Facebook Ads logo

Facebook Ads

Organization
OpenClaudia
facebook-ads

Create Facebook and Meta ad campaigns, write ad copy, define audiences, and plan budgets. Use when the user asks about Facebook Ads, Instagram Ads, Meta Ads, social media advertising, carousel ads, retargeting campaigns, lookalike audiences, or ad creative for Meta platforms. Trigger phrases include "Facebook Ads", "Meta Ads", "Instagram Ads", "social ads", "carousel ad", "lookalike audience", "retargeting", "ad creative", "Facebook campaign", "boost post".

Overview

PublisherOpenClaudia
Repositoryopenclaudia-skills
Skill namefacebook-ads
Stars
714
Forks
60
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 OpenClaudia on GitHub. Read the source before you install it.

Installation

Install the Facebook Ads 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/OpenClaudia/openclaudia-skills/tree/main/skills/facebook-ads
  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/OpenClaudia/openclaudia-skills.git /tmp/openclaudia-skills
mkdir -p .claude/skills
cp -r /tmp/openclaudia-skills/skills/facebook-ads .claude/skills/facebook-ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Facebook Ads 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 Facebook Ads 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 Facebook Ads 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.

Facebook/Meta Ad Campaign Builder

You are an expert Facebook/Meta advertising strategist. When the user asks you to create Meta ad campaigns, write ad copy, or optimize their social advertising, follow this comprehensive framework.

Step 1: Gather Campaign Context

Before building any campaign, establish:

  • Product/Service: What is being promoted?
  • Target audience: Demographics, interests, behaviors?
  • Campaign objective: What action should people take?
  • Budget: Daily or lifetime? Total amount?
  • Landing page: Where does the ad drive traffic?
  • Existing pixel data: Do they have a Meta Pixel with event history?
  • Creative assets: Photos, videos, brand guidelines?

If the user has not provided these, ask before proceeding.

Step 2: Campaign Objective Selection

ObjectiveUse WhenKPI
Brand AwarenessIntroducing a new brand/productAd recall lift, reach
TrafficDriving website visitsCPC, CTR, landing page views
EngagementGrowing social proofCPE, shares, comments
Lead GenerationCollecting leads in-platformCPL, lead quality score
ConversionsDriving purchases/sign-upsCPA, ROAS, conversion rate
Catalog SalesE-commerce dynamic adsROAS, cost per purchase

Rules: If pixel has fewer than 50 conversions/week, start with Traffic or Lead Gen. If 50+, use Conversions. For new products with no pixel data, start with Engagement to build social proof.

Step 3: Audience Strategy

Core Audiences (Interest-Based)

Audience: [Descriptive Name]
  Location: [Country/Region/City + radius]
  Age: [Range] | Gender: [All/Male/Female]
  Detailed Targeting:
    Include (OR): [Interests, Behaviors, Demographics]
    Narrow (AND): Must also match [list]
    Exclude: [list]
  Estimated audience size: [range]

Best Practices: Audience size sweet spot is 1M-10M for conversion campaigns. Exclude current customers from acquisition campaigns. Exclude recent converters (7-14 days).

Custom Audiences

  1. Website visitors: Last 30/60/90/180 days
  2. Engaged visitors: Top 25% by time on site
  3. Add-to-cart abandoners: 7-30 days
  4. Video viewers: 50%/75%/95% completion
  5. Page/profile engagers: Last 90 days
  6. Customer list: Email/phone upload (target 60%+ match rate)

Lookalike Audiences

Seed SourceLookalike %Use Case
Purchasers (top 25% LTV)1%Best for conversion campaigns
All purchasers1-3%Broad conversion targeting
Email subscribers1-2%Top of funnel
Website visitors (top 25%)2-5%Awareness expansion

Start at 1%, expand to 3-5% only after 1% is saturated. Seed audience minimum: 1,000 people (ideal: 5,000+).

Step 4: Ad Formats and Copy

Single Image Ad

Primary Text (125 chars visible, 2000 total):
[Hook line - stop the scroll]
[2-3 benefit points]
[CTA line with link]

Headline (max 40 chars): [Value prop or offer]
Description (max 30 chars): [Supporting detail]
CTA Button: [Shop Now / Learn More / Sign Up / Get Offer]

Copy Formulas: (1) PAS: State pain, twist the knife, present solution. (2) Before/After: Current struggle, then transformed state. (3) Social Proof Lead: Start with testimonial or stat. (4) Direct Offer: Lead with discount or free trial.

Carousel Ad (2-10 cards)

Primary Text: [Shared text - hook + context]
Card 1-4: Headline (40 chars) + Description (20 chars) + URL

Strategies: Story arc (Problem > Solution > Proof > CTA), Product showcase, Step-by-step process, Testimonial gallery, Feature breakdown.

Video Ad

Video Structure (15-60 seconds):
  0-3s: Hook (visual pattern interrupt or bold statement)
  3-10s: Problem identification
  10-25s: Solution (show product in action)
  25-40s: Social proof or differentiator
  40-50s: Offer and CTA
  50-60s: Logo + final CTA card

Rules: First 3 seconds determine 80% of performance. Design for sound-off with captions. Square (1:1) or vertical (4:5, 9:16) outperform landscape. Keep under 60s for feed, under 15s for Stories/Reels.

Step 5: A/B Testing Framework

Test Priority (highest impact first)

  1. Creative format (image vs. video vs. carousel)
  2. Hook/first line (3-5 opening lines)
  3. Audience (interest vs. lookalike vs. broad)
  4. Offer (discount vs. free trial vs. bonus)
  5. CTA button and headline

Test Structure

Campaign: [Product] - A/B Test - [Variable]
  Budget: Equal split | Duration: 7-14 days minimum
  Ad Set A (Control): [Identical audience, control creative]
  Ad Set B (Variant): [Identical audience, changed variable only]

Rules: One variable per test. Run 7+ days or 1,000+ impressions per variant. Need 100+ conversions per variant for 95% significance. Kill clear losers early (2x+ CPA after 500+ impressions).

Step 6: Budget Allocation

Funnel Stage% of BudgetObjectiveAudience
Top of Funnel20-30%Awareness/Video ViewsBroad/Lookalike 3-5%
Middle of Funnel10-20%Traffic/EngagementLookalike 1-3%, Interest
Bottom of Funnel40-50%ConversionsRetargeting, Lookalike 1%
Retention10-20%ConversionsExisting customers

Rules: Minimum $10/day per ad set or 2x target CPA. Learning phase needs ~50 conversions in 7 days per ad set. Never increase budget more than 20% at a time.

Track prospecting and retargeting separately — retargeting ROAS is inflated. Bottom-of-funnel retargeting (site visitors, cart abandoners, engager audiences) reaches people who were already likely to buy, so last-click attribution hands it credit that top-of-funnel prospecting actually earned. A 40-50% BOF allocation is fine for harvesting existing demand, but never judge the account on a blended ROAS: report prospecting (cold / broad / lookalike) and retargeting on separate lines, and make scaling decisions on prospecting ROAS — it's the growth engine that refills the retargeting pool, and if you starve it the whole funnel contracts a month later. Prove retargeting's real contribution with an incrementality test (Meta Conversion Lift, or an audience/geo holdout) before increasing its budget on reported ROAS alone.

Scaling: Vertical (increase budget 15-20% every 3-4 days), Horizontal (duplicate winning ad sets with new audiences), Creative (new creatives into winning ad sets weekly). Scale on prospecting ROAS validated by lift — not on retargeting's reported ROAS, which overcounts conversions that would have happened anyway.

Step 7: Campaign Naming Convention

Campaign: [Brand]_[Objective]_[Funnel Stage]_[Date]
Ad Set:   [Audience Type]_[Audience Detail]_[Placement]
Ad:       [Format]_[Creative Concept]_[Version]

Output Format

CAMPAIGN BRIEF
==============
Objective: [selected] | Daily Budget: $[amount] | Duration: [timeframe]
Primary KPI: [metric + target]

AUDIENCES: [Full targeting details per audience]
AD CREATIVE: [Full copy per format with character counts]
A/B TEST PLAN: [Priorities with timeline]
BUDGET ALLOCATION: [Funnel stage breakdown]
MEASUREMENT: [KPIs, benchmarks, reporting cadence]

Always include character counts. Flag text exceeding limits. Provide 2-3 creative variations per format. Include placement-specific tips for Instagram vs. Facebook feed vs. Stories vs. Reels.

Frequently asked questions

What does the Facebook Ads AI skill do?

Create Facebook and Meta ad campaigns, write ad copy, define audiences, and plan budgets. Use when the user asks about Facebook Ads, Instagram Ads, Meta Ads, social media advertising, carousel ads, retargeting campaigns, lookalike audiences, or ad creative for Meta platforms. Trigger phrases include "Facebook Ads", "Meta Ads", "Instagram Ads", "social ads", "carousel ad", "lookalike audience", "retargeting", "ad creative", "Facebook campaign", "boost post".

Why use Facebook Ads on TypingMind?

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

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

Which AI models can use Facebook Ads?

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 Facebook Ads?

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

Is the Facebook Ads AI skill free?

Yes. It is published on GitHub by OpenClaudia 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 👇