AGENT SKILLBY KOSTJA94
Meta ads
AT A GLANCE
Meta ads is a paid ads agent skill from kostja94. Guides Meta (Facebook/Instagram) Ads setup, campaign structure, audience targeting, and creative optimization. It is published in the kostja94/marketing-skills GitHub repository (691 stars) under the MIT license. Install it with: npx skills add kostja94/marketing-skills --skill meta-ads
- SOURCE REPOSITORY
- kostja94/marketing-skills (opens GitHub in a new tab)
- REPO STARS
- SOURCE REPOSITORY
- LICENSE
- MIT
- CATEGORIES
- SKILL.MD SIZE
- 3.3 KB87 LINES
QUICK ANSWER
- WHAT IT IS01
- Guides Meta (Facebook/Instagram) Ads setup, campaign structure, audience targeting, and creative optimization. What sets it apart is how it narrows paid media into one specific workflow rather than a broad, generic prompt.
- INPUTS02
- Context for paid media: your goals, audience, constraints, and any source material the skill asks for.
- OUTPUT03
- A ready-to-use result for paid media: the analysis, copy, or recommendations the agent produces.
INSTALL
One command adds this skill from its source repository.
npx skills add kostja94/marketing-skills --skill meta-adsREAD THE SKILL.MD BELOW BEFORE YOU RUN IT. SKILLS INSTRUCT YOUR AGENT.
SKILL.MD
The full file, as published in the source repository. Copy it, download it or open it on GitHub.
ON THIS PAGE · 9
Paid Ads: Meta Ads#
Guides Meta (Facebook/Instagram) Ads setup, campaign structure, audience targeting, and creative optimization. Meta excels at demand generation and visual products; use when creating demand or when creative assets are strong.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Campaign Structure#
Hierarchy: Campaign → Ad Set → Ad (3 levels)
Principle: One objective per campaign. Multiple campaigns for the same objective split budget and data, slowing the algorithm's learning phase. Consolidate by objective; focus on clean structure and data-led decisions.
Account
├── Campaign: Prospecting
│ ├── Ad Set: Lookalike 1%
│ └── Ad Set: Broad (Advantage+)
├── Campaign: Retargeting
└── Campaign: TestingNaming: META_[Objective]_[Audience]_[Offer]_[Date] (e.g., META_Conv_Lookalike-Customers_FreeTrial_2024Q1)
Advantage+ & Automation#
| Feature | Use |
|---|---|
| Advantage+ Shopping Campaigns | E-commerce; automatic audience discovery |
| Dynamic Ads | Product catalog; auto-generated creative |
| Automatic Placements | Let Meta optimize across Feed, Stories, Reels |
| Advantage+ Audience | Broad targeting; algorithm finds converters |
Provide diverse creative assets to enable multiple ad formats; algorithm performs better with variety.
Campaign Objectives#
| Objective | Use when |
|---|---|
| Awareness | Reach; brand recall |
| Traffic | Clicks to site |
| Conversions | Leads; sales; app installs |
| Engagement | Video views; post engagement |
Audience Targeting#
| Type | Best for |
|---|---|
| Lookalikes | Base on best customers (by LTV), not all customers |
| Interest/behavior | Broad; let algorithm optimize |
| Advantage+ | Automated; fewer manual controls |
| Retargeting | Website visitors; engagers; custom audiences |
Exclusions: Existing customers; recent converters (7–14d).
Creative Best Practices#
- Image: Clear product; before/after; human faces; text <20%
- Video (15–30s): Hook 0–3s; problem 3–8s; solution 8–20s; CTA 20–30s
- Placements: Feed (FB/IG); Stories/Reels; vertical for Stories
- Volume: 3–5 ad variants per ad set for testing
Optimization#
- Learning phase: 50+ conversions per ad set per week to exit; avoid frequent changes during learning
- CBO vs ABO: Campaign Budget Optimization consolidates spend; use when scaling
- Frequency: <3 to avoid fatigue
- Creative refresh: Plan continuous testing; creative fatigue is a main lever—refresh when performance drops
Tracking#
- Meta Pixel + Conversions API: Server-side for better attribution
- Events API: App events; server-to-server
Pre-Launch Checklist#
- Pixel installed; Conversions API configured
- Conversion events firing correctly
- Landing page mobile-friendly; fast load
- 3+ ad creatives per ad set
- Audience exclusions set
Related Skills#
- paid-ads-strategy: Channel selection; creative frameworks; budget allocation
- landing-page-generator: LP for paid traffic
- analytics-tracking: Conversion tracking; ROAS
FAQ
07 QUESTIONS
01What is the Meta ads agent skill?
Guides Meta (Facebook/Instagram) Ads setup, campaign structure, audience targeting, and creative optimization. It is listed under paid ads in the 100xLab agent skills directory.
02How do I install Meta ads in Cursor, Claude Code, or Codex?
Run npx skills add kostja94/marketing-skills --skill meta-ads in the project where you want it, then ask your agent for the skill by name. The --skill flag installs only Meta ads, not every skill in the repository.
03What does the Meta ads SKILL.md cover?
The SKILL.md includes sections on Campaign Structure, Advantage+ & Automation, Campaign Objectives, Audience Targeting, Creative Best Practices and Optimization. Read the full text on this page or in plain markdown at /resources/agent-skills/kostja94-marketing-skills--meta-ads--16uffha/raw.
04Which agents can use Meta ads?
Meta ads installs with the cross-agent skills installer (npx skills add), which sets it up for agents such as Claude Code, Cursor and Codex. Each agent loads the SKILL.md when you ask for the skill by name.
05What license is Meta ads under?
The kostja94/marketing-skills repository declares the MIT license. Read the license file in the repository before you copy or redistribute the skill.
06Is Meta ads free to use?
Reading, copying and installing Meta ads costs nothing: it is published in a public GitHub repository under the MIT license. Reuse and redistribution follow that license.
07Where is the source of Meta ads?
Meta ads comes from https://github.com/kostja94/marketing-skills, which has 691 GitHub stars. The SKILL.md is at https://github.com/kostja94/marketing-skills/blob/HEAD/skills/paid-ads/platforms/meta-ads/SKILL.md. The author is kostja94.
Need an agent workflow built around your stack?
Tell us the workflow you want automated. We reply within 4 working hours (IST).
ATTRIBUTION
Meta ads was written by its original authors and is published in kostja94/marketing-skills (opens GitHub in a new tab) under the MIT license. All rights stay with the original authors.
100xLab did not write, maintain or endorse this skill. This page lists it for discovery. Repo stars belong to the source repository, not to the skill. Review any skill before you install it.