When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, full variations — for any paid platform; 'ad copy variations,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads.' For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Generate high-performing ad creative at scale — headlines, descriptions, and primary text — and iterate on real performance data.
Product context: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it first and tailor output to it; only ask for what it doesn't cover.
Gather this context (ask if not provided):
Two modes:
Core loop:
Pull performance data → Identify winning patterns → Generate new variations → Validate specs → Deliver
Platforms reject or truncate creative over these limits — verify every piece of copy fits before delivering.
| 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, one benefit-focused, and one CTA headline.
| 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 |
| 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 |
| Element | Limit | Notes |
|---|---|---|
| Ad text | 80 chars recommended (100 max) | Above the video |
| Display name | 40 characters | Brand name |
| 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.
For image and video creative, use generative AI tools and code-based video rendering. See references/generative-tools.md for the complete guide:
Scaled production workflow: (1) generate hero creative with AI tools (exploratory, high-quality); (2) build Remotion templates from winning patterns; (3) batch produce variations with Remotion using data feeds; (4) iterate — AI for new angles, Remotion for scale.
Before writing headlines, establish 3-5 distinct angles — different reasons someone would click, each tapping a different motivation.
| 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" |
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).
Check every piece against the platform's character limits; flag anything over and provide a trimmed alternative.
Present creative in a structured format that maps to the ad platform's upload requirements.
From the top performers (by CTR, conversion rate, or ROAS — ask which metric matters most), identify:
From the worst performers, identify themes that fall flat (angles not resonating) and common patterns (too generic? too long? wrong tone?).
New creative should: double down on winning themes with fresh phrasing, extend winning angles into new variations, test 1-2 unexplored angles, and avoid patterns found in underperformers.
## 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]
Strong headlines: specific ("Cut reporting time 75%") over vague ("Save time"); benefits ("Ship code faster") over features ("CI/CD pipeline"); active voice ("Automate your reports") over passive ("Reports are automated"); numbers when possible ("3x faster," "in 5 minutes," "10,000+ teams").
Avoid: jargon the audience won't recognize; claims without specificity ("Best," "Leading," "Top"); all caps or excessive punctuation; clickbait the landing page can't deliver on.
Descriptions complement headlines, not repeat them. Use them to: add proof points (numbers, testimonials, awards); handle objections ("No credit card required," "Free forever for small teams"); reinforce CTAs ("Start your free trial today"); add urgency when genuine ("Limited to first 500 signups").
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)
For 10+ variations, offer CSV 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"
## 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]
For large-scale production (Anthropic's growth team generates 100+ variations per cycle):
For pulling performance data and managing campaigns, see the tools registry.
| Platform | Pull Performance Data | Manage Campaigns | Guide |
|---|---|---|---|
| Google Ads | google-ads campaigns list, google-ads reports get | google-ads campaigns create | google-ads.md |
| Meta Ads | meta-ads insights get | meta-ads campaigns list | meta-ads.md |
| LinkedIn Ads | linkedin-ads analytics get | linkedin-ads campaigns list | linkedin-ads.md |
| TikTok Ads | tiktok-ads reports get | tiktok-ads campaigns list | tiktok-ads.md |
# 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
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.
The English summary is being prepared. Showing the original description.
When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
The English summary is being prepared. Showing the original description.
When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup.
The English summary is being prepared. Showing the original description.
When the user wants to set up, improve, or audit analytics tracking and measurement — "GA4," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "attribution," "Mixpanel," "Segment," "are my events firing," or how to measure marketing results. For A/B test measurement, see ab-test-setup.
The English summary is being prepared. Showing the original description.
Architectural decision advisor for cloud, data, and SaaS distributed systems. Use when the user asks "should we use X or Y", weighs a tradeoff, or needs a decision matrix, scaling analysis, cost-at-scale review, data-tier design, multi-tenancy model, or API/resilience guidance. For full technical blueprints, use enterprise-design.
The English summary is being prepared. Showing the original description.
Create a feature branch from the default branch with a descriptive, conventional name.
The English summary is being prepared. Showing the original description.