SkillMachine
All skills

Paid Ads Campaign Architect

Document

Account structure, targeting, budget, and platform-compliant RSAs — a launch-ready campaign plan from one brief.

Live output preview

Input Format: Input FormatOutputWatch the Output: Watch the Output

A plan is required to view this content

Choose a plan to access input format, sample outputs, and live previews.

View Plans →

About the skill

What it does

Takes your brief (objective, CPA/ROAS, budget, offer, audience) and produces an end-to-end paid ads campaign plan, optionally adding a platform-compliant Google RSA package. It first selects the platform by intent signal: Google for high-intent search, Meta for demand generation and visual products, LinkedIn for job-title-based B2B, TikTok for younger video audiences. It then builds the account → campaign → ad set → ad hierarchy, the [Platform]_[Objective]_[Audience]_[Offer]_[Date] naming convention, and a 70/30 test budget split (test phase) with 20-30% incremental scaling steps (3-5 day learning gaps).

For copy, it applies three proven frameworks: PAS (Problem-Agitate-Solve), BAB (Before-After-Bridge), and Social-Proof Lead. The targeting layer defines LTV-based lookalikes, funnel-stage retargeting segmentation, and exclusion lists for existing customers and recent converters. When RSAs are requested, Google's hard limits are enforced: exactly 15 headlines (≤30 chars), 4 descriptions (≤90 chars), 3 RSAs per ad group, with character counts printed, plus ≥8 negative keywords, ≥4 sitelinks, ≥4 callouts. In regulated contexts (e.g. CFM Brazilian medical) it filters superlatives and outcome-promise terms.

When to use

When standing up a new campaign from scratch; deciding platform/budget; applying optimization levers when an existing campaign has high CPA or low CTR; generating platform-compliant Google RSAs without manual character counting; building funnel-based retargeting and exclusion architecture.

Method / frameworks

Platform Selection Matrix (intent × audience) · account-structure hierarchy · 70/30 test→scale budget model · PAS / BAB / Social-Proof copy formulas · creative testing hierarchy (concept > hook > visual > body > CTA) · funnel-based retargeting (Hot 1-7d / Warm 7-30d / Cold 30-90d) · objective-based metric sets (CPM/Reach → CTR/CPC → CPA/ROAS) · Google RSA hard-limit + negative-keyword + extension contract · CFM compliance filter. Output is anchored against industry benchmarks (e.g. Google avg CPC ~$5.26, CVR ~7.5%; Meta median CPM ~$13.5, B2B SaaS CPL ~$63).

How do I use this skill?

You don't "run" a skill — after installing it you just tell the agent your task (e.g. ask for the relevant job), and the skill kicks in by itself when its description matches.

Upload the ads.zip you downloaded as-is — no packaging needed, the format is already correct (folder at root).

  1. Open Settings → Customize → Skills
  2. Upload → select the ads.zip you downloaded
  3. Claude reads SKILL.md; the name + description appear. Ready ✅

Scripts run in Anthropic's code-execution environment (sandbox) — not on your machine.