Paid Advertising

Organization

LeadMagic

paid-advertising

Build and manage paid advertising campaigns across B2B platforms — LinkedIn Ads, Google Ads, Meta (Facebook/Instagram) Ads, TikTok Ads, and programmatic. Use when launching paid campaigns, allocating ad budget, selecting platforms, or optimizing paid acquisition. Triggers on: "paid ads", "LinkedIn ads", "Google Ads", "Meta ads", "Facebook ads", "TikTok ads", "advertising", "paid acquisition", "ad budget", "ad campaign", or any request about paid marketing.

Overview

Publisher	LeadMagic
Repository	`gtm-skills`
Skill name	`paid-advertising`
Stars	72
Forks	18
Bundled files	3
License	MIT
Links	Skill source Repository Homepage

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 Paid Advertising AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/LeadMagic/gtm-skills/tree/main/skills/analytics/paid-advertising
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.

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/analytics/paid-advertising .claude/skills/paid-advertising

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paid Advertising 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 Paid Advertising 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 Paid Advertising 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.

Paid Advertising

Overview

Paid advertising is a dial, not a switch. Start small, measure everything, double down on what works. B2B advertising is fundamentally different from B2C — smaller audiences, higher CPCs, longer conversion cycles. Platform selection matters more than budget size.

This skill covers platform selection, budget allocation, campaign structure, and measurement across the four major B2B ad platforms plus programmatic.

Authoritative Foundations

Meta Advantage+ campaigns — Use broad targeting with diversified creative, and feed server-side conversions so the algorithm optimizes on real outcomes.
Google Ads — Performance Max — Set conversion goals and audience signals, and exclude brand terms so PMax doesn't claim demand you already own.
LinkedIn Campaign Manager — Target by company, job function, and seniority; respect minimum audience sizes and use Lead Gen Forms for low-friction capture.

When to Use

"Launch paid ads"
"Which ad platform should I use?"
"Set up LinkedIn Ads"
"Allocate ad budget"
"Optimize Google Ads for B2B"
"Run Meta ads for SaaS"
"Measure ad ROI"

Step-by-Step Process

Phase 1: Platform Selection

Platform	Best For	CPC Range	Min Budget	B2B Fit
LinkedIn Ads	B2B targeting by title, company, industry	$5-15 CPC	$3-5K/mo	Highest — native B2B
Google Ads	Intent capture (search), retargeting (display)	$2-10 CPC	$2-5K/mo	High — capture demand
Meta (FB/IG)	Top-of-funnel awareness, retargeting	$1-5 CPC	$1-3K/mo	Medium — audience building
TikTok Ads	Brand awareness, younger demographics	$0.50-3 CPC	$1-3K/mo	Low-Medium — emerging B2B
Programmatic	Scale, retargeting, account-based	$2-8 CPM	$5-10K/mo	Medium — ABM

For most B2B SaaS, stack priority: LinkedIn (targeting) → Google (intent capture) → Meta (retargeting). Add TikTok and programmatic when the first three are profitable.

Phase 2: LinkedIn Ads Deep Dive

LinkedIn is the highest-intent B2B ad platform. Targeting by job title, company size, industry, and skills means you reach exactly your ICP.

Ad formats:

Sponsored Content: In-feed single image, carousel, or video. Best for awareness and content promotion.
Message Ads (InMail): Direct message to prospects. Higher engagement, higher cost. Best for event invites and demo offers.
Text Ads: Small sidebar/dashboard ads. Low CPC, low volume. Best for ongoing brand presence.
Document Ads: Lead gen forms attached to downloadable content. Highest conversion for gated assets.

Campaign structure:

Top-of-funnel: Sponsored content promoting educational content. CTA: "Read more" or "Download guide." Target: ICP title + industry.
Middle-of-funnel: Retargeting website visitors with case studies. CTA: "See how [similar company] achieved [result]."
Bottom-of-funnel: Message Ads to decision-makers who engaged. CTA: "Book a demo."

Budget: Start at $3-5K/mo. LinkedIn minimums are higher than other platforms. Test for 6-8 weeks before judging ROI.

Phase 3: Google Ads for B2B

Search campaigns: Bid on keywords your ICP searches: problem phrases ("[problem] solution"), competitor names ("[competitor] alternative"), category terms ("best [category] software").

Performance Max: Google's AI-driven campaign type. Combines search, display, YouTube, discovery, and Gmail. Feed it audience signals (customer lists, website visitors) and conversion goals. Works well for B2B when fed quality conversion data.

Budget: Start at $2-5K/mo. Monitor search terms report weekly. Add negative keywords aggressively — B2B search terms leak to consumer intent quickly.

Phase 4: Meta Ads for B2B

Meta's strength is audience building and retargeting, not intent capture.

Campaign types:

Lead Ads: Native forms within FB/IG. Lowest friction for gated content.
Retargeting: Website visitors, content engagers, video viewers.
Lookalike audiences: Seed from customer list or LinkedIn followers.

Budget: Start at $1-3K/mo. Meta needs 50+ conversions/week for algorithm optimization. Below that, manual bidding outperforms automated.

Phase 5: Measurement

Track everything. Every ad dollar must be attributable.

Platform pixels: LinkedIn Insight Tag, Meta Pixel, Google Ads conversion tag, TikTok Pixel. Install all four on your website.

UTM parameters: Standardize across all campaigns. utm_source=linkedin utm_medium=cpc utm_campaign=product_demo_q1. Consistent naming prevents attribution chaos.

KPIs by funnel stage:

Top-of-funnel: CPM, CTR, CPC (efficiency metrics)
Middle-of-funnel: Landing page conversion rate, lead quality
Bottom-of-funnel: Cost per demo, cost per opportunity, pipeline generated
ROI: Revenue attributed ÷ ad spend. Target: 3:1+ for B2B, but expect 6-12 month payback on enterprise deals.

Attribution: B2B sales cycles are 3-12 months. First-touch and last-touch both matter. Multi-touch attribution is ideal. At minimum: track UTM source through CRM to closed-won.

Output Format

Paid advertising plan with: platform selection rationale, budget allocation by platform and funnel stage, campaign structure per platform, creative requirements, pixel/tracking setup, and KPI dashboard.

Quality Check

Platform selection matches ICP and budget
All four major pixels installed (LinkedIn, Google, Meta, TikTok)
UTM parameters standardized across all campaigns
Campaign structure has clear funnel stage per campaign
Budget allocation per platform with rationale
Measurement: cost per demo, pipeline, closed revenue (not just leads)

Common Pitfalls

LinkedIn as the only platform. LinkedIn gets you targeting but misses intent capture (Google) and retargeting (Meta). Run all three.
Not enough budget to test. LinkedIn at $1K/mo won't produce meaningful data. Minimum $3K/mo for 6-8 weeks to validate.
B2C metrics for B2B. Cost per lead is meaningless if those leads don't become pipeline. Measure cost per opportunity and revenue.
No retargeting. 97% of first-time visitors don't convert. Retargeting captures the other 97%.
Creative fatigue. Same ad for 6 weeks burns out. Rotate creative every 2-3 weeks. Test multiple variants simultaneously.

Execution Artifacts

references/framework-notes.md — named frameworks, citation anchors, and operating assumptions
templates/output-template.md — copy-paste deliverable structure for the user
scripts/check-output.py — local checklist validator for required sections This skill includes lightweight artifacts the agent can load on demand: Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.

Related Skills

ad-creative-strategy: Creative development and testing
a-b-testing: Experiment framework for ad tests
attribution: Multi-touch attribution models
gtm-metrics: Revenue attribution and ROI

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 Paid Advertising AI skill do?

Why use Paid Advertising on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeadMagic/gtm-skills/tree/main/skills/analytics/paid-advertising. 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 Paid Advertising?

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 Paid Advertising?

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

Is the Paid Advertising 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

Ad Creative

coreyhaines31

CommunityPopular

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad…

Ads

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,'…

Ai Seo

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine…

Analytics

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Paid Advertising

Overview

Authoritative Foundations

When to Use

Step-by-Step Process

Phase 1: Platform Selection

Phase 2: LinkedIn Ads Deep Dive

Phase 3: Google Ads for B2B

Phase 4: Meta Ads for B2B

Phase 5: Measurement

Output Format

Quality Check

Common Pitfalls

Execution Artifacts

Related Skills

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now