Bodega

Skills › Marketing

ad-creative

Ideas y textos para anuncios pagados, con variantes para probar.

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'ad templates,' 'iMessage ad,' 'ChatGPT ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'creative review page,' 'motion video ad,' 'faceless video ad,' 'UGC ad,' 'greenscreen ad,' 'TikTok/Reels ad format,' 'Meta ad format tier list,' or 'creative format taxonomy.' Use it to produce or iterate ad copy at scale. Copy avoids AI tells like 'it's not X, it's Y' reveals. For campaign strategy and targeting, see ads. For landing page copy, see copywriting. Test hypotheses must be falsifiable, naming the metric, the comparison, and the expected direction.

Descargar .zipVer en GitHub
Departamento
Marketing
Fuente
Comunidad · coreyhaines31/marketingskills
Autor
Corey Haines
Licencia
MIT
Idioma
Inglés
Riesgo
Alto

Señales de riesgo

Cómo instalarla en Claude

  1. Descargue el .zip sin descomprimirlo.
  2. En Claude active Configuración › Capacidades › Crear y editar archivos.
  3. Vaya a Personalizar › Skills › Crear skill › Subir una skill y elija el archivo.

Instrucciones completas (SKILL.md)

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.

Before Starting

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

Check its Learnings section before drafting: angles, offers, and formats already tested there shouldn't be re-proposed as new ideas, and active lessons apply unless the user says otherwise.

Gather this context (ask if not provided):

1. Platform & Format

2. Product & Offer

3. Audience & Intent

4. Performance Data (if iterating)

5. Constraints

---

How This Skill Works

This skill supports four 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 performance data → Identify winning patterns → Generate new variations → Validate specs → Deliver

Mode 3: Scaled Static Batches (Grounded)

For recurring static ad production at volume (e.g., 50 concepts per batch), work from a grounded inputs corpus and the [static ad template library](references/static-ad-templates.md). Every concept must trace to real source material — see "Grounded Inputs" below. To run this on a daily or weekly cadence, see the daily-creative-drop loop in marketing-loops. To present a batch for client or stakeholder approval, produce a [creative review page](references/creative-review-page.md).

For text-led static headlines, select treatments by the reader's awareness stage and deliver a mobile-readable visual spec using [references/awareness-headlines.md](references/awareness-headlines.md). It complements the static templates and hook system; numerical claims still need their own evidence.

Mode 4: Creative Strategy Loop

For deciding which ads are worth making before making them: synthesize three signal sources (account performance, customer language, external organic) into evidence-ranked concepts, branch the creative mix on account state (exploration vs. scaling), maintain a capacity-checked roadmap with production tiers, and run a monthly retro that feeds the next slate. The full system lives in [references/creative-roadmap.md](references/creative-roadmap.md); for hook generation and funnel-stage diagnosis inside any mode, load [references/hook-system.md](references/hook-system.md).

---

Grounded Inputs

Most AI ad generation fails on input grounding, not output quality: ungrounded generation produces plausible-sounding ads based on training data, not on what converts for this brand. For scaled production (Mode 3), maintain a durable inputs corpus:

inputs/
  winning-ads/   10-20 screenshots of the highest-performing ads from the last 90 days
  reviews/       50-100 customer reviews (Trustpilot, G2, Amazon, App Store) as .md/.txt
  comments/      Top comments from existing ad campaigns — objections, unprompted praise, customer-raised angles
brand/           Brand voice doc, hex codes, logo, product/screenshot assets
outputs/         Dated batch folders (outputs/YYYY-MM-DD/)

Why each input matters:

Grounding rules:

---

Platform Specs

Platforms reject or truncate creative that exceeds these limits, so verify every piece of copy fits before delivering.

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:

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 | 100 chars recommended (300 max) | Appears in some placements |

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

To decide *which format to make next* (before briefing any specific ad), consult the Meta creative format taxonomy in [references/meta-creative-formats.md](references/meta-creative-formats.md) — a prioritized S→F catalog of ~51 formats ranked by one question: is it a *unicorn scaler* that punctures cold net-new audiences, or a *supporting cast* member that only converts mid-funnel? Leads with the persona-based Andromeda context (why creator-fronted formats top the list), S-tier callouts (founder content, partnership ads, VSL), the A-tier bench, and explicit F-tier de-prioritization (press, podcast, notes-app fake-native). Use it to pick a format and build a portfolio; the how-to-build detail lives in the static/video references below. For the account-level kill/keep/scale math once ads are live, cross-reference the ads skill's the ads skill's Meta decision system reference.

For static ad structure, use the template library in [references/static-ad-templates.md](references/static-ad-templates.md) — layout frameworks (Us vs. Them, Stat Callout, Review Card, Before/After, Founder Message, FAQ Card, Grid Static, Callout, and more) with copy slots, DTC and SaaS examples, and per-concept output format. Each template carries a tier (S–F) and funnel role (unicorn cold-scaler vs. mid-funnel supporting cast) so you reach for the right one first. Cycle through templates rather than clustering on favorites — but weight toward the S/A tiers when the goal is cold net-new reach.

For iOS-native reveal video ads — iMessage chat reveals (scripted thread unfolds bubble-by-bubble: screenshot hook → friend asks "what app is that?" → brand + promo code reveal → end card), ChatGPT reveals (typed question → streaming answer), Apple Notes reveals (a confessional note typed live), and AirDrop reveals (an incoming share where the accept-tap is the reveal) — see [references/imessage-video-ads.md](references/imessage-video-ads.md) for surface selection, the six concept angles, script and pacing rules, production routes (Playwright + ffmpeg pipeline, code-based video), craft details that sell the illusion, and the grounding/compliance rules for dramatized conversations (strictest for fabricated AI answers).

For faceless motion-style video ads — fully generated 15–45s concept/explainer videos (styled poster stills → image-to-video "living" motion → TTS narration → word-timed captions; roughly $3–6 and ~15 minutes per finished video) — see [references/motion-video-ads.md](references/motion-video-ads.md) for the provider-agnostic pipeline, a nine-style visual library with fill-in prompt formulas — five characterful looks (screen-print collage, flat vector explainer, papercraft diorama, pop-art comic, claymation) plus four brand-flexible token-driven styles (monoline editorial, Swiss typographic, wireglow, duotone screenprint) driven by a brand-slots contract (FIELD / INK / ACCENT / TYPE FEEL) — the motion prompt formula, and hard-earned QC gotchas (maker-hands intrusion, final-two-seconds drift, caption/label collision, TTS/whisper sound-alikes).

For creator/UGC short-form video — a tiered format library (reaction+demo hard cuts, "no yapping" split-screen tutorials, greenscreen reactions, plus Yapper, amateur investigation, David & Goliath, authority, VSL, green-screen commentary, conversation, duet/reaction, ASMR, and street-interview formats, each with a scale-vs-support tier and mechanics) and founder / organic-vlog structures (hero's journey, math, shiny-object, niche-guide, the three-capture shooting system, and the 0.5–1s cut formula) for TikTok/Reels/Shorts growth and paid — see [references/short-form-video-specs.md](references/short-form-video-specs.md). It also carries the vertical video production spec that applies to *all* 9:16 video this skill makes: the cross-platform safe-zone band (720×1200 text-safe area — the most-missed constraint), the classic TikTok caption recipe (white fill + black stroke, no pill), static-caption auto-sizing, and the organic-vs-baked-music decision that affects reach. Load it before producing any vertical video.

For image and video generation tools, see [references/generative-tools.md](references/generative-tools.md) for the complete guide covering:

Workflow for scaled production:

---

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:

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:

Step 1: Analyze Winners

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

Step 2: Analyze Losers

Look at the worst performers and identify:

Step 3: Generate New Variations

Create new creative that:

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]

---

Writing Quality Standards

Headlines That Click

Strong headlines:

Avoid:

brief gives, in every field of every concept, unless a short form is explicitly approved

Test Hypotheses That Can Lose

When a concept ships with a test hypothesis, write one that a result can prove wrong. "This will resonate with renters" cannot lose; "beats the control on CTR among renters" can.

against which control or sibling concept, in which audience

("+15% CTR vs. Concept A")

loss teaches you something about the audience, not just the asset

No AI Tells

Ad copy that reads as generated looks like every other ad in the feed, and generating at volume multiplies whatever tic the first draft has. Check the whole batch.

Never write these:

Ad-specific tells:

Across a batch, vary the sentence shapes. Ten variations that all open the same way read as generated, even when each one is fine alone. For the full blacklist, use the copywriting skill's AI-tells reference.

Descriptions That Convert

Descriptions should complement headlines, not repeat them. Use descriptions to:

---

Output Formats

Standard Output

Organize by angle, with character counts:

## Angle: [Pain Point — Manual Reporting]

### Headlines (30 char max)
1. "Stop Building Reports by Hand" (29)
2. "Automate Your Weekly Reports" (28)
3. "Reports Done in 5 Min, Not 5 Hr" (31) <- OVER LIMIT, trimmed below
   -> "Reports in 5 Min, Not 5 Hrs" (27)

### Descriptions (90 char max)
1. "Marketing teams save 10+ hours/week with automated reporting. Start free." (73)
2. "Connect your data sources once. Get automated reports forever. No code required." (80)

Bulk CSV Output

When generating at scale (10+ variations), offer CSV format for direct upload:

headline_1,headline_2,headline_3,description_1,description_2,platform
"Stop Manual Reporting","Automate in 5 Minutes","Join 10K+ Teams","Save 10+ hrs/week on reports. Start free.","Connect data sources once. Reports forever.","google_ads"

Static Batch Output (Mode 3)

For scaled static batches, save to a dated folder with an index:

outputs/YYYY-MM-DD/
  INDEX.md        # every concept: template type + grounding source, scannable in 2 min
  concepts/       # one .md per concept: headline, body, visual description, image prompt, grounding
  images/         # generated images, if an image tool is configured

Per-concept format is defined in [references/static-ad-templates.md](references/static-ad-templates.md). The human workflow this supports: open the folder, scan INDEX.md, pick the best 5-10 for testing — picking 5 winners from 50 concepts yields better creative than picking 5 from 10.

Creative Review Page (client / stakeholder approval)

When a person who isn't you needs to review and pick — a client, a partner, a stakeholder — produce a creative review page: a self-contained HTML artifact that presents each concept as an in-feed platform mockup (Instagram/Facebook, with a whitelist-handle toggle), breaks carousels into a labeled frame-by-frame storyboard, lets them toggle headline/copy variations, and discloses what's grounded in real assets. It's the visual upgrade to INDEX.md — a decision made off one link instead of by reading markdown. The template ships at [assets/creative-review-template.html](assets/creative-review-template.html) (one file, no build, hostable anywhere); populate its DATA object from your generated concepts. Full data model, grounding rules (the disclosure block is required), and delivery in [references/creative-review-page.md](references/creative-review-page.md).

Iteration Report

When iterating, include a summary:

## Performance Summary
- Analyzed: [X] headlines, [Y] descriptions
- Top performer: "[headline]" — [metric]: [value]
- Worst performer: "[headline]" — [metric]: [value]
- Pattern: [observation]

## New Creative
[organized variations]

## Recommendations
- [What to pause, what to scale, what to test next]

---

Batch Generation Workflow

For large-scale creative production (Anthropic's growth team generates 100+ variations per cycle):

1. Break into sub-tasks

2. Generate in waves

3. Quality filter

---

Common Mistakes

---

Tool Integrations

For pulling performance data and managing campaigns, see the [tools registry](https://github.com/coreyhaines31/marketingskills/blob/main/tools/REGISTRY.md).

| Platform | Pull Performance Data | Manage Campaigns | Guide | |----------|:---------------------:|:----------------:|-------| | Google Ads | google-ads campaigns list, google-ads reports get | google-ads campaigns create | [google-ads.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/google-ads.md) | | Meta Ads | meta-ads insights get | meta-ads campaigns list | [meta-ads.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/meta-ads.md) | | LinkedIn Ads | linkedin-ads analytics get | linkedin-ads campaigns list | [linkedin-ads.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/linkedin-ads.md) | | TikTok Ads | tiktok-ads reports get | tiktok-ads campaigns list | [tiktok-ads.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/tiktok-ads.md) |

Workflow: Pull Data, Analyze, Generate

# 1. Pull recent ad performance
node tools/clis/google-ads.js reports get --type ad_performance --date-range last_30_days

# 2. Analyze output (identify top/bottom performers)
# 3. Feed winning patterns into this skill
# 4. Generate new variations
# 5. Upload to platform

> Skip the plumbing. Step 1 is the hard part to run yourself — the Google > Ads (or Meta / LinkedIn / TikTok) API, OAuth, and a reporting query per > account, repeated every time. [Magister](https://magistermarketing.com?ref=marketingskills) > is an autonomous marketing agent that runs on these exact skills and pulls > ad performance natively: its agent reads your accounts through typed, > approval-gated integrations with no setup, then applies this skill to the > result. If you're wiring these pulls up by hand, it's worth a look.> > *Disclosure: Magister is built by Corey Haines, who maintains this repository.* > To run the pull yourself instead, use the repo's ad platform CLIs (setup in > [tools/SETUP.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/SETUP.md)), > or a reporting connector such as Supermetrics or Coupler.

---

Related Skills