跳到正文
cccskills
免费在 GitHub 公开

ad-creative

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.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(4)

  • SKILL.md12.0 KB
  • evals/evals.json6.7 KB
  • references/generative-tools.md23.5 KB
  • references/platform-specs.md6.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Ad Creative

Generate high-performing ad creative at scale — headlines, descriptions, and primary text — and iterate on real performance data.

Before Starting

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):

1. Platform & Format

  • Platform? (Google Ads, Meta, LinkedIn, TikTok, Twitter/X)
  • Ad format? (Search RSAs, display, social feed, stories, video)
  • Existing ads to iterate on, or starting from scratch?

2. Product & Offer

  • What are you promoting? (Product, feature, free trial, demo, lead magnet)
  • Core value proposition?
  • Differentiation from competitors?

3. Audience & Intent

  • Target audience?
  • Stage of awareness? (Problem-aware, solution-aware, product-aware)
  • Driving pain points or desires?

4. Performance Data (if iterating)

  • What creative is currently running?
  • Best-performing headlines/descriptions? (CTR, conversion rate, ROAS)
  • Underperformers?
  • Angles or themes already tested?

5. Constraints

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

How This Skill Works

Two modes:

  • Mode 1: Generate from Scratch — full set of ad creative from product context, audience insights, and platform best practices.
  • Mode 2: Iterate from Performance Data — given data (CSV, paste, or API output), analyze what's working, find patterns in top performers, and generate variations that build on winning themes while exploring new angles.

Core loop:

Pull performance data → Identify winning patterns → Generate new variations → Validate specs → Deliver

Platform Specs

Platforms reject or truncate creative over these limits — verify every piece of copy fits before delivering.

Google Ads (Responsive Search Ads)

ElementLimitQuantity
Headline30 charactersUp to 15
Description90 charactersUp to 4
Display URL path15 characters each2 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.

Meta Ads (Facebook/Instagram)

ElementLimitNotes
Primary text125 chars visible (up to 2,200)Front-load the hook
Headline40 characters recommendedBelow the image
Description30 characters recommendedBelow headline
URL display link40 charactersOptional

LinkedIn Ads

ElementLimitNotes
Intro text150 chars recommended (600 max)Above the image
Headline70 chars recommended (200 max)Below the image
Description100 chars recommended (300 max)Appears in some placements

TikTok Ads

ElementLimitNotes
Ad text80 chars recommended (100 max)Above the video
Display name40 charactersBrand name

Twitter/X Ads

ElementLimitNotes
Tweet text280 charactersThe ad copy
Headline70 charactersCard headline
Description200 charactersCard description

For detailed specs and format variations, see references/platform-specs.md.


Generating Ad Visuals

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

  • 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

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.


Generating Ad Copy

Step 1: Define Your Angles

Before writing headlines, establish 3-5 distinct angles — different reasons someone would click, each tapping a different motivation.

CategoryExample 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

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

Check every piece against the platform's character limits; flag anything 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

Step 1: Analyze Winners

From the top performers (by CTR, conversion rate, or ROAS — ask which metric matters most), identify:

  • Winning themes — topics or pain points in top performers
  • Winning structures — questions? statements? commands? numbers?
  • Winning word patterns — recurring words or phrases
  • Character utilization — are top performers shorter or longer?

Step 2: Analyze Losers

From the worst performers, identify themes that fall flat (angles not resonating) and common patterns (too generic? too long? wrong tone?).

Step 3: Generate New Variations

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.

Step 4: Document the Iteration

## 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: 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 That Convert

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").


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

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"

Iteration Report

## 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 production (Anthropic's growth team generates 100+ variations per cycle):

1. Break into sub-tasks

  • Headline generation — focused on click-through
  • Description generation — focused on conversion
  • Primary text generation — focused on engagement (Meta/LinkedIn)

2. Generate in waves

  • Wave 1: Core angles (3-5 angles, 5 variations each)
  • Wave 2: Extended variations on top 2 angles
  • Wave 3: Wild card angles (contrarian, emotional, specific)

3. Quality filter

  • Remove anything over character limit
  • Remove duplicates or near-duplicates
  • Flag potential platform policy violations
  • Ensure headline/description combinations make sense together

Common Mistakes

  • Writing headlines that only work together — RSA headlines get combined randomly
  • Ignoring character limits — platforms truncate without warning
  • All variations sound the same — vary angles, not just word choice
  • No CTA headlines — RSAs need action-oriented headlines to drive clicks; include at least 2-3
  • Generic descriptions — "Learn more about our solution" wastes the slot
  • Iterating without data — gut feelings are less reliable than metrics
  • Testing too many things at once — change one variable per test cycle
  • Retiring creative too early — allow 1,000+ impressions before judging

Tool Integrations

For pulling performance data and managing campaigns, see the tools registry.

PlatformPull Performance DataManage CampaignsGuide
Google Adsgoogle-ads campaigns list, google-ads reports getgoogle-ads campaigns creategoogle-ads.md
Meta Adsmeta-ads insights getmeta-ads campaigns listmeta-ads.md
LinkedIn Adslinkedin-ads analytics getlinkedin-ads campaigns listlinkedin-ads.md
TikTok Adstiktok-ads reports gettiktok-ads campaigns listtiktok-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

Related Skills

  • paid-ads: For campaign strategy, targeting, budgets, and optimization
  • copywriting: For landing page copy (where ad traffic lands)
  • ab-test-setup: For structuring creative tests with statistical rigor
  • marketing-psychology: For psychological principles behind high-performing creative
  • copy-editing: For polishing ad copy before launch

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

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.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

ai-seo

免费

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.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

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.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

architect

免费

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.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

branch

免费

Create a feature branch from the default branch with a descriptive, conventional name.

中文简介正在准备中。当前显示原文说明。

rajitsaha/100xprism102026年10月14日 更新

查看 rajitsaha 的全部技能

报告此技能的问题