Marketing Campaign Planner Agent Skill

Marketing campaign planner

A campaign is a bounded push around one story. If it has no end date and no single story, it is a

program, not a campaign, and it should be planned as one.

One story

Every campaign carries exactly one idea. Channels change the format; they never change the meaning.

Campaigns that say slightly different things on each channel produce no compounding — the audience

sees three impressions and remembers none.

Write the story as a sentence before anything else: for whom, what changes, why now. If it takes

a paragraph, it is not ready and the campaign will not hold.

The "why now" is the part most campaigns skip and the part that produces urgency. Without it you are

asking people to act on something that would be equally true next quarter.

Objective

One primary number with a date, and the leading indicator that will move first. Campaigns with

several equal objectives cannot be sequenced, because every tradeoff has an argument on both sides.

State what you are *not* optimizing for. A launch optimizing for signups will make choices that cost

brand, and that is fine — as long as it was chosen.

Channels: choose, do not spray

Pick channels by where the audience already is and which formats you can actually produce well. Two

channels executed properly beat five done adequately, and the fifth channel usually consumes the

attention that would have made the first two work.

Sequence them. Most campaigns run everything at once and learn nothing:

• Owned first — your list and existing audience. Cheapest, fastest signal, and it tells you

whether the message lands before you pay to amplify it.

• Earned next — press, partners, communities. Needs lead time; brief them before launch.
• Paid last, amplifying what already worked. Paying to distribute an untested message is how

budget disappears.

Timeline

Work backward from the launch date, and place the asset freeze at least several days before

anything ships. Campaigns slip because copy is still being edited while ads are being trafficked.

Front-load anything with a dependency you do not control — press, partners, legal review, app-store

approval. These are what actually move launch dates.

Plan the two weeks *after* launch as deliberately as the launch itself. Most campaigns are designed

as a spike and produce one.

Assets

List every asset by channel with owner and due date. Derive them from the one story rather than

writing each independently — independently written assets drift, and the drift is invisible until

they are seen side by side.

The offer

A campaign amplifies an offer; it cannot rescue a weak one. Before planning channels, check the

offer itself: is the value obvious, is the risk to the buyer low, and is there a reason to act now

that is not manufactured?

The levers, in rough order of effect: what is included, the risk reversal (guarantee, trial, pilot),

the payment structure, and only then the price. Discounting is the weakest of these and the most

reached for, and it trains the audience to wait for the next discount.

If the offer only works with urgency attached, the urgency is doing the work and it will not survive

contact with a considered buyer.

Before committing

• If the primary channel underdelivers by half, does the campaign still work?
• What is the single point of failure, and what is the fallback?
• Who says go, and what would make them say no?
• What happens if it works far better than expected — can delivery, support, and inventory absorb

it?

Return contract

The story in one sentence, objective and leading indicator, channels with sequencing rationale,

timeline with the freeze date, asset list with owners, risks with fallbacks, and what is explicitly

out of scope.