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

create-paid-campaign

Skill14 starsChanged 3 months agoMITView on GitHub

Create and evaluate a focused paid-media test. Use for Meta, Google, LinkedIn, TikTok, or another ad network when the user needs audience and offer strategy, finished ads, creative direction, landing-page congruence, budget logic, policy awareness, and a measurement decision.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Verify current network formats, targeting availability, and policy when they affect the work.

    line 17
  2. Distinctive:

    Do not invent customer proof, performance benchmarks, targeting precision, or policy clearance.

    line 27
  3. Distinctive:

    Write finished network-native ads.

    line 31
  4. Distinctive:

    Use current auction/input evidence when available.

    line 41
  5. Distinctive:

    keep, revise, stop, and reallocation conditions.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Create a paid campaign

Design the smallest paid test that can answer a consequential question. Do not treat spend, reach, or clicks as the strategy.

Establish the ad contract

Choose one network, one audience segment, one temperature, one offer, and one destination per test. Verify current network formats, targeting availability, and policy when they affect the work.

Define:

  • costly moment and audience qualification;
  • promise, mechanism, proof, and main objection;
  • offer and proportionate next action;
  • what the landing page must repeat;
  • primary business signal and diagnostic platform metrics.

Do not invent customer proof, performance benchmarks, targeting precision, or policy clearance.

Create discriminating variants

Write finished network-native ads. Variants must test different hypotheses—not synonyms. For each, provide the required components, such as primary text, headline, description, CTA, search headline, or video hook.

Brief creative around product evidence, mechanism, or a real transformation. Keep ad, creative, offer, and destination congruent. Identify claims or visual behavior that must be verified before launch.

Budget learning

Use current auction/input evidence when available. Fund the minimum viable test that can answer its question, or recommend zero spend.

Specify:

  • budget ceiling and allocation;
  • sample or observation requirement;
  • primary decision signal;
  • diagnostics and guardrails;
  • keep, revise, stop, and reallocation conditions;
  • attribution limits and likely confounders.

Evaluate one network/segment at a time. A high click-through rate cannot override poor qualified conversion or a safety/compliance failure.

Deliver

Return the audience/offer contract, finished ad set, creative direction, destination requirements, budget/test table, evaluation plan, and exact human approval boundary. Never launch, spend, upload audiences, or change a live account without explicit approval for that action.

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.