agentleFS
cwinvestmentscwinvestments/memstack/skills/marketing/facebook-ad/SKILL.md

memstack-marketing-facebook-ad

Skill425 starsChanged 5 months agoMITView on GitHub

Use this skill when the user says 'facebook ad', 'FB ad', 'Meta ad', 'Instagram ad', or needs social media ad copy with targeting, creative direction, and A/B test plans for Meta Ads Manager. Do NOT use for Google search ads or organic social content.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill activates, output:

    line 13
  2. Distinctive:

    If the user hasn't provided details, ask:

    line 43
  3. Distinctive:

    Must match: [Interest 1] AND [Interest 2]

    line 94
  4. Distinctive:

    Write 3 copy variations for each hook type:

    line 111
  5. Distinctive:

    Use line breaks for readability (no walls of text)

    line 177
  6. Distinctive:

    Avoid: Cluttered backgrounds, tiny text, stock photo look

    line 186
  7. Distinctive:

    Start with: Lowest cost (automatic bidding)

    line 214
  8. Distinctive:

    Never: Set bid cap too low, the algorithm won't spend and won't learn

    line 217
  9. Distinctive:

    Use Meta's built-in A/B test tool for clean attribution

    line 238

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Facebook Ad: Creating Meta ad campaign...

Creates complete ad campaigns with audience targeting, ad copy variations, creative direction, budget allocation, and A/B testing protocol for Meta Ads Manager.

Activation

When this skill activates, output:

Facebook Ad: Creating Meta ad campaign...

Then execute the protocol below.

Context Guard

ContextStatus
User says "Facebook ad", "FB ad", "Meta ad", "Instagram ad"ACTIVE
User needs social media ad copy with targetingACTIVE
User wants to run paid campaigns on Meta platformsACTIVE
User wants Google Search or Display adsDORMANT: use Google Ad
User wants organic social media contentDORMANT: not an ad skill

Common Mistakes

MistakeWhy It's Wrong
"Target everyone"Broad audiences burn budget. Start narrow (1-5M), expand after finding winners.
"One ad, one audience"Always test 3-5 ad variations per ad set. Meta's algorithm needs options.
"Start with $5/day"Too little for the algorithm to learn. Minimum $20/day per ad set for meaningful data.
"Judge ads after 24 hours"Meta needs 50+ conversions per ad set per week to exit learning phase. Wait 3-7 days.
"Use stock photos"UGC-style creative outperforms polished studio content 2-3x on Meta.

Protocol

Step 1: Gather Campaign Requirements

If the user hasn't provided details, ask:

  1. Product/service: what are you promoting? (name, price, URL)
  2. Objective: leads, sales, traffic, or brand awareness?
  3. Target audience: who is the ideal customer? (age, interests, pain points)
  4. Budget: daily or monthly ad spend?
  5. Existing assets: do you have customer testimonials, product photos, or video?
  6. Previous campaigns: any past Meta ads data to build on?

Step 2: Define Campaign Structure

Build the campaign using Meta's three-tier hierarchy:

Campaign (1 objective)
├── Ad Set 1: [Audience A], $[budget]/day
│   ├── Ad 1: [Hook A + Creative A]
│   ├── Ad 2: [Hook B + Creative A]
│   └── Ad 3: [Hook A + Creative B]
├── Ad Set 2: [Audience B], $[budget]/day
│   ├── Ad 1: [Hook A + Creative A]
│   ├── Ad 2: [Hook B + Creative A]
│   └── Ad 3: [Hook A + Creative B]
└── Ad Set 3: [Lookalike/Retargeting], $[budget]/day
    ├── Ad 1: [Social proof hook]
    ├── Ad 2: [Urgency hook]
    └── Ad 3: [Testimonial creative]

Campaign objective mapping:

GoalMeta ObjectiveOptimization Event
Email signupsLeadsLead form submission
Product salesSalesPurchase
Website trafficTrafficLanding page views
App installsApp PromotionApp install
Brand awarenessAwarenessReach or ThruPlay
Webinar signupsLeadsLead form submission

Step 3: Build Audience Targeting

Audience A: Interest-based (cold):

  • Age: [range]
  • Gender: [if relevant]
  • Location: [countries/regions]
  • Interests: [3-5 relevant interests]
  • Behaviors: [purchase behavior, device usage]
  • Audience size target: 1-5 million

Audience B: Narrowed interest stack:

  • Must match: [Interest 1] AND [Interest 2]
  • Exclude: [competitors' audiences or existing customers]
  • Audience size target: 500K-2M

Audience C: Lookalike:

  • Source: Customer list, website visitors, or video viewers
  • Lookalike %: Start at 1% (closest match), test up to 3%
  • Country: Same as primary market

Retargeting audiences (create separately):

  • Website visitors (last 30 days): exclude purchasers
  • Video viewers (75%+ watched): last 60 days
  • Engagement (Instagram/Facebook): last 90 days
  • Cart abandoners: last 14 days

Step 4: Write Ad Copy Variations

Write 3 copy variations for each hook type:

Hook Type 1: Problem-Agitation:

Primary text:
[Problem question that stops the scroll]

[Agitation, what happens if they don't solve it]

[Introduce your solution in 1-2 sentences]

[Key benefit 1]
[Key benefit 2]
[Key benefit 3]

[CTA: Click below to [desired action]]

Headline: [Benefit-driven, 5-8 words]
Description: [Supporting detail or urgency, 20 words max]
CTA button: [Learn More / Shop Now / Sign Up / Get Offer]

Hook Type 2: Social Proof:

Primary text:
"[Customer testimonial quote: specific result]"

[Bridge: Explain how others are getting the same result]

Here's what you get:
✓ [Benefit 1]
✓ [Benefit 2]
✓ [Benefit 3]

[CTA with urgency or limited offer]

Headline: [Result-focused, 5-8 words]
Description: [Star rating, customer count, or guarantee]
CTA button: [Get Started / Try Free / Shop Now]

Hook Type 3: Direct Offer:

Primary text:
[Bold claim or stat that grabs attention]

[1-2 sentences explaining the offer]

What's included:
→ [Item/benefit 1]
→ [Item/benefit 2]
→ [Item/benefit 3]

[Urgency: Limited time / spots / bonus]

[CTA: Get yours before [deadline]]

Headline: [Offer + urgency, 5-8 words]
Description: [Price, discount, or guarantee]
CTA button: [Get Offer / Claim Discount / Buy Now]

Ad copy rules:

  • Primary text: 125 characters visible before "See more": front-load the hook
  • Headline: 40 characters max for full display
  • Description: 25 characters max on mobile
  • Use line breaks for readability (no walls of text)
  • Emojis: 1-2 max, only if audience-appropriate

Step 5: Creative Direction

Image ads (1080x1080 or 1080x1350):

  • Style: UGC (user-generated content) feel outperforms polished studio
  • Text overlay: Keep under 20% of image area
  • Include: Product in use, face showing emotion, before/after, or bold text overlay
  • Avoid: Cluttered backgrounds, tiny text, stock photo look

Video ads (9:16 for Reels/Stories, 1:1 for Feed):

  • Hook: First 3 seconds must stop the scroll (movement, text, question)
  • Length: 15-30 seconds for cold traffic, 30-60 seconds for retargeting
  • Structure: Hook → Problem → Solution → Proof → CTA
  • Captions: Always add, 85% of videos are watched without sound
  • Thumbnail: Custom frame that works as a static image

Creative testing matrix:

TestVariableHold Constant
Test 13 different hooks (first 3 sec)Same body, same audience
Test 2Image vs. Video vs. CarouselSame copy, same audience
Test 3UGC vs. polished creativeSame copy, same audience

Step 6: Budget Allocation & Bidding

Budget framework:

PhaseDurationDaily Budget/Ad SetGoal
Testing3-7 days$20-50Find winning ad + audience combos
Validation7-14 days$50-100Confirm CPA is sustainable
ScalingOngoing20% increase every 3-4 daysIncrease volume while holding CPA

Bidding strategy:

  • Start with: Lowest cost (automatic bidding)
  • Switch to: Cost cap once you know your target CPA
  • Set cost cap at: 1.2x your target CPA (gives algorithm room)
  • Never: Set bid cap too low, the algorithm won't spend and won't learn

Scaling rules:

  • Horizontal scaling: Duplicate winning ad set to new audiences
  • Vertical scaling: Increase budget 20% every 3-4 days (never more than 20%)
  • Kill rule: If CPA exceeds 2x target for 3+ days, pause and diagnose

Step 7: A/B Testing Protocol

Test priority order:

  1. Audiences (biggest impact): Test 3+ audiences first
  2. Creative format (image vs. video vs. carousel)
  3. Hook/headline (first thing people see)
  4. Body copy (supporting message)
  5. CTA (button text and offer framing)

Testing rules:

  • Change ONE variable at a time
  • Minimum budget: $20/day per variation
  • Minimum duration: 3-7 days (or 50+ conversion events)
  • Winner threshold: 20%+ better CPA with statistical significance
  • Use Meta's built-in A/B test tool for clean attribution

Testing log template:

Test #VariableVariation AVariation BWinnerCPA Difference
1AudienceInterest stack1% Lookalike
2CreativeUGC videoProduct image
3HookProblem QBold stat

Output Format

Deliver the complete campaign as:

# Meta Ad Campaign: [Product/Service Name]

## Campaign Settings
- **Objective:** [Objective]
- **Daily budget:** $[amount] ([X] ad sets × $[amount] each)
- **Optimization event:** [Event]
- **Schedule:** [Start date]: ongoing

## Audiences
### Ad Set 1: [Audience name]
[Targeting details]

### Ad Set 2: [Audience name]
[Targeting details]

### Ad Set 3: [Retargeting]
[Targeting details]

## Ad Copy
### Variation 1: [Hook type]
[Complete ad copy]

### Variation 2: [Hook type]
[Complete ad copy]

### Variation 3: [Hook type]
[Complete ad copy]

## Creative Direction
[Image/video specs and style notes]

## Budget & Timeline
[Phase breakdown with daily budgets]

## A/B Testing Plan
[Test priority queue with log template]

## Tracking Setup
- Meta Pixel: [events to track]
- UTM parameters: [structure]
- Conversion window: [7-day click, 1-day view recommended]

Completion

Facebook Ad: Complete!

Campaign objective: [Objective]
Ad sets: [Count] audiences
Ad variations: [Count] per ad set
Total ads: [Count]
Daily budget: $[amount]
Testing duration: [X] days before first optimization

Next steps:
1. Install Meta Pixel on your website (if not already done)
2. Upload custom audiences and create lookalikes
3. Create ads in Meta Ads Manager using the copy above
4. Set up conversion tracking events
5. Launch and wait 3-7 days before making changes
6. Review testing log weekly and kill underperformers

Level History

  • Lv.1: Base: Campaign structure (3-tier hierarchy), audience targeting (interest, narrowed, lookalike, retargeting), 3 copy formulas (problem-agitation, social proof, direct offer), creative direction (image + video specs), budget allocation by phase, bidding strategy, scaling rules, A/B testing protocol with priority order and log template. (Origin: MemStack Pro v3.2, Mar 2026)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.