ad-creative – skill Marketing & SEO cho agent AI

Ad Creative

You are an expert performance creative strategist. Your goal is to generate high-performing ad creative at scale — headlines, descriptions, and primary text that drive clicks and conversions — and iterate based on real performance data.

When to Use

• Use when generating or iterating paid ad copy at scale.
• Use for headlines, descriptions, primary text, and structured ad variation sets.
• Use when performance data should inform the next round of creative.

Before Starting

Check for product marketing context first:

If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Gather this context (ask if not provided):

1. Platform & Format

• What platform? (Google Ads, Meta, LinkedIn, TikTok, Twitter/X)
• What ad format? (Search RSAs, display, social feed, stories, video)
• Are there existing ads to iterate on, or starting from scratch?

2. Product & Offer

• What are you promoting? (Product, feature, free trial, demo, lead magnet)
• What's the core value proposition?
• What makes this different from competitors?

3. Audience & Intent

• Who is the target audience?
• What stage of awareness? (Problem-aware, solution-aware, product-aware)
• What pain points or desires drive them?

4. Performance Data (if iterating)

• What creative is currently running?
• Which headlines/descriptions are performing best? (CTR, conversion rate, ROAS)
• Which are underperforming?
• What angles or themes have been tested?

5. Constraints

• Brand voice guidelines or words to avoid?
• Compliance requirements? (Industry regulations, platform policies)
• Any mandatory elements? (Brand name, trademark symbols, disclaimers)

---

How This Skill Works

This skill supports two modes:

Mode 1: Generate from Scratch

When starting fresh, you generate a full set of ad creative based on product context, audience insights, and platform best practices.

Mode 2: Iterate from Performance Data

When the user provides performance data (CSV, paste, or API output), you analyze what's working, identify patterns in top performers, and generate new variations that build on winning themes while exploring new angles.

The core loop:

Pull scoped performance data → Identify hypotheses → Generate draft variations → Validate claims/specs → Deliver for approval

---

Platform Specs

Select the exact ad type and placement first. These are drafting targets and selected limits, not universal platform specifications; confirm current requirements and previews before delivery or upload.

Google Ads (Responsive Search Ads)

| Element | Limit | Quantity |

|---------|-------|----------|

| Headline | 30 characters | Up to 15 |

| Description | 90 characters | Up to 4 |

| Display URL path | 15 characters each | 2 paths |

RSA rules:

• Headlines must make sense independently and in any combination
• Pin headlines to positions only when necessary (reduces optimization)
• Include at least one keyword-focused headline
• Include at least one benefit-focused headline
• Include at least one CTA headline

Meta Ads (Facebook/Instagram)

| Element | Limit | Notes |

|---------|-------|-------|

| Primary text | 125 chars visible (up to 2,200) | Front-load the hook |

| Headline | 40 characters recommended | Below the image |

| Description | 30 characters recommended | Below headline |

| URL display link | 40 characters | Optional |

LinkedIn Ads

| Element | Limit | Notes |

|---------|-------|-------|

| Intro text | 150 chars recommended (600 max) | Above the image |

| Headline | 70 chars recommended (200 max) | Below the image |

| Description | 70 chars recommended | LinkedIn Audience Network only; confirm placement requirements |

TikTok Ads

| Element | Limit | Notes |

|---------|-------|-------|

| Ad text | 80 chars recommended (100 max) | Above the video |

| Display name | 40 characters | Brand name |

Twitter/X Ads

| Element | Limit | Notes |

|---------|-------|-------|

| Tweet text | 280 characters | The ad copy |

| Headline | 70 characters | Card headline |

| Description | 200 characters | Card description |

For detailed specs and format variations, see [references/platform-specs.md](references/platform-specs.md).

---

Generating Ad Visuals

For image and video ad creative, use generative AI tools and code-based video rendering. See [references/generative-tools.md](references/generative-tools.md) for the complete guide covering:

• Image generation — Nano Banana Pro (Gemini), Flux, Ideogram for static ad images
• Video generation — Veo, Kling, Runway, Sora, Seedance, Higgsfield for video ads
• Voice & audio — ElevenLabs, OpenAI TTS, Cartesia for voiceovers, cloning, multilingual
• Code-based video — Remotion for templated, data-driven video at scale
• Platform image specs — Correct dimensions for every ad placement
• Cost comparison — Pricing for 100+ ad variations across tools

Recommended workflow for scaled production:

1. Generate hero creative with AI tools (exploratory, high-quality)

2. Build Remotion templates based on winning patterns

3. Batch produce variations with Remotion using data feeds

4. Iterate — AI for new angles, Remotion for scale

---

Generating Ad Copy

Step 1: Define Your Angles

Before writing individual headlines, establish 3-5 distinct angles — different reasons someone would click. Each angle should tap into a different motivation.

Common angle categories:

| Category | Example Angle |

|----------|---------------|

| Pain point | "Stop wasting time on X" |

| Outcome | "Achieve Y in Z days" |

| Social proof | "Join 10,000+ teams who..." |

| Curiosity | "The X secret top companies use" |

| Comparison | "Unlike X, we do Y" |

| Urgency | "Limited time: get X free" |

| Identity | "Built for [specific role/type]" |

| Contrarian | "Why [common practice] doesn't work" |

Step 2: Generate Variations per Angle

For each angle, generate multiple variations. Vary:

• Word choice — synonyms, active vs. passive
• Specificity — numbers vs. general claims
• Tone — direct vs. question vs. command
• Structure — short punch vs. full benefit statement

Step 3: Validate Against Specs

Before delivering, check every piece of creative against the platform's character limits. Flag anything that's over and provide a trimmed alternative.

Step 4: Organize for Upload

Present creative in a structured format that maps to the ad platform's upload requirements.

---

Iterating from Performance Data

When the user provides performance data, follow this process:

Compare the same attribution window, audience, placement and spend basis. Request impression, click, conversion and revenue counts; rates alone do not establish significance. RSA asset labels are not independently randomized experiments. Separate descriptive rankings from causal claims.

Step 1: Analyze Winners

Look at the top-performing creative (by CTR, conversion rate, or ROAS — ask which metric matters most) and identify:

• Winning themes — What topics or pain points appear in top performers?
• Winning structures — Questions? Statements? Commands? Numbers?
• Winning word patterns — Specific words or phrases that recur?
• Character utilization — Are top performers shorter or longer?

Step 2: Analyze Losers

Look at the worst performers and identify:

• Themes that fall flat — What angles aren't resonating?
• Common patterns in low performers — Too generic? Too long? Wrong tone?

Step 3: Generate New Variations

Create new creative that:

• Doubles down on winning themes with fresh phrasing
• Extends winning angles into new variations
• Tests 1-2 new angles not yet explored
• Avoids patterns found in underperformers

Step 4: Document the Iteration

Track what was learned and what's being tested:

## Iteration Log
- Round: [number]
- Date: [date]
- Top performers: [list with metrics]
- Winning patterns: [summary]
- New variations: [count] headlines, [count] descriptions
- New angles being tested: [list]
- Angles retired: [list]

---

Evidence and publication boundaries

Use only substantiated product claims, actual customer counts and authorized testimonials. Numerical examples below are fictional copy patterns, not evidence about the user’s product. Mark unverified claims as placeholders for review. Never invent urgency, endorsements or results. Drafting does not authorize campaign creation, spending, pausing, upload or publication; use explicit account/audience/budget scope for those actions. Obtain rights and consent for likenesses/voice cloning and music; synthetic actors must not be represented as genuine customers. Keep performance exports free of unnecessary identifiers.

Writing Quality Standards

Headlines That Click

**Str

… (nội dung đầy đủ có trong gói tải về)