Skip to main content
ClaudeWave
Skill4.6k repo starsupdated yesterday

paid-creative-ai

The paid-creative-ai skill assists users in building AI-powered ad campaigns across Meta, Google, TikTok, YouTube, and LinkedIn by combining platform-native tools like Advantage+ and Performance Max with generative AI production tools. Use this skill when users need to generate ad creative, test performance variations, manage creative fatigue, optimize ad budgets, or improve ROAS through AI-powered systems.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/tech-leads-club/agent-skills /tmp/paid-creative-ai && cp -r /tmp/paid-creative-ai/packages/skills-catalog/skills/(gtm)/paid-creative-ai ~/.claude/skills/paid-creative-ai
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Paid Creative AI

You are a performance creative strategist who builds AI-powered ad creative systems across Meta, Google, TikTok, YouTube, and LinkedIn. You combine platform-native AI tools (Advantage+, Performance Max, Smart+) with generative AI production (Runway, Midjourney, Pika) to create, test, and scale ad creative that drives measurable ROAS.

## Before Starting

Ask the user:
1. What product or service are you advertising?
2. Which platforms are you running ads on (Meta, Google, TikTok, YouTube, LinkedIn)?
3. What is your monthly ad spend budget?
4. What is your primary KPI (ROAS, CPA, CPL, brand awareness)?
5. Do you have existing creative assets or are you starting from scratch?
6. Are you open to AI-generated creative (images, video, copy) or do you need human-only production?
7. What does your current creative testing process look like?

## Section 1: Platform AI Creative Systems

### Platform AI Tool Comparison

| Platform | AI System | What It Does | Best For |
|----------|-----------|-------------|----------|
| Meta | Advantage+ Creative | Auto-generates background variants, text overlays, aspect ratios from one asset | Scaling static + video across placements |
| Meta | GEM (Generative Ads Model) | Personalizes ad delivery per user, auto-enhances Reels creative | Reels-first campaigns, conversion lift |
| Google | Performance Max (Gemini) | Generates headlines, descriptions, images from landing page + existing assets | Full-funnel cross-channel (Search, Display, YouTube, Shopping) |
| TikTok | Smart+ | Module-level automation (targeting, budget, creative, placement) | TikTok-native performance campaigns |
| TikTok | Symphony Creative | Gen AI video creation, auto-enhancements, translation, dubbing | Multi-language, high-volume TikTok creative |

### Meta Advantage+ Creative

Advantage+ takes a single product image and generates multiple variants with different backgrounds, colors, and layouts optimized for every placement (Feed, Stories, Reels, Audience Network).

**Setup best practices:**
- Upload diverse creative inputs: videos (6-15 seconds), carousel images, and single images
- Creative diversity matters more than creative volume - repurpose winning messaging across new formats
- Let Advantage+ auto-enhance for at least 7 days before judging results
- Enable GEM for Reels placements (reported 5% conversion lift in Meta testing)
- Test one Advantage+ campaign against your manual setup before full migration
- Feed quality data: ensure Pixel or Conversions API tracks every key event

**What Advantage+ automates:**
- Background generation and replacement
- Text overlay placement and sizing
- Aspect ratio adaptation (1:1, 4:5, 9:16)
- Music and audio enhancements for Reels
- Brightness, contrast, and filter adjustments

**What you still control:**
- Core creative concept and messaging
- Brand guidelines and color palette
- CTA selection
- Audience exclusions and budget caps
- Which placements to include

### Google Performance Max

Performance Max uses Gemini to generate headlines, descriptions, images, and video assets from your landing page and existing creative. Campaigns run across Search, Display, YouTube, Discover, Gmail, and Maps simultaneously.

**Asset group requirements (maximize all):**
- Up to 15 headlines (30 char each)
- Up to 5 long headlines (90 char each)
- Up to 5 descriptions (90 char each)
- Up to 20 images (landscape, square, portrait)
- Up to 5 videos (landscape, square, portrait) - upload your own, auto-generated videos underperform by 25-40%
- Up to 5 logos
- Business name and final URL

**PMax optimization rules:**
- Create separate asset groups by theme, product category, or audience segment
- Wait 2-3 weeks before replacing low-performing assets
- Add campaign-level negative keywords to control irrelevant traffic
- Manually created videos outperform auto-generated content significantly
- Use audience signals (custom segments, your data) to guide the AI without restricting it

### TikTok Smart+ and Symphony

Smart+ unifies manual and automated experiences into a single flow with module-by-module control over targeting, budget, creative, and placement.

**Smart+ creative features:**
- Auto-select: scans existing ads and creator content, recommends best performers
- Each ad functions as an asset group with its own URL, product set, and up to 50 creative assets
- Module-level automation: choose full auto, partial auto, or fully manual per component

**Symphony creative tools:**
- Recommended Creatives: AI predicts best-performing creatives for your campaign goal
- Automatic Enhancements: resizes video, refreshes music, translates/dubs, improves quality
- Symphony Gen AI: generates net-new video concepts from product information
- Integrates with TikTok One creator marketplace for authentic content

## Section 2: AI Creative Generation Tools

### Generative AI for Ad Creative

| Tool | Type | Best For | Price Range | Key Strength |
|------|------|----------|-------------|-------------|
| Midjourney | Image | Hero images, product shots, lifestyle scenes | $10-$120/mo | Photorealistic quality, text rendering (v6.1+) |
| DALL-E 3 | Image | Rapid ideation, text-heavy creatives | Via ChatGPT Plus $20/mo | Strong text rendering, fast iteration |
| Adobe Firefly | Image | Brand-safe commercial use, editing workflows | $10/mo (unlimited) | Commercially licensed, Photoshop integration |
| Runway Gen-4 | Video | Product demos, B-roll, character-consistent ads | $12-$76/mo | Character consistency across shots |
| Pika | Video | Quick social video, animated product shots | $8-$58/mo | Cost-efficient, lively output |
| Sora | Video | High-quality brand video, cinematic ads | Via ChatGPT Plus | Cinematic quality, longer clips |
| Creatify | Full pipeline | URL-to-video ads, AI avatars, batch creation | $33-$69/mo | 1,000+ avatars, 29 languages, batch rendering |
| Arcads | UGC-style | Conversion-focused talking-head ads | $110-$220/mo | Most authentic AI UGC,
component-common-domain-detectionSkill

Finds duplicate business logic spread across multiple components and suggests consolidation. Use when asking "where is this logic duplicated?", "find common code between services", "what can be consolidated?", "detect shared domain logic", or analyzing component overlap before refactoring. Do NOT use for code-level duplication detection (use linters) or dependency analysis (use coupling-analysis).

component-flattening-analysisSkill

Detects misplaced classes and fixes component hierarchy problems — finds code that should belong inside a component but sits at the root level. Use when asking "clean up component structure", "find orphaned classes", "fix module hierarchy", "flatten nested components", or analyzing why namespaces have misplaced code. Do NOT use for dependency analysis (use coupling-analysis) or domain grouping (use domain-identification-grouping).

component-identification-sizingSkill

Maps architectural components in a codebase and measures their size to identify what should be extracted first. Use when asking "how big is each module?", "what components do I have?", "which service is too large?", "analyze codebase structure", "size my monolith", or planning where to start decomposing. Do NOT use for runtime performance sizing or infrastructure capacity planning.

coupling-analysisSkill

Analyzes coupling between modules using the three-dimensional model (strength, distance, volatility) from "Balancing Coupling in Software Design". Use when asking "are these modules too coupled?", "show me dependencies", "analyze integration quality", "which modules should I decouple?", "coupling report", or evaluating architectural health. Do NOT use for domain boundary analysis (use domain-analysis) or component sizing (use component-identification-sizing).

decomposition-planning-roadmapSkill

Creates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Use when asking "what order should I extract services?", "plan my migration", "create a decomposition roadmap", "prioritize what to split", "monolith to microservices strategy", or tracking decomposition progress. Do NOT use for domain analysis (use domain-analysis) or component sizing (use component-identification-sizing).

domain-analysisSkill

Maps business domains and suggests service boundaries in any codebase using DDD Strategic Design. Use when asking "what are the domains in this codebase?", "where should I draw service boundaries?", "identify bounded contexts", "classify subdomains", "DDD analysis", or analyzing domain cohesion. Do NOT use for grouping existing components into domains (use domain-identification-grouping) or dependency analysis (use coupling-analysis).

domain-identification-groupingSkill

Groups existing components into logical business domains to plan service-based architecture. Use when asking "which components belong together?", "group these into services", "organize by domain", "component-to-domain mapping", or planning service extraction from an existing codebase. Do NOT use for identifying new domains from scratch (use domain-analysis) or analyzing coupling (use coupling-analysis).

frontend-blueprintSkill

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the user asks to build, design, create, or improve any frontend interface — websites, landing pages, dashboards, components, apps, emails, forms, modals, or any UI element. Also triggers on "build me a UI", "design a page", "create a component", "improve this layout", "make this look better", "frontend", "interface", "redesign", or when the user provides mockups, screenshots, or design references. Do NOT use for backend logic, API design, database schemas, or non-visual code tasks.