skills/facebook-ads/SKILL.md
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".
npx skillsauth add OpenClaudia/openclaudia-skills facebook-adsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
Before building any campaign, establish:
If the user has not provided these, ask before proceeding.
| Objective | Use When | KPI | |---|---|---| | Brand Awareness | Introducing a new brand/product | Ad recall lift, reach | | Traffic | Driving website visits | CPC, CTR, landing page views | | Engagement | Growing social proof | CPE, shares, comments | | Lead Generation | Collecting leads in-platform | CPL, lead quality score | | Conversions | Driving purchases/sign-ups | CPA, ROAS, conversion rate | | Catalog Sales | E-commerce dynamic ads | ROAS, 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.
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).
| Seed Source | Lookalike % | Use Case | |---|---|---| | Purchasers (top 25% LTV) | 1% | Best for conversion campaigns | | All purchasers | 1-3% | Broad conversion targeting | | Email subscribers | 1-2% | 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+).
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.
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 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.
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).
| Funnel Stage | % of Budget | Objective | Audience | |---|---|---|---| | Top of Funnel | 20-30% | Awareness/Video Views | Broad/Lookalike 3-5% | | Middle of Funnel | 10-20% | Traffic/Engagement | Lookalike 1-3%, Interest | | Bottom of Funnel | 40-50% | Conversions | Retargeting, Lookalike 1% | | Retention | 10-20% | Conversions | Existing 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.
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).
Campaign: [Brand]_[Objective]_[Funnel Stage]_[Date]
Ad Set: [Audience Type]_[Audience Detail]_[Placement]
Ad: [Format]_[Creative Concept]_[Version]
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.
data-ai
Generate images using AI (OpenAI GPT Image or Stability AI). Use when the user asks to generate an image, create an AI image, make an illustration, or produce artwork from a text prompt.
development
Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb. Use when the user asks about a domain's traffic, monthly visits, traffic sources, audience countries, or wants to compare/benchmark sites against competitors.
development
Find which ChatGPT search queries mention a given brand. Tests long-tail queries against ChatGPT's web-search-enabled model and reports which ones surface the brand. Use when the user asks to "find queries for [brand]", "check GEO visibility", "which queries mention [brand]", "geo query finder", "find AI mentions", or "test ChatGPT queries for [brand]".
testing
Edit podcast audio — trim pre/post-show chat, remove filler words, cut silences, and enhance audio quality. Use when the user asks to edit a podcast, clean up audio, remove fillers, trim a recording, or improve voice quality.