agentleFS
HainrixzHainrixz/claude-ads/skills/ads-creative/SKILL.md

ads-creative

Skill102 starsChanged 6 months agoMITView on GitHub

Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Use when user says creative audit, ad creative, creative fatigue, ad copy, ad design, or creative review.

10 other projects use a version of this, 7 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ads-apple, gsap and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • chriswesttSkill

    ads-apple

    Apple Ads (formerly Apple Search Ads) deep analysis for mobile app advertisers. Evaluates campaign structure, bid health, Custom Product Pages (CPPs), MMP attribution, budget pacing, TAP coverage (Today/Search/Product Pages), Maximize Conversions bidding, and goal CPA benchmarks by country. Use when user says Apple Ads, Apple Search Ads, ASA, App Store ads, Apple ads, Search Ads, or is advertising a mobile app on iOS.

    Also in 5 projects that use this

  • OpenAISkill

    gsap

    GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.

    Also in 3 projects that use this

  • OpenAISkill

    hyperframes-cli

    HyperFrames CLI tool — hyperframes init, lint, inspect, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting, validating, inspecting visual layout in compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the HyperFrames environment.

    Also in 3 projects that use this

  • StrayDragonSkill

    ui-ux-pro-max

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 6 are common, 1 is distinctive, and 3 are very specific to this project.

  • 6

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ads/references/platform-specs.md for creative specifications

    line 13
  2. Very specific:

    Read ads/references/benchmarks.md for CTR/engagement benchmarks

    line 14
  3. Very specific:

    Read ads/references/scoring-system.md for weighted scoring algorithm

    line 15
  4. Distinctive:

    Validate: verify fatigue signals reference actual performance trends, not assumptions

    line 19
  5. Common:

    All video 9:16 vertical 1080x1920 (non-negotiable)

    line 50
  6. Common:

    No creative active >7 days with declining CTR

    line 53
  7. Common:

    Keep critical elements centered and within safe margins

    line 156
  8. Common:

    Test on mobile devices (75%+ of ad impressions are mobile)

    line 157
  9. Common:

    Use numbers and specifics over vague claims

    line 163
  10. Common:

    Test emotional vs rational appeals

    line 164

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Portions Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) - see LICENSE for original authors · tododeia.com · id er-fd4fa55b -->

Cross-Platform Creative Quality Audit

Process

  1. Collect creative assets or performance data from active platforms
  2. Read ads/references/platform-specs.md for creative specifications
  3. Read ads/references/benchmarks.md for CTR/engagement benchmarks
  4. Read ads/references/scoring-system.md for weighted scoring algorithm
  5. Validate: confirm at least one platform has creative data (assets or performance metrics) before proceeding
  6. Evaluate creative quality per platform
  7. Assess cross-platform creative consistency
  8. Validate: verify fatigue signals reference actual performance trends, not assumptions
  9. Generate production priority recommendations

Per-Platform Assessment

Google Ads Creative

  • RSA: ≥8 unique headlines, ≥3 descriptions per ad group
  • RSA ad strength: "Good" or "Excellent"
  • Pin usage: minimal and strategic (over-pinning kills RSA flexibility)
  • Extensions: sitelinks (≥4), callouts (≥4), structured snippets, image
  • PMax asset groups: text + image + video + optional product feed
  • YouTube video campaigns: video quality, hook, subtitles (covered inside audit-google checks G-DG*, G-CTV* — YouTube uses the Google Ads API)

Meta Ads Creative

  • Format diversity: ≥3 formats active (image, video, carousel, collection)
  • Creative volume: ≥5 creatives per ad set
  • Fatigue detection: CTR declining >20% over 14 days = FAIL
  • Video length: 15s max Stories/Reels, 30s max Feed
  • UGC/testimonial content tested
  • Advantage+ Creative enhancements enabled
  • Headline under 40 chars, primary text under 125 chars

LinkedIn Creative

  • Thought Leader Ads active, ≥30% budget for B2B
  • Format diversity: ≥2 formats tested (single image, carousel, video, document)
  • Video ads tested
  • Creative refresh: every 4-6 weeks
  • Professional tone appropriate for platform

TikTok Creative

  • ≥6 creatives per ad group (Critical requirement)
  • All video 9:16 vertical 1080x1920 (non-negotiable)
  • Native-looking content (not corporate)
  • Hook in first 1-2 seconds
  • No creative active >7 days with declining CTR
  • Spark Ads tested (~3% CTR vs ~2% standard)
  • Sound-on optimization (never silent)
  • Safe zone compliance: X:40-940, Y:150-1470
  • Trending audio used

Microsoft Creative

  • RSA: ≥8 headlines, ≥3 descriptions
  • Multimedia Ads tested (unique rich format)
  • Ad copy optimized for Bing demographics (older, higher income, professional)
  • Action Extension utilized (unique to Microsoft)
  • Filter Link Extension tested

Creative Fatigue Detection

Signals of Fatigue

SignalThresholdAction
CTR declining>20% over 14 daysRefresh creative
Frequency (Meta)>5.0 prospecting, >12.0 retargetingNew audience or creative
Watch time declining (TikTok)<3s averageNew hook needed
QS declining (Google)Drop of 2+ pointsRefresh ad copy
Engagement rate drop>30% declineFull creative overhaul

Refresh Cadence by Platform

PlatformRecommended Refresh
TikTokEvery 7-10 days (fastest fatigue)
MetaEvery 14-21 days
LinkedInEvery 4-6 weeks
Google SearchEvery 8-12 weeks
MicrosoftEvery 8-12 weeks
YouTubeEvery 4-8 weeks

Format Diversity Matrix

Evaluate which formats are active per platform:

FormatGoogleMetaLinkedInTikTokMicrosoft
Static ImageRSA image ext✅✅❌Multimedia
VideoYouTube, PMax✅✅✅ (required)✅ (9:16 vertical, April 2025)
Carousel❌✅✅❌❌
Collection❌✅❌❌❌
Document❌❌✅❌❌
ShoppingPMax, ShoppingCatalog❌ShopShopping

Apple Ads Format Support:

FormatApple Ads
Static Image✅ (Custom Product Pages)
Video✅ (App preview videos)
Search Tab✅ (banner)
Today Tab✅ (editorial-style)

Andromeda Creative Similarity Score (Meta)

Meta's Andromeda engine (launched October 2025) clusters ads with >60% similarity and suppresses delivery of near-identical creatives. 100 minor variations (color swaps, small text changes) perform no better than 10 genuinely distinct creatives. Evaluate:

  • Are creatives genuinely diverse in concept, angle, and format?
  • Flag accounts relying on iterative variations rather than distinct concepts
  • Recommend testing fundamentally different hooks, formats, and value propositions

Symphony Automation Awareness (TikTok, 2025)

TikTok's Symphony AI (2025) generates creative variations from product URLs. Assess:

  • Whether account uses AI-generated vs original creatives
  • Quality and performance comparison of Symphony vs manual creatives
  • Impact on creative refresh strategy (Symphony can accelerate iteration)

Creative Health Scoring Weights

Format Diversity:      25%  ████████░░
Fatigue Signals:       25%  ████████░░
Platform Compliance:   20%  ██████░░░░
Refresh Cadence:       15%  █████░░░░░
Volume:                15%  █████░░░░░

Grade: A (90-100), B (75-89), C (60-74), D (40-59), F (<40).

Creative Check IDs

IDCheckSeverity
CR-01Format diversity: >=3 formats per platformHigh
CR-02Creative volume: meets platform minimumsHigh
CR-03Fatigue detection: CTR/engagement declining past thresholdsCritical
CR-04Refresh cadence: within platform-recommended cycleHigh
CR-05Platform compliance: specs, safe zones, text limitsCritical
CR-06Hook quality: first 1-5s engagement (video) or headline impact (static)High
CR-07UGC ratio: UGC/testimonial content tested on Meta and TikTokMedium
CR-08Video specs: codec, resolution, aspect ratio per platformMedium
CR-09Safe zone compliance: critical elements within 900x1000px usable areaMedium
CR-10Andromeda diversity: genuinely distinct concepts, not iterative variations (Meta)High

Universal Creative Best Practices

Cross-Platform Safe Zone

  • 900x1000px usable area works across all vertical placements
  • Keep critical elements centered and within safe margins
  • Test on mobile devices (75%+ of ad impressions are mobile)

Ad Copy Principles

  • Lead with benefit, not feature
  • Include clear CTA (what should they do next?)
  • Match ad message to landing page (message match)
  • Use numbers and specifics over vague claims
  • Test emotional vs rational appeals

Video Production Standards

  • H.264 codec, AAC audio, MP4 container
  • Minimum 720p (1080p preferred)
  • Subtitles/captions always (accessibility + sound-off viewing)
  • Brand mention within first 5s (awareness) or at CTA (performance)

Output

Creative Quality Report

Cross-Platform Creative Health

Google:     ████████░░  X/X checks passing
Meta:       ██████████  X/X checks passing
LinkedIn:   ███████░░░  X/X checks passing
TikTok:     █████░░░░░  X/X checks passing
Microsoft:  ████████░░  X/X checks passing

Deliverables

  • CREATIVE-AUDIT-REPORT.md: Per-platform creative assessment
  • Fatigue alerts (any creative past refresh cadence)
  • Format diversity gaps per platform
  • Production priority list (most impactful creative to produce next)
  • Quick Wins (format conversions, CTA changes, Spark Ads setup)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.