Ads tiktok
Skill kennyolofsson23-netizen/claude-code-config/skills/claude-ads/skills/ads-tiktok
The most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.
npx -y skills add kennyolofsson23-netizen/claude-code-config --skill ads-tiktokAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", or "TikTok campaign".
SKILL.md
6.2 KB, ~1.6k tokens by cl100k_base, as published. Nobody here has run it
TikTok Ads Deep Analysis
Process
- Collect TikTok Ads data (Ads Manager export, Pixel/Events API status)
- Read
ads/references/tiktok-audit.mdfor full 25-check audit - Read
ads/references/benchmarks.mdfor TikTok-specific benchmarks - Read
ads/references/platform-specs.mdfor creative specifications - Read
ads/references/scoring-system.mdfor weighted scoring algorithm - Evaluate all applicable checks as PASS, WARNING, or FAIL
- Calculate TikTok Ads Health Score (0-100)
- Generate findings report with action plan
What to Analyze
Creative Quality (30% weight)
- ≥6 creatives per ad group (T05) — Critical
- All video 9:16 vertical 1080x1920 (T06) — Critical
- Native-looking content, not corporate/polished (T07)
- Hook in first 1-2 seconds (T08)
- No creative active >7 days with declining CTR (T09)
- Spark Ads tested: ~3% CTR vs ~2% standard (T10)
- TikTok Shop integration for e-commerce (T20)
- Video Shopping Ads tested (T21)
- Caption SEO with high-intent keywords (T22)
- Trending audio used (sound-on platform) (T23)
- Custom CTA button, not default (T24)
- Safe zone compliance: X:40-940, Y:150-1470 (T25)
Technical Setup (25% weight)
- TikTok Pixel installed and firing on all pages (T01)
- Events API + ttclid passback active (T02)
- Standard events configured (ViewContent, AddToCart, Purchase, CompleteRegistration)
- Advanced matching parameters configured
Bidding & Budget (20% weight)
- Bid strategy matches goal: Lowest Cost for volume, Cost Cap for efficiency (T11)
- Daily budget ≥50x target CPA per ad group (T12)
- Learning phase: ≥50 conversions per 7 days per ad group (T13)
- No edits during learning phase (resets learning)
Structure & Settings (15% weight)
- Separate campaigns for prospecting vs retargeting (T03)
- Smart+ campaigns tested: 42% adoption, 1.41-1.67 ROAS (T04)
- Search Ads Toggle enabled (T14)
- Placement selection reviewed: TikTok, Pangle, etc. (T15)
- Dayparting aligned with audience activity (T16)
Performance (10% weight)
- CTR ≥1.0% for in-feed ads (T17)
- CPA within target, 3x Kill Rule applies (T18)
- Average video watch time ≥6 seconds (T19)
Creative-First Strategy
TikTok is a creative-first platform. Unlike Google/Meta where targeting and bidding drive most performance, TikTok success depends primarily on creative quality.
What Makes a TikTok Ad Work
- Native feel: looks like organic content, not a polished ad
- Sound-on: 93% of TikTok is consumed with sound (never run silent)
- Fast hooks: capture attention in 1-2 seconds or lose the viewer
- Trend alignment: use trending sounds, formats, and editing styles
- UGC style: user-generated content outperforms studio content
- Vertical only: 9:16 is non-negotiable (no letterboxed horizontal)
Creative Testing Framework
- Test 3-5 hooks per winning concept
- Rotate creatives every 5-7 days (fatigue sets in fast)
- Kill underperformers after 3 days if CTR <0.5%
- Scale winners by duplicating (not increasing budget on same ad)
- Repurpose winning concepts, not assets (fresh footage, same angle)
Safe Zone
All critical text, logos, and CTAs must be within the safe zone:
┌──────────────────────┐
│ UNSAFE (status) │ Y: 0-150px
├──────────────────────┤
│ │UNSA│
│ │FE │
│ SAFE ZONE │icon│ X: 40-940px
│ 900×1320px │ │ Y: 150-1470px
│ │ │
│ │ │ Right 140px: like/comment/share
├──────────────────────┤
│ UNSAFE (caption) │ Y: 1470-1920px
└──────────────────────┘
TikTok Shop Assessment
If e-commerce, evaluate TikTok Shop setup:
- Product catalog connected and synced
- Product detail pages complete (images, descriptions, reviews)
- Video Shopping Ads linking to in-app checkout
- Shop tab on TikTok profile configured
- Affiliate program active (if applicable)
- Shop CVR benchmark: >10% (significantly higher than standard landing page)
Smart+ Campaigns
- 42% of advertisers have adopted Smart+ (TikTok's automated campaign type)
- Average ROAS: 1.41-1.67
- Best for: e-commerce with product feed, app installs
- Evaluate: is the advertiser testing Smart+ alongside manual campaigns?
- Compare Smart+ performance vs manual for same objectives
TikTok Context
| Setting | Value |
|---|---|
| CPM | 40-60% cheaper than Meta |
| Spark Ads CTR | ~3% (vs ~2% standard) |
| Smart+ adoption | 42% of advertisers |
| Smart+ ROAS | 1.41-1.67 |
| Shop CVR | >10% |
| Available markets | 11 countries (US, UK, ID, MY, PH, SG, TH, VN, JP, KR, BR) |
Key Thresholds
| Metric | Pass | Warning | Fail |
|---|---|---|---|
| CTR (in-feed) | ≥1.0% | 0.5-1.0% | <0.5% |
| Creatives per ad group | ≥6 | 3-5 | <3 |
| Video watch time | ≥6s | 3-6s | <3s |
| Learning conversions | ≥50/week | 30-50/week | <30/week |
| Daily budget | ≥50x CPA | 20-49x CPA | <20x CPA |
| Creative age (declining) | <7 days | 7-14 days | >14 days |
Output
TikTok Ads Health Score
TikTok Ads Health Score: XX/100 (Grade: X)
Creative Quality: XX/100 ████████░░ (30%)
Technical Setup: XX/100 ██████████ (25%)
Bidding & Budget: XX/100 ███████░░░ (20%)
Structure: XX/100 █████░░░░░ (15%)
Performance: XX/100 ████████░░ (10%)
Deliverables
TIKTOK-ADS-REPORT.md— Full 25-check findings with pass/warning/fail- Creative scorecard per ad (hook quality, safe zone, native feel)
- Smart+ vs manual performance comparison
- TikTok Shop readiness assessment (if e-commerce)
- Quick Wins sorted by impact
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in ~1.6k tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.