Easy~25 min setup

A Campaign Brief and Content Calendar From One Prompt

Turn a marketing goal into a real plan: objective, audience, message, a week-by-week content calendar, and the metrics you'll judge it by — built on your brand and your channels.

A campaign is a plan with a date on every piece — not a goal and a hope.

The gap between 'we should promote the launch' and an executable plan is the work most campaigns skip. Store your brand, audience, and channels, and one prompt turns a goal into a brief plus a dated calendar you can actually run.

Most campaigns live as a vague intention and a flurry of last-minute posts. The calendar is what turns intention into shipped work.

A goal without a dated calendar is a wish. The calendar is where a campaign becomes real.

The first calendar is a draft to react to, not a contract. Move things, cut what's thin, and you'll have a plan you believe in faster than building it from blank.

At a glance
ComplexityEasy
Tools neededClaude Pro or above, Claude Desktop → Cowork mode, on macOS or Windows, Claude Projects
Time to build~25 min first time · ~10 min per campaign after that
Best forOwner or marketing lead who plans and runs the campaigns — B2B services and small product companies

What this solves

Campaigns that start as 'let's promote this' and end as a scramble — no dated plan, no owner per piece, no way to answer whether it worked.

The problem

Someone decides it’s time to promote the new offering, and the plan is “let’s do a campaign.” A few posts go out when somebody remembers, the email goes late because no one owned it, and three weeks later the question “did the campaign work?” can’t be answered because nobody defined what working would look like. The energy was there. What was missing was the unglamorous middle: an objective, a clear audience, a message, and a dated calendar that says exactly what ships when. That middle is the difference between a campaign and a scramble.

The fix is generating the whole plan up front, so execution is just following it.

Ingredients

  • Claude SubscriptionsCowork and Projects aren't available on the free plan
  • Platforms & ModesCowork runs in the desktop app only — not on web or mobile. This recipe builds a brief and a calendar across files — multi-step work that runs in Cowork
  • Claude ProjectsYour brand, your audience, and your channels stay the same campaign to campaign. A Project stores them so every plan is built on what you actually are and where you actually reach people
Built on these guides

How it works

1
A Claude Project

You run campaigns repeatedly, and your brand, audience, and channels are constant. A Project stores them so every campaign plan is grounded in your real positioning and the channels you actually use — not generic marketing advice.

  1. Open Claude Desktop and click Cowork in the mode selector across the top (Chat · Cowork · Code).
  2. In the left panel, find Projects and click the + button.
  3. Choose Start from scratch. Name the project “Campaigns” or “Marketing Plans” and let Claude set up its folder.
  4. You’ll know it worked when the project appears in the left panel with its own folder and an instructions field.
~25 minutes the first time. ~10 minutes per campaign after that
2
Set Up Your Workspace

Your project has a folder on your computer — that’s where the two working files live.

  1. Ask Claude, right in the project: “Create two files in this project’s folder: brand.md and channels.md. Leave them empty — I’ll fill them in.” (Or create them yourself in any text editor and save them into the project folder.)
  2. Fill in both files using the descriptions below.
  3. Confirm Claude can see them: ask “List the files you can see in this project.” Both filenames should come back. If they don’t, see If It Doesn’t Work.

brand.md

Who you are, who you serve, and the messages you keep coming back to — so the campaign sounds like you and speaks to the right person.

Example: “Audience: operations leaders at growing services firms. Positioning: we make AI usable for non-technical teams. Messaging pillars: governance, simplicity, real outcomes. Voice: direct, concrete, no hype.”

channels.md

Where you actually publish and what each channel is good for, plus your realistic cadence — so the calendar fits your capacity instead of an ideal.

Example: “LinkedIn (2x/week, thought leadership), email list (1x/week, deeper value), blog (1x/week, SEO + proof), no paid right now. One person executes — don’t plan more than ~5 pieces a week.”

3
Prompt Claude

Open your Project in Claude Cowork. Give Claude the specifics for this run, ask for the main output, then follow up for any additional pieces you want. The exact wording for each prompt — with what it’s asking for and why — is in What you actually type below.

4
Review What Comes Back

Check three things before you commit to the plan:

  1. The calendar fits your actual capacity. A beautiful plan that needs ten pieces a week from a team of one is a plan that fails in week two. Match it against channels.md and your real time. Cut before you commit, not after you fall behind.
  2. The metrics connect to the goal. “Engagement” is not a goal. If the objective is demo requests, the metrics should ladder to that — not vanity numbers that look good and prove nothing. Push back if success is defined as likes.
  3. The angles are distinct, not the same post five ways. Three supporting angles should give you genuinely different things to say. If they’re rephrasings, the campaign will feel repetitive by week two. Ask for real variety.

Before you commit: does this match what’s actually happening in your business? If sales can only handle ten demos a week, a goal of thirty creates a different problem. Your knowledge of capacity downstream keeps the plan honest.

What you actually type

Name your files explicitly the first few runs, and ask Claude to show its work on anything that matters.

Prompt AGenerateCopy this
Ask for the plan
Build a four-week campaign to promote [offering] with the goal of [e.g. 30 demo requests]. Using `brand.md` and `channels.md`: define the objective and audience, the core message and three supporting angles, then a week-by-week content calendar with a specific piece per channel per slot, and the metrics we'll judge it by.
Prompt BFollow upCopy this
Follow up
Week 3 is overloaded for one person — rebalance it across the four weeks.
Prompt CRefineCopy this
Follow up
Draft the LinkedIn post for week 1, slot 1, in our voice.
What you get back

A campaign brief with five labeled parts: the objective and audience, one core message with three supporting angles, a week-by-week calendar naming a specific piece per channel per slot, and the metrics that ladder to the goal. Expect roughly a page of brief plus the calendar grid, sized to the cadence in your channels.md. If the three angles are one point rephrased or the metrics are vanity numbers, it missed — send it back.

What this does not do
  • It doesn't execute the calendar. The pieces still have to be drafted, scheduled, and shipped — the plan only makes that work visible and dated.
  • It only knows the capacity `channels.md` admits to. Pad the cadence and the plan pads with it, then fails in week two.
  • It can't measure the campaign. The metrics it defines are targets; pulling the actual numbers is your analytics tool's job.

If it doesn’t work

  • No Cowork tab in Claude Desktop — update the app to the latest version and confirm you’re on a paid plan; Cowork isn’t on the free tier. On Windows, Cowork also needs the Virtual Machine Platform feature enabled — if the tab still won’t appear, that’s the fix.
  • Claude can’t see brand.md or channels.md — the files aren’t in the project’s folder, or they’re in a different folder than the one the project owns. Open the project, check which folder it points to, and move the files there. Then re-run “list the files you can see.”
  • The calendar plans for a team you don’t have — your channels.md is stating an ideal cadence, not your real one. Rewrite it with the honest number (“one person executes — no more than ~5 pieces a week”), then ask Claude to rebalance the four weeks against it. The plan should survive your busiest week, not your best one.
  • The metrics come back as engagement and reach — the goal in your prompt wasn’t measurable, so Claude reached for vanity numbers. Restate it in countable terms — “the goal is 30 demo requests; give me metrics that ladder to that” — and the success measures sharpen with it.

Extra credit

Small additions that pay back the next time you run it.

  • Scheduled cadence — once the calendar’s set, use a scheduled task to surface each week’s slots every Monday so nothing slips. See the Scheduled Tasks guide.
  • Draft as you go — keep the campaign Project open and draft each piece in it, so everything inherits the same brand and message.
  • Live dashboard — turn the metrics into a live artifact that refreshes from your analytics so you can see the campaign working without rebuilding a report.

“The campaigns that ship are the ones where every piece already had a date before the week started.”

What this teaches you about Claude Cowork

The recipe is one application. The principles apply to everything you’d hand to Claude.

The plan is the missing middle. Campaigns rarely fail for lack of energy; they fail because the dated, owned, measurable plan never got made. The recipe produces exactly that middle in one pass, so the team’s energy lands on execution instead of figuring out what to do.

Capacity is a real constraint, and the file enforces it. Storing your honest cadence in channels.md means Claude plans for the team you have, not an imaginary one. A plan you can actually run beats an ambitious one you abandon.

Metrics decided up front are the only ones you trust later. Defining success before the campaign runs is what makes “did it work?” answerable. Decide the measure first, and the post-mortem becomes useful instead of an argument.

Who this is for

Owner or marketing lead who plans and runs the campaigns in B2B services and small product companies (2–50 employees).

The pain: Campaign ideas that never become a dated, executable plan

The outcome: Every campaign starts with a brief and a calendar the team can actually run

Published June 17, 2026 · 0 views