Ad Creative Strategy logo

Ad Creative Strategy

Organization
LeadMagic
ad-creative-strategy

Develop ad creative strategy for B2B campaigns — creative formats per platform, testing methodology, creative fatigue management, UGC/AI-generated creative, and performance measurement. Use when creating ad creative, managing creative production, testing ad variants, or scaling creative output. Triggers on: "ad creative", "creative strategy", "ad copy", "ad design", "creative testing", "UGC ads", "ad fatigue", or any ad creative request.

Overview

PublisherLeadMagic
Repositorygtm-skills
Skill namead-creative-strategy
Stars
72
Forks
18
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Ad Creative Strategy 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/LeadMagic/gtm-skills/tree/main/skills/creative/ad-creative-strategy
  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/LeadMagic/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/creative/ad-creative-strategy .claude/skills/ad-creative-strategy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ad Creative Strategy 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 Ad Creative Strategy 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 Ad Creative Strategy 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.

Ad Creative Strategy

Overview

Creative is the single biggest lever in paid advertising performance. A great creative on a mediocre audience outperforms a mediocre creative on a perfect audience. This skill covers creative formats per platform, testing methodology, fatigue management, and scaling creative production.

Authoritative Foundations

  • The B2B Institute (LinkedIn) — 95:5 rule — Only about 5% of B2B buyers are in market at any time, so creative must build memory with the other 95% as well as convert the 5%.
  • Meta — Dynamic creative testing — Let the platform rotate headlines, images, and copy variants, then promote winners into fixed ads; test one variable family at a time.
  • LinkedIn Marketing Solutions — Ad creative best practices — Follow format specs, lead with the value in the first line, and refresh creative before frequency-driven fatigue sets in.
  • Ann Handley — Everybody Writes — Write ad copy that is specific, human, and about one idea; cut anything the buyer would skim past.

When to Use

  • "Create ad creative for LinkedIn"
  • "Develop a creative testing plan"
  • "Our ads are fatigued — refresh creative"
  • "What creative formats work on each platform?"
  • "Scale our ad creative production"
  • "AI-generated ad creative"

Step-by-Step Process

Phase 1: Creative Formats by Platform

LinkedIn Ads:

  • Single image: 1200x627px. 1-2 lines of text overlay. Best for: offers, events.
  • Carousel: 1080x1080px per card, 3-10 cards. Best for: storytelling, data.
  • Video: 3-30 seconds. Square (1:1) or vertical (4:5). Best for: product demos.
  • Document ads: PDF uploaded as carousel. Best for: guides, reports, templates.

Google Ads:

  • Responsive search ads: 15 headlines (30 chars), 4 descriptions (90 chars). Google mixes and optimizes. Feed all 15 — more assets = better performance.
  • Display: 1200x628, 300x250, 728x90, 160x600. Static or HTML5.
  • YouTube: 15-30 seconds skippable. Hook in first 5 seconds.

Meta (FB/IG):

  • Feed: 1080x1080 (square) or 1080x1350 (vertical). Video or static.
  • Stories: 1080x1920 (full vertical). 15 seconds max.
  • Lead forms: same creative specs, plus form questions.

TikTok:

  • 9:16 vertical video. 15-60 seconds. Native-looking (not polished corporate).
  • Hook in first 2 seconds. Text overlay. Captions. Trending audio optional.

Phase 2: Creative Testing Methodology

Always test: At minimum 2-3 variants running simultaneously. Never one creative at a time.

Test one variable at a time:

  • Headline/hook (most impact)
  • Visual style (photo vs illustration vs screenshot)
  • Offer/CTA (demo vs trial vs guide)
  • Social proof placement
  • Format (single image vs carousel vs video)

Testing cadence:

  • Launch 3-5 variants → run 7-14 days → kill underperformers → launch new variants against winners → repeat.

Platform minimums for statistical significance:

  • LinkedIn: 1,000+ impressions per variant
  • Google: 100+ clicks per variant
  • Meta: 50+ conversions per variant per week
  • TikTok: 5,000+ impressions per variant

Phase 3: Creative Fatigue Management

Creative fatigue = performance drops because audience has seen the ad too many times. Signs: CTR declining, CPC rising, frequency >3-4.

Prevention:

  • Rotate creative every 2-3 weeks.
  • Maintain 3-5 active variants per ad set.
  • Use platform automated creative refresh (Meta Advantage+ Creative).
  • Segment audiences to reduce overlap.

Phase 4: Scaling Creative Production

Traditional model: agency → brief → concept → production → 2-4 assets/month. $3-10K/month. Slow but polished.

AI-augmented model: 1 in-house creative + AI tools → 10-20 assets/week. $1-3K/month (tools + person). Fast, testable volume beats polished scarcity.

AI creative tools:

  • Ad copy: ChatGPT, Claude, Jasper (write multiple headline/body variants).
  • Image generation: Midjourney, DALL-E (concept visuals, backgrounds).
  • Video: Arcads, Creatify (AI-generated UGC-style ads from scripts).
  • Iteration: Canva AI, Adobe Firefly (resize, remix, translate).

The volume advantage: A $5K/month agency producing 4 polished assets/month loses to a $2K/month AI-augmented workflow producing 40 testable variants/month. Testing velocity beats production quality.

Output Format

Creative strategy document with: platform-specific format guide, testing plan (what to test first), fatigue management rules, creative production workflow, and creative asset tracker.

Quality Check

  • Creative formats matched to each active platform
  • Testing methodology defined (what variable, what sample size)
  • Fatigue prevention rules (rotation cadence, frequency caps)
  • Production workflow (who creates what, how fast)
  • Creative asset tracker (variant, launch date, performance)

Common Pitfalls

  1. One creative at a time. "Let's see how this performs" with no comparison. You can't optimize what you don't test.

  2. Polished over volume. A beautiful ad nobody sees loses to 10 rough variants that find the winning message.

  3. No fatigue monitoring. Same ad for 8 weeks with frequency >10. CTR drops 50%+. Rotate before performance degrades.

  4. Creative not matching platform context. A polished corporate video on TikTok looks like an ad. Native-looking content wins.

  5. Testing too many variables at once. Changed headline AND visual AND CTA. No idea which change caused the lift. One variable per test.

Execution Artifacts

  • references/framework-notes.md — Named frameworks and reference tables
  • templates/output-template.md — Deliverable shell for agent output
  • scripts/check-output.py — Lightweight deliverable validator

Related Skills

  • paid-advertising: Platform-specific ad setup
  • a-b-testing: Experiment design and statistical significance
  • graphic-design-gtm: Visual asset creation and sizing
  • copywriting: Ad copy and headline writing

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ad Creative Strategy AI skill do?

Develop ad creative strategy for B2B campaigns — creative formats per platform, testing methodology, creative fatigue management, UGC/AI-generated creative, and performance measurement. Use when creating ad creative, managing creative production, testing ad variants, or scaling creative output. Triggers on: "ad creative", "creative strategy", "ad copy", "ad design", "creative testing", "UGC ads", "ad fatigue", or any ad creative request.

Why use Ad Creative Strategy on TypingMind?

Because you install it once and use it with any model. Ad Creative Strategy 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 Ad Creative Strategy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeadMagic/gtm-skills/tree/main/skills/creative/ad-creative-strategy. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ad Creative Strategy?

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 Ad Creative Strategy?

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

Is the Ad Creative Strategy AI skill free?

Yes. It is published on GitHub by LeadMagic 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 👇