ads

Plan, optimize, and audit paid advertising campaigns across Google, Meta, LinkedIn, and other ad platforms.

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/agnivon/viral_thread_generator --skill ads-agnivon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ads
Source: https://github.com/agnivon/viral_thread_generator/tree/main/.agents/skills/ads
Command: npx skills add https://github.com/agnivon/viral_thread_generator --skill ads-agnivon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Running paid ads without a disciplined strategy burns budget on wrong audiences, weak creative, and premature kill decisions. This Skill turns an AI assistant into a performance marketer that plans campaigns, sets budgets, diagnoses underperformance, and audits live accounts using evidence-based rules instead of guesswork. ## Core Features & Use Cases - Campaign Strategy & Structure: Platform selection guidance (Google, Meta, LinkedIn, TikTok, X), naming conventions, budget allocation, and audience targeting frameworks for B2B and B2C. - Platform Playbooks & Decision Systems: Deep references for Meta (Andromeda-era creative strategy), LinkedIn B2B, Google Search, ABM, payback-period math, and retargeting frameworks with concrete kill/scale thresholds. - Audit Guardrails: Four-state pass/fail/unknown/NA scoring, benchmark discipline, and hard stops against unsafe actions like inventing negative keywords or summing conversions across attribution windows. - Use Case: A B2B SaaS team with $15k/month asks where to advertise; the Skill checks product context, recommends LinkedIn and Google Search, structures campaigns, and defines breakeven CPL targets from deal math. ## Quick Start Ask the assistant to plan a paid ads strategy for your product, including platform choice, budget split, and target CPA based on your deal size.

Frequently Asked Questions about ads

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan a paid advertising strategy for a B2B SaaS product?▼

Start with platform selection based on audience and price point: LinkedIn for job-title targeting, Google Search for high-intent keywords, and Meta for retargeting. Derive breakeven CPL from deal size times close rate, then structure campaigns with clear naming conventions and a 70/30 proven-to-testing budget split.

When should I kill or pause an underperforming ad?▼

Pause new ads after they spend 2-3x target CPL with zero conversions, and pause mature ads when CPL runs 1.5-2x over target. Never pause on a fixed CPA threshold without checking sample size, conversion lag, and learning-phase status first.

Should I use broad targeting or interest stacking on Meta ads?▼

In the Andromeda era, broad targeting with specific creative typically outperforms interest stacking. Put audience knowledge into the creative itself using identity-trigger keywords, and let the algorithm match each creative variant to the right segment.

Can I combine Meta and Google conversion counts into one total?▼

No. Meta's 7-day click and Google's 30-day windows use different attribution definitions, so summing them double-counts conversions. Report them side by side and use a neutral source like GA4 or your CRM for a blended view.

Why is blended LTV:CAC misleading for budget decisions?▼

Blended LTV:CAC hides per-plan variance under averaged ARPU, so a healthy-looking ratio can mask unprofitable plans. Use Payback Period (CAC divided by per-plan ARPU) instead, targeting a 3-12 month payback band before scaling spend on any plan.

What are the limitations of AI-driven ad account audits?▼

An audit can only grade what it can verify; missing data like a search terms report makes those checks unknown, not failed. Below 60% evidence coverage no health score should be given, and negative keywords must never be invented without actual search term data.