菜单
Cross-platform creative quality audit: ad copy, video, image, format diversity; detects creative fatigue, scores diversity for Andromeda Entity-ID retrieval, sets production priorities. Use when user says creative audit, ad creative, creative fatigue, creative diversity score, or creative review.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | ads-creative |
| description | Cross-platform creative quality audit: ad copy, video, image, format diversity; detects creative fatigue, scores diversity for Andromeda Entity-ID retrieval, sets production priorities. Use when user says creative audit, ad creative, creative fatigue, creative diversity score, or creative review. |
| user-invokable | false |
| tested_date | "2026-05-17T00:00:00.000Z" |
| tested_with | claude-code v2.x |
ads/references/platform-specs.md for creative specificationsads/references/benchmarks.md for CTR/engagement benchmarksads/references/scoring-system.md for weighted scoring algorithm| 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 |
| Platform | Recommended Refresh |
|---|---|
| TikTok | Every 7-10 days (fastest fatigue) |
| Meta | Every 14-21 days |
| Every 4-6 weeks | |
| Google Search | Every 8-12 weeks |
| Microsoft | Every 8-12 weeks |
| YouTube | Every 4-8 weeks |
Evaluate which formats are active per platform:
| Format | Meta | 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) |
Meta's Andromeda engine (launched October 2025) clusters ads with >60% similarity and suppresses delivery of near-identical creatives (Confect; Meta Engineering). 100 minor variations (color swaps, small text changes) perform no better than 10 genuinely distinct creatives. Evaluate:
TikTok's Symphony AI (2025) generates creative variations from product URLs. Assess:
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).
| 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 |
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
CREATIVE-AUDIT-REPORT.md: Per-platform creative assessmentBuild, secure, and package Electron desktop apps — main/preload/renderer split, contextIsolation-safe typed IPC over a preload bridge, BrowserWindow + application menu + app naming, a strict CSP, and distribution (electron-builder/Forge, productName, code signing). Use when building an Electron app, wiring IPC, hardening security, fixing the app/menu name, or packaging. Do NOT use for web-only React UI (use cleanui) or Expo/React Native.
Write an engineering tech spec (design doc / RFC) that turns an approved PRD into an implementable design. Use when turning a PRD or epic into a design doc, writing an RFC, or answering 'how should we build this'. Do NOT use for product requirements (prd-development) or recording a single architectural decision (adr).
Run a right-sized threat-modeling pass (trust boundaries, STRIDE, abuse cases) on a forming design so security decisions land before Sign-Off 2. Use when a design adds attack surface — a new endpoint, data class, integration, or authz change. Do NOT use for code-diff security review (/security-review), pentests, or compliance audits.
Build and maintain a durable automated E2E suite — Playwright for web, Maestro for Expo/React Native: stable selectors, owned test data, CI gating, and a flake policy with teeth. Use when automating the E2E journeys a test plan defines or fixing a slow/flaky suite. Do NOT use for deciding what to test (test-strategy) or unit tests (tdd).
Run a go/no-go release review producing a scored readiness report — rollout plan, observability, rollback, comms verified before shipping. Use when preparing a release/launch, a go-live checklist, a rollout plan, or 'are we ready to ship'. Do NOT use for store-submission mechanics (expo-deployment) or writing the test plan itself (test-strategy).
Define production health before launch: user-centric SLIs, SLO targets with error budgets, burn-rate alerts that page on user pain (not CPU), and a runbook per pageable alert. Use when designing SLOs, alerts, error budgets, or runbooks. Do NOT use for the go/no-go review (release-readiness) or post-incident analysis (incident-postmortem).