scoring them. Keep at most three active bets unless independent capacity exists. Treat budget as a constraint, not a strategy.

Give every experiment:

  • hypothesis and mechanism;
  • one intentional change;
  • audience and channel;
  • primary signal and diagnostic guardrails;
  • minimum useful observation window;
  • keep, revise, or stop rule.

Fund a test at the minimum level that can answer its question, or fund it at zero. Give each allocation a reallocation trigger and destination. Do not hide uncertainty behind precise forecasts.

For lifecycle work, use behavioral triggers, activation events, and suppression conditions. For referrals, earn retention first, bound rewards by economics, and add abuse controls before scaling.

Deliver

Return:

  1. campaign spine and strategic bet;
  2. channel roles and sequence;
  3. must-have assets, with finished primary assets when possible;
  4. lightweight schedule or run of show;
  5. experiment and budget table;
  6. measurement plan and decision date;
  7. owners and the final human approval boundary.

Separate must-have launch work from optional follow-up. Keep publishing, spend, credentials, and external writes behind explicit approval.

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.