# Agentic marketing prompts

From https://www.supermarketers.ai/agentic-marketing
Use them in Claude Code (best), Cowork, or a Claude Project with the files attached.

## 1. Find your first agent job

List every marketing task I did in the last two weeks from my calendar, docs and
this list: [paste]. For each one, score 1 to 5 on: how often it repeats, whether it
uses data from a tool, and how much judgment the final call needs.
Rank them. The best first agent job repeats weekly, uses real data and needs judgment
only at the end. Recommend one, and say what "done" looks like as something a
script could check.

## 2. Capture the Brain

Read everything in brain/sources/: sales call transcripts, support tickets, our best
posts, the strategy doc. Build three files:
brain/icp.md (who buys, in their exact words, with the file each quote came from),
brain/positioning.md (what we believe, each point with its proof file),
brain/questions.md (every question a buyer asked, in their words, ranked by how often
it comes up and how close it is to a purchase).
Don't invent anything. Mark gaps [CHECK]. Stop after the top 10 questions and ask me
to approve them before you continue.

## 3. Turn a repeated job into a skill

I'm going to do [job] by hand while you watch. Ask me why at each step.
When we're done, write .claude/skills/[job-name]/SKILL.md: a description that says
when to use it, numbered steps a new hire could follow, the exact output format,
and where the draft gets saved. Keep it to one job and one output.

## 4. Build the checker

Write .claude/agents/fact-checker.md. It reads a draft and checks every number, name,
quote and claimed outcome against brain/sources/. It can only read files. It returns
a table of claim, source, pass or fail, and fix, and never rewrites the draft.
Use a different model from the one that writes the drafts.

## 5. Set a goal the agent can finish

/goal Refresh every page listed in brain/refresh-queue.md with /page-refresh.
Done when every draft in drafts/ passes python3 gates/check_draft.py with exit code 0
and the fact-checker returns PASS for each one. Don't publish anything.

## 6. Build the competitor-gap backlog

From this week's AI visibility data, list every tracked buying prompt where an AI
engine names a competitor and doesn't name us. For each one: the prompt, the engine,
which competitor, which source the engine cited, and the page of ours that should
answer it (or "no page"). Sort by how close the prompt is to a purchase.
This is the backlog. Don't propose new topics outside it.

## 7. The weekly report (for a schedule)

Run /weekly-visibility-report. If any data source fails, stop and say which one.
Compare to last week. End with three actions, each tied to a row in the report.
Mark the report unreviewed.

## 8. Turn an edit into a lesson

Here's your draft and the version I approved: [paste both].
List every change I made. For each one, write the rule it shows, with the reason and
the before and after. Add them to lessons.md with today's date. Then tell me which
skill or voice-guide section each lesson should change, and propose the exact edit.