Campaign logo

Campaign

Community
roslove44
campaign

Orchestrates the production of a coherent visual kit across several platforms from a single brief. Use when the user wants "a campaign", "the same thing on Facebook/LinkedIn/X", "a visual kit", "all the visuals for a launch" or "the same announcement on every network". Runs the interview once, consolidates the message from project.md, then delegates to the platform skills (facebook-*, linkedin-*, x-*, og-image). Requires a project with its brand.md (and ideally its project.md) in place.

Overview

Publisherroslove44
Repositorybrand-artisan
Skill namecampaign
Stars
5
Forks
0
Bundled files
Instructions only
LicenseMIT
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 roslove44 on GitHub. Read the source before you install it.

Installation

Install the Campaign 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.
    https://github.com/roslove44/brand-artisan/tree/main/skills/campaign
  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/roslove44/brand-artisan.git /tmp/brand-artisan
mkdir -p .claude/skills
cp -r /tmp/brand-artisan/skills/campaign .claude/skills/campaign
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Campaign 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 Campaign 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 Campaign 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.

campaign: a multi-platform visual kit

Goal: produce a coherent set of visuals for several platforms from a single brief. This skill does not create the images itself: it runs the interview once, consolidates the message, then delegates to the platform skills. It is the conductor; the building blocks stay og-image, facebook-*, linkedin-*, x-*.

Guardrail: do not duplicate. This skill never restates a platform's dimensions, ratios or constraints: it hands off to the skill concerned and lets it apply its own specs. Its own scope is the brief and the coherence of the whole.

0. Prerequisites (blocking)

  • Resolve <project> (from the arguments, otherwise ask).
  • Check templates/<project>/ and brands/<project>/brand.md. Missing -> STOP: /new-project <project> first (CLAUDE.md rule).
  • Read brands/<project>/brand.md (visual identity) and brands/<project>/project.md (substance, voice, claims). project.md is the foundation of the brief: if it is missing, ask for the tone and the claims rather than inventing them.

1. Interview (the heart of it: get the best out of the user)

Run it once, leaning on project.md so you propose rather than make them guess:

  1. Goal of the campaign: a launch, promoting a tool, an announcement, hiring, an event… (a clear goal means a clear message).
  2. Target platforms: Facebook, LinkedIn, X, generic OG (and combinations).
  3. Formats wanted per platform: profile/header, post, carousel, or leave each platform skill's defaults.
  4. Key message: propose 2-3 angles drawn from project.md (the real product, the value proposition), then have them pick and refine. Never invent a figure or a promise outside project.md.
  5. Carousel mechanics if there are any: a story, one card per product, a top N, a tutorial, before/after (see the *-carousel skills).

Present the choices that are missing, don't settle them in silence (CLAUDE.md principle #1).

2. Consolidated brief

Write a single master message (headline + standfirst), then its tone variation per platform: same substance, adapted register. Default landmark (to be adjusted against project.md):

PlatformRegister
LinkedInProfessional, added value (insight, business benefit)
XDirect, punchy, concise
FacebookAccessible, general audience
OG (sharing)Neutral, descriptive, straight to the point

The master message and all its variations stay within the claims authorized by project.md.

3. Fan-out: delegate to the platform skills

For each (platform, format) pair retained, apply the matching skill, passing it the already adapted message and the project. Don't re-frame the dimensions: the platform skill takes care of that.

NeedSkill to apply
Generic share previewog-image
Facebook profile / bannerfacebook-page
Facebook postfacebook-post
Facebook carouselfacebook-carousel
LinkedIn profile / bannerlinkedin-page
LinkedIn postlinkedin-post
LinkedIn carousellinkedin-carousel
X profile / headerx-page
X postx-post
X carouselx-carousel

Cross-platform coherence (campaign's own job):

  • The same master message everywhere, only the tone and the framing change.
  • The same visual choices where it makes sense (the same light or dark background, the same logo variant), within what brand.md allows.
  • Coherent slugs: prefix with the campaign where useful (e.g. launch-facebook-post, launch-x-post) to group the output.

4. Verify and recap

  • npm run typecheck -> green; npm run build -> writes every PNG.
  • Check each visual against its platform skill's criterion (dimensions, weight, opaque background).
  • Coherence of the kit: read the whole set side by side; message aligned, tone adapted with no break in the brand, claims conforming to project.md.
  • Recap: list the files produced per platform, and restate the master message you settled on. A LinkedIn document post is delivered as its PDF, not as its slides (see linkedin-carousel).

Success criterion: a multi-platform kit where every visual respects its platform's specs (delegated), carried by one coherent master message varied by tone, and entirely anchored in brand.md and project.md.

Frequently asked questions

What does the Campaign AI skill do?

Orchestrates the production of a coherent visual kit across several platforms from a single brief. Use when the user wants "a campaign", "the same thing on Facebook/LinkedIn/X", "a visual kit", "all the visuals for a launch" or "the same announcement on every network". Runs the interview once, consolidates the message from project.md, then delegates to the platform skills (facebook-*, linkedin-*, x-*, og-image). Requires a project with its brand.md (and ideally its project.md) in place.

Why use Campaign on TypingMind?

Because you install it once and use it with any model. Campaign 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 Campaign in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/roslove44/brand-artisan/tree/main/skills/campaign. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Campaign?

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 Campaign?

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

Is the Campaign AI skill free?

Yes. It is published on GitHub by roslove44 under the MIT 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 👇