paid-creative-ai
When the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools. Also use when the user mentions 'ad creative,' 'performance creative,' 'creative testing,' 'creative fatigue,' 'Meta ads,' 'Google ads,' 'TikTok ads,' 'AI ads,' 'ad budget,' 'ROAS,' 'Advantage+,' or 'Performance Max.' This skill covers AI-powered paid creative from generation through performance optimization. Do NOT use for technical implementation, code review, or software architecture.
npx skills add tech-leads-club/agent-skills --skill paid-creative-ai --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
You are instructed to act as a performance creative strategist who builds AI-powered ad creative systems across Meta, Google, TikTok, YouTube, and LinkedIn. You combine platform-native AI tools with generative AI production to create, test, and scale ad creative that drives measurable ROAS.
How it works
- Before Starting: Ask the user for 7 specifics: product/service, platforms, monthly ad spend, primary KPI, existing assets vs. starting from scratch, openness to AI-generated creative, and current creative testing process.
- Section 1: Platform AI Creative Systems: Present platform tools (e.g., Meta Advantage+, GEM; Google Performance Max; TikTok Smart+ and Symphony) with their roles and best-use scenarios, plus setup best practices and what each tool automates vs. what the user controls.
- Section 2: AI Creative Generation Tools: List tools (Midjourney, DALL-E 3, Adobe Firefly, Runway Gen-4, Pika, Sora, Creatify, Arcads) and describe the AI creative production workflow from concept generation (Day 1) through asset creation (Days 1-2), assembly (Days 2-3), quality filter (Day 3), to deploy and test (Day 4+). Then compare AI vs traditional production and suggest a hybrid approach (70/30) for certain budgets.
- Section 3: Budget Allocation Framework: Provide a 70/20/10 rule for creative spend and monthly spend tables across ranges, plus cross-platform budget split decisions by scenario and a separate creative testing budget section.
- Section 4: Modular Creative Testing Framework: Define the Hook/Body/CTA matrix (12-45 combinations), Phase 1 concept testing, Phase 2 element isolation, Phase 3 winner scaling, and a testing timeline, plus platform-specific testing features (Meta Dynamic Creative, TikTok Smart Creative, Google PMax asset groups).
- Section 5: Creative Fatigue Management: Give early warning signals, platform-specific creative lifespans, a refresh pipeline, and anti-fatigue tactics like format rotation, audience rotation, seasonal refresh, and iterative hooks.
When to use it
Use when a user is optimizing paid media creative with AI, including generation through performance optimization, for environments involving Meta, Google, TikTok, YouTube, and LinkedIn. It is not intended for technical implementation, code review, or software architecture.
What it can touch
Tools listed in the skill include: "claude-code, copilot, cursor". The workflow references platform systems and generative tools, asset creation, and deployment steps.
Caveats
No explicit licensing or risk statements are provided in the text beyond the general workflow and tool usage guidance. The guideline emphasizes testing and validation of assets and performance metrics before scaling.
# 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
- Before Starting
- Section 1: Platform AI Creative Systems
- Platform AI Tool Comparison
- Meta Advantage+ Creative
- Google Performance Max
- TikTok Smart+ and Symphony
- Section 2: AI Creative Generation Tools
- Generative AI for Ad Creative
- AI Creative Production Workflow
- AI vs Traditional Production Decision
- Section 3: Budget Allocation Framework
- The 70/20/10 Rule for Creative Spend
- Budget Allocation by Monthly Spend
- Cross-Platform Budget Split Decision
What does the paid-creative-ai skill do?
When the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools. Also use when the user mentions 'ad creative,' 'performance creative,' 'creative testing,' 'creative fatigue,' 'Meta ads,' 'Google ads,' 'TikTok ads,' 'AI ads,' 'ad budget,' 'ROAS,' 'Advantage+,' or 'Performance Max.' This skill covers AI-powered paid creative from generation through performance optimization. Do NOT use for technical implementation, code review, or software architecture.
How do I install it?
Run `npx skills add tech-leads-club/agent-skills --skill paid-creative-ai --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From tech-leads-club/agent-skills, a repository with 4,983 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.