Marketing Campaigns logo

Marketing Campaigns

OrganizationPopular
anthropics
marketing-campaigns

Drafting campaigns and ads as staged drafts, from acquisition and seasonal pushes to lifecycle sends such as win-backs, pre-arrival messages, and presale or last-call notices, choosing audiences and placements by intent, allocating budget across campaigns, and reviewing campaign results with their attribution caveats. Not needed for listing copy (catalog-listings) or overall performance questions (performance-insights).

Overview

Publisheranthropics
Repositorycommerce-agents
Skill namemarketing-campaigns
Stars
3K
Forks
574
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Marketing Campaigns AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/commerce-agents.git /tmp/commerce-agents
mkdir -p .claude/skills
cp -r /tmp/commerce-agents/merchant-agent/skills/marketing-campaigns .claude/skills/marketing-campaigns
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Marketing Campaigns in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Marketing Campaigns on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Marketing Campaigns is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Marketing and campaigns

Below, "audience" means whoever this operation reaches: customers, guests, subscribers, or past attendees.

A review reads the campaign figures; a draft, a copy change, or a budget move is staged. Scheduling, sending, and spending happen in the host's campaign system after approval; say so when you hand a change over.

Where each fact comes from

  • Take spend, revenue, return, and status from get_campaign_performance fetched in this conversation, and read them against the goal the operator stated. When no goal has been stated, ask what the campaign was for before calling it good or bad.
  • Report attributed revenue as the channel's claim about what it drove, in those words, and state the caveat wherever it would change the conclusion (a renewal send credited with renewals that happen every year anyway).
  • Report a short window or thin spend as too early to read, with the date it becomes worth reading, taken from the campaign's dates and the local time you were given.
  • Draft in the brand voice saved in memory; when none is saved and tone matters, ask once and use the answer from then on.
  • Take a product fact in copy from the listing record (get_listing) or from the operator; a spec, a savings amount, or a superlative that neither supplies stays out.

Campaign shapes

  • Give every draft one audience intent and one measurable it is meant to move, and pass them to stage_campaign as the audience and the objective.
  • The shapes differ only in those two fields. An acquisition push names people who have not bought before and first orders in the window; a win-back names people inactive for a set period and their activity a month later; a pre-arrival or last-call send names people with a date coming up and the add-on or sell-through it should move.
  • Write audience and placement as intent ("arriving in the next seven days"). The targeting settings live in the host's system; do not describe them as set.

Reviewing a campaign against its shape

  • Read return per shape: attributed revenue against spend for acquisition; for a retention send, what the audience did afterwards against that audience's usual rate. When the numbers hold no such baseline, say the send's effect cannot be separated from what the audience would have done anyway.
  • Report the two kinds of return side by side and say which measurable each campaign is judged on; do not rank them on one number.
  • Review the campaigns get_campaign_performance returned, and report a send it does not include as not visible to this flow.

Budget

  • Treat the total as fixed unless the operator says otherwise, so a recommendation to put more behind one campaign names the campaign that gets less.
  • Rest a reallocation on a measured difference in return, worded as an expectation. When the window is too short or the spend too thin, recommend waiting and give the date to look again.

Stage and preview

  • Stage a draft, a copy change, or a budget move with stage_campaign; a change to an existing campaign uses an id get_campaign_performance returned. Stage what was asked for: a copy refresh carries no budget change, a budget move no new copy, and a draft the operator asked for is staged even when a running campaign overlaps its audience, with the overlap noted beside the preview.
  • The guardrail you will meet here is the deployment's campaign budget cap; the alternative to offer is the same send at the cap.
  • After an apply, say where the send now sits in the host's campaign system; the send date and the spend are that system's to carry out.
  • End a review with present_metrics, with a sentence or two before it, and a draft or budget move with its preview.

Frequently asked questions

What does the Marketing Campaigns AI skill do?

Drafting campaigns and ads as staged drafts, from acquisition and seasonal pushes to lifecycle sends such as win-backs, pre-arrival messages, and presale or last-call notices, choosing audiences and placements by intent, allocating budget across campaigns, and reviewing campaign results with their attribution caveats. Not needed for listing copy (catalog-listings) or overall performance questions (performance-insights).

Why use Marketing Campaigns on TypingMind?

Because you install it once and use it with any model. Marketing Campaigns is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Marketing Campaigns in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/commerce-agents/tree/main/merchant-agent/skills/marketing-campaigns. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Marketing Campaigns?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Marketing Campaigns?

As many as you like. As long as a model supports skills, you can use Marketing Campaigns with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Marketing Campaigns AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇