paid-advertising

What this skill does

# Paid Advertising

## Recent platform API changes (April–May 2026)

If you're integrating with or generating code against any of these platforms, the following recent changes have direct impact:

### Google Ads API v24 (released 22 April 2026)
Source: [Google Ads API release notes](https://developers.google.com/google-ads/api/docs/release-notes).

**Breaking changes that affect code construction of ads:**

- **`videos` and `logo_images` are now REQUIRED** in `DemandGenVideoResponsiveAdInfo` and `VideoResponsiveAdInfo`. Existing code that creates these ad types without populating both fields will fail at request time on v24+. Any DMP-generated Google Ads request bodies or asset-attach helpers must include both.
- **`Campaign.video_brand_safety_suitability` has been REMOVED.** The control still exists, but only at the **Customer level**. Any code that set brand-safety suitability per-campaign must be repointed to the Customer object. If a brand profile encodes a "video brand safety suitability" preference, the implementation should now apply it once at the Customer level on connector setup, not per-campaign.
- **`CallAd` / `CallAdInfo` are fully removed** (deprecation finalized — was in progress through v23).

### Google Ads API v23.1 (released 25 February 2026 — AEO-relevant)
- **`text_guidelines` on AI-generated assets in Performance Max and Search** — `term_exclusions` and `messaging_restrictions` are now supported. This is the channel where DMP can pipe a brand's banned-word list (`brand.profile.json → restrictions.md → banned_words`) and approved messaging restrictions directly into the Performance Max asset-generation guardrails. When generating PMax campaigns, populate `text_guidelines.term_exclusions` and `text_guidelines.messaging_restrictions` from the brand profile to keep AI-generated headlines and descriptions on-brand.

### What DMP files must reflect this

- `skills/paid-advertising/google-ads.md` — surface the v24 breaking changes in any code patterns shown
- `scripts/connector_resolver.py` — if Google Ads is in the connector map, note v24 requirements in manifest comments / setup hints (the resolver already returns `manifest_ready` / `stub_unconfigured` per the v3.7.10 architecture; no behavioral change needed beyond doc accuracy)
- `.mcp.json.connectors-reference` — Google Ads connector entry should note "v24+" as the minimum supported API version

## When to Use This Skill

Activate this skill when the user's request involves any of the following:

- Creating, auditing, or optimizing campaigns on Google Ads, Meta/Facebook Ads, LinkedIn Ads, or TikTok Ads
- Designing campaign structures, ad groups, or ad set hierarchies on any paid platform
- Selecting or troubleshooting bid strategies (manual CPC, target CPA, target ROAS, maximize conversions, etc.)
- Building audience strategies including prospecting, retargeting, lookalike/similar audiences, or custom audiences
- Allocating or pacing budgets across platforms or campaigns
- Setting up or optimizing Google Shopping, Performance Max, YouTube Ads, or Display campaigns
- Working with Meta Advantage+ campaigns or manual campaign structures
- Running LinkedIn Ads with account-based marketing (ABM) targeting
- Launching TikTok Ads including Spark Ads or TikTok Shop integrations
- Programmatic advertising including DSP selection, connected TV (CTV), or digital out-of-home (DOOH)
- Retail media networks including Amazon Ads, Walmart Connect, Target Roundel, Kroger Precision Marketing, or Instacart Ads
- Any question about paid media strategy, creative strategy for ads, or paid channel mix decisions

## Brand Context (Auto-Applied)

Before producing any marketing output from this module:

1. **Check session context** — The active brand summary was output at session start. Use the brand name, industry, voice settings, channels, goals, compliance, and competitors shown there.
2. **If you need the full profile**, read: `~/.claude-marketing/brands/{slug}/profile.json`
3. **Apply brand voice** — Formality, energy, humor, authority levels must shape all content tone and word choices
4. **Check compliance** — Auto-apply rules for brand's target_markets and industry using `skills/context-engine/compliance-rules.md`
5. **Reference industry benchmarks** — Consult `skills/context-engine/industry-profiles.md` for the brand's industry
6. **Use platform specs** — Reference `skills/context-engine/platform-specs.md` for character limits and format requirements
7. **Check campaign history** — Run `python campaign-tracker.py --brand {slug} --action list-campaigns` before planning new work
8. **If no brand exists**, say: "No brand profile found. Use /digital-marketing-pro:brand-setup to create one, or I can proceed with general best practices."
9. **Check brand guidelines** — If `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json` exists, load and enforce: `restrictions.md` for banned words, restricted claims, and mandatory disclaimers; `channel-styles.md` for channel-specific tone overrides (may differ from base voice); `messaging.md` for approved key messages, taglines, and positioning language; `voice-and-tone.md` for detailed voice rules beyond the 4 numeric scores. If producing content for a specific channel, channel style rules take precedence over base voice settings.

Do not ask the user for information that already exists in their brand profile.

## Required Context

Before executing, gather the following from the user (ask if not provided):

- **Business type**: B2B, B2C, D2C, marketplace, local business
- **Current platforms**: Which ad platforms are active (if any)
- **Monthly budget**: Total paid media spend or per-platform budgets
- **Goals**: Primary KPI (ROAS, CPA, CPL, brand awareness, traffic) and target values
- **Audience**: Who they are trying to reach (demographics, firmographics, interests, behaviors)
- **Funnel stage focus**: Top-of-funnel awareness, mid-funnel consideration, or bottom-funnel conversion
- **Existing assets**: Landing pages, creative assets, product feeds, tracking setup
- **Tracking infrastructure**: Pixel/tag status, conversion tracking, attribution model in use
- **Industry**: Needed to flag regulated category restrictions (healthcare, finance, alcohol, cannabis, gambling)

## Capabilities

### Campaign Structure Design
- Platform-specific campaign architecture (campaigns, ad groups/ad sets, ads)
- Naming conventions for scalable account management
- Campaign type selection per objective (Search, Display, Shopping, Video, App, PMax, Demand Gen)
- Ad group theming and keyword/audience segmentation strategies

### Audience Strategy
- **Prospecting**: Interest-based, behavior-based, demographic, and contextual targeting
- **Retargeting**: Website visitors, video viewers, lead form engagers, customer lists, cart abandoners
- **Lookalike/Similar audiences**: Source audience selection, expansion percentages, layering strategies
- **ABM targeting**: Company lists, job title targeting, seniority filtering (LinkedIn-specific)
- **Exclusion strategies**: Negative audiences, customer suppression, converter exclusion windows

### Bid Strategy Selection
- Manual vs automated bidding decision framework
- Target CPA, target ROAS, maximize conversions, maximize conversion value
- Portfolio bid strategies for Google Ads
- Learning phase management and bid strategy transitions
- Seasonality adjustments and bid modifiers

### Creative Strategy
- Ad format selection per platform and objective
- Responsive search ads (RSA) best practices and pin strategies
- Meta creative diversification (static, video, carousel, collection, instant experience)
- LinkedIn creative formats (single image, carousel, video, document, conversation ads)
- TikTok native-style creative principles
- Creative testing frameworks (variable isolation, iterative testing)

### Budget Allocation and Pacing
- Cross-platform budget distribution models
- Campaign-level budget optimization vs ad-set level budgets