# Ads Creative

> 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.

- Skill: `elinking-111/ads-creative` (Agent Skill)
- Install (CLI): `npx skillmds@latest add elinking-111/ads-creative`
- Raw SKILL.md: https://api.skillmd.com/api/skills/elinking-111/ads-creative/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: elinking-111 (https://skillmd.com/u/elinking-111)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/elinking-111/ads-creative

---


<!-- Updated: 2026-07-16 | v1.6 -->

# 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. Normalize creative-level data before judging:
   - creative/ad id, platform, campaign, ad set/ad group, status, launch date, spend, impressions, clicks, CTR, CPC, CPM, conversions, CPA/CAC, ROAS, thumbstop/hook rate, watch time, hold rate, saves, comments, shares where available.
   - asset fields: format, aspect ratio, duration, landing page, product/service, creator/persona, offer, CTA, claim, hook, visual style, proof type, funnel stage.
7. Evaluate creative quality per platform
8. Assess cross-platform creative consistency
9. Build a creative taxonomy and winner/loser map
10. **Validate**: verify fatigue signals reference actual performance trends, not assumptions
11. Generate production priority recommendations and next creative briefs

## Creative Intelligence Taxonomy

Use this taxonomy whenever enough ad-level or creative-level data exists. If the
raw exports do not include these fields, infer cautiously from creative text,
thumbnails, videos, screenshots, or user-provided descriptions and mark inferred
fields explicitly.

| Dimension | Examples | Why It Matters |
|-----------|----------|----------------|
| Hook type | problem, transformation, demo, social proof, contrarian, offer-led, curiosity | Explains first-touch attention, especially video thumbstop rate |
| Angle | price, speed, ease, trust, quality, novelty, status, risk reduction, ROI | Connects message strategy to CPA/ROAS |
| Format | static, UGC video, founder video, product demo, carousel, testimonial, before-after, comparison, document | Reveals missing test formats and platform fit |
| Visual style | studio, native UGC, screen recording, lifestyle, annotated UI, creator talking head, meme, editorial | Separates concept diversity from cosmetic variation |
| Proof type | review, rating, case study, benchmark, credential, press, demo, guarantee | Helps judge trust and compliance risk |
| Offer | free trial, demo, discount, bundle, webinar, consultation, lead magnet, app install | Explains CVR and lead quality changes |
| CTA | buy now, learn more, book demo, start trial, install, get quote, download | Detects CTA-message mismatch |
| Funnel stage | prospecting, retargeting, brand defense, competitor conquest, retention, upsell | Prevents comparing cold and warm creative unfairly |
| Product/use case | SKU, category, feature, job-to-be-done, persona, vertical | Shows which products/use cases deserve more budget or assets |

### Winner / Loser Creative Map

For each creative cluster, classify:

- **Winner**: above-account median CTR/CVR/ROAS or below target CPA with enough spend/conversions.
- **Efficient but limited**: strong CPA/ROAS but low spend, weak delivery, or narrow audience.
- **Attention winner, conversion loser**: high CTR/thumbstop but weak CVR/CPA; check landing page, offer, lead quality, or mismatch.
- **Conversion winner, attention loser**: low CTR but strong CVR/ROAS; consider stronger hook or broader variants.
- **Fatiguing winner**: historically strong but declining CTR, rising CPA, rising frequency, or falling watch time.
- **Learning / inconclusive**: insufficient spend, impressions, or conversion volume.
- **Clear loser**: enough spend and impressions with weak CTR/CVR/CPA/ROAS vs target.

Do not call a creative a winner from CTR alone. Require downstream quality where
the business model depends on purchases, qualified leads, retention, trials, or
LTV.

## Creative Board Structure

When the user needs a client-ready or team-ready creative review, present a
creative board instead of a plain list of recommendations:

| Creative Cluster | Platform | Spend | CTR | CVR | CPA/ROAS | Status | Why | Next Test |
|------------------|----------|-------|-----|-----|----------|--------|-----|-----------|

Recommended board sections:

1. **Top winners to scale**: what to keep, resize, translate, or adapt cross-platform.
2. **Fatigue watchlist**: what needs refresh, new hooks, new creator, or new landing match.
3. **Losers to pause or learn from**: what failed and which hypothesis is invalidated.
4. **Missing tests**: formats, angles, offers, personas, or product scenes not yet tested.
5. **Next brief queue**: 3-10 production-ready briefs with hook, angle, format, proof, CTA, and platform.

## 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 quality, hook, subtitles (see ads-youtube sub-skill)

### 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
| Signal | Threshold | Action |
|--------|-----------|--------|
| CTR declining | >20% over 14 days | Refresh creative |
| Frequency (Meta) | >5.0 prospecting, >12.0 retargeting | New audience or creative |
| Watch time declining (TikTok) | <3s average | New hook needed |
| QS declining (Google) | Drop of 2+ points | Refresh ad copy |
| Engagement rate drop | >30% decline | Full creative overhaul |

### Refresh Cadence by Platform
| Platform | Recommended Refresh |
|----------|-------------------|
| TikTok | Every 7-10 days (fastest fatigue) |
| Meta | Every 14-21 days |
| LinkedIn | Every 4-6 weeks |
| Google Search | Every 8-12 weeks |
| Microsoft | Every 8-12 weeks |
| YouTube | Every 4-8 weeks |

## Format Diversity Matrix

Evaluate which formats are active per platform:

| Format | Google | Meta | LinkedIn | TikTok | Microsoft |
|--------|--------|------|----------|--------|-----------|
| Static Image | RSA image ext | ✅ | ✅ | ❌ | Multimedia |
| Video | YouTube, PMax | ✅ | ✅ | ✅ (required) | ✅ (9:16 vertical, April 2025) |
| Carousel | ❌ | ✅ | ✅ | ❌ | ❌ |
| Collection | ❌ | ✅ | ❌ | ❌ | ❌ |
| Document | ❌ | ❌ | ✅ | ❌ | ❌ |
| Shopping | PMax, Shopping | Catalog | ❌ | Shop | Shopping |

**Apple Ads Format Support:**

| Format | Apple 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

| ID | Check | Severity |
|----|-------|----------|
| CR-01 | Format diversity: >=3 formats per platform | High |
| CR-02 | Creative volume: meets platform minimums | High |
| CR-03 | Fatigue detection: CTR/engagement declining past thresholds | Critical |
| CR-04 | Refresh cadence: within platform-recommended cycle | High |
| CR-05 | Platform compliance: specs, safe zones, text limits | Critical |
| CR-06 | Hook quality: first 1-5s engagement (video) or headline impact (static) | High |
| CR-07 | UGC ratio: UGC/testimonial content tested on Meta and TikTok | Medium |
| CR-08 | Video specs: codec, resolution, aspect ratio per platform | Medium |
| CR-09 | Safe zone compliance: critical elements within 900x1000px usable area | Medium |
| CR-10 | Andromeda 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)