Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Google Ads・Meta・LinkedIn等の有料広告キャンペーンを設計・最適化するスキル。 「広告を出したい」「広告キャンペーンを作って」「リターゲティング」等のリクエストで発動。
.claude/skills/minicoohei-paid-ads/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 114% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 91% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 103% | 0% |
You are an expert performance marketer with direct access to ad platform accounts. Your goal is to help create, optimize, and scale paid advertising campaigns that drive efficient customer acquisition.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
| Platform | Best For | Use When | |----------|----------|----------| | Google Ads | High-intent search traffic | People actively search for your solution | | Meta | Demand generation, visual products | Creating demand, strong creative assets | | LinkedIn | B2B, decision-makers | Job title/company targeting matters, higher price points | | Twitter/X | Tech audiences, thought leadership | Audience is active on X, timely content | | TikTok | Younger demographics, viral creative | Audience skews 18-34, video capacity |
Account
├── Campaign 1: [Objective] - [Audience/Product]
│ ├── Ad Set 1: [Targeting variation]
│ │ ├── Ad 1: [Creative variation A]
│ │ ├── Ad 2: [Creative variation B]
│ │ └── Ad 3: [Creative variation C]
│ └── Ad Set 2: [Targeting variation]
└── Campaign 2...[Platform]_[Objective]_[Audience]_[Offer]_[Date]
Examples:
META_Conv_Lookalike-Customers_FreeTrial_2024Q1
GOOG_Search_Brand_Demo_Ongoing
LI_LeadGen_CMOs-SaaS_Whitepaper_Mar24Testing phase (first 2-4 weeks):
Scaling phase:
Problem-Agitate-Solve (PAS): > Problem] → Agitate the pain] → Introduce solution] → CTA]
Before-After-Bridge (BAB): > Current painful state] → Desired future state] → Your product as bridge]
Social Proof Lead: > Impressive stat or testimonial] → What you do] → CTA]
For detailed templates and headline formulas: See references/ad-copy-templates.md
| Platform | Key Targeting | Best Signals | |----------|---------------|--------------| | Google | Keywords, search intent | What they're searching | | Meta | Interests, behaviors, lookalikes | Engagement patterns | | LinkedIn | Job titles, companies, industries | Professional identity |
For detailed targeting strategies by platform: See references/audience-targeting.md
Production tips:
| Objective | Primary Metrics | |-----------|-----------------| | Awareness | CPM, Reach, Video view rate | | Consideration | CTR, CPC, Time on site | | Conversion | CPA, ROAS, Conversion rate |
If CPA is too high:
If CTR is low:
If CPM is high:
| Funnel Stage | Audience | Message | Goal | |--------------|----------|---------|------| | Top | Blog readers, video viewers | Educational, social proof | Move to consideration | | Middle | Pricing/feature page visitors | Case studies, demos | Move to decision | | Bottom | Cart abandoners, trial users | Urgency, objection handling | Convert |
| Stage | Window | Frequency Cap | |-------|--------|---------------| | Hot (cart/trial) | 1-7 days | Higher OK | | Warm (key pages) | 7-30 days | 3-5x/week | | Cold (any visit) | 30-90 days | 1-2x/week |
Before launching campaigns, ensure proper tracking and account setup.
For complete setup checklists by platform: See references/platform-setup-checklists.md
For implementation, see the tools registry. Key advertising platforms:
| Platform | Best For | MCP | Guide | |----------|----------|:---:|-------| | Google Ads | Search intent, high-intent traffic | ✓ | google-ads.md | | Meta Ads | Demand gen, visual products, B2C | - | meta-ads.md | | LinkedIn Ads | B2B, job title targeting | - | linkedin-ads.md | | TikTok Ads | Younger demographics, video | - | tiktok-ads.md |
For tracking, see also: ga4.md, segment.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 13,921 | 14,119 | +1% | 1 | 1 | 0% | 2,429 | 4,934 | +103% | 0 | 0 | — |
case-02 | fail→pass | 15,704 | 15,972 | +2% | 1 | 1 | 0% | 2,397 | 5,128 | +114% | 0 | 0 | — |
case-03 | fail→fail | 15,770 | 17,098 | +8% | 1 | 1 | 0% | 2,744 | 5,113 | +86% | 0 | 0 | — |
case-04 | fail→pass | 16,320 | 12,346 | -24% | 1 | 1 | 0% | 2,517 | 4,339 | +72% | 0 | 0 | — |
case-05 | fail→fail | 10,337 | 7,090 | -31% | 1 | 1 | 0% | 1,740 | 3,546 | +104% | 0 | 0 | — |
case-06 | fail→pass | 15,771 | 11,712 | -26% | 1 | 1 | 0% | 2,429 | 4,321 | +78% | 0 | 0 | — |
case-07 | pass→pass | 13,266 | 10,134 | -24% | 1 | 1 | 0% | 2,100 | 3,947 | +88% | 0 | 0 | — |
case-08 | pass→pass | 13,826 | 8,800 | -36% | 1 | 1 | 0% | 2,185 | 3,644 | +67% | 0 | 0 | — |
case-09 | pass→pass | 11,013 | 9,787 | -11% | 1 | 1 | 0% | 1,684 | 3,604 | +114% | 0 | 0 | — |
case-10 | fail→fail | 13,636 | 11,974 | -12% | 1 | 1 | 0% | 2,134 | 4,079 | +91% | 0 | 0 | — |
case-11 | fail→fail | 10,066 | 9,630 | -4% | 1 | 1 | 0% | 1,457 | 3,765 | +158% | 0 | 0 | — |
case-12 | pass→pass | 11,247 | 14,306 | +27% | 1 | 1 | 0% | 1,712 | 3,941 | +130% | 0 | 0 | — |
case-13 | pass→pass | 13,796 | 10,503 | -24% | 1 | 1 | 0% | 2,020 | 3,823 | +89% | 0 | 0 | — |
case-14 | pass→pass | 12,201 | 9,399 | -23% | 1 | 1 | 0% | 1,852 | 3,790 | +105% | 0 | 0 | — |
case-15 | fail→pass | 13,013 | 9,890 | -24% | 1 | 1 | 0% | 2,063 | 3,939 | +91% | 0 | 0 | — |
case-16 | pass→pass | 16,629 | 11,760 | -29% | 1 | 1 | 0% | 2,279 | 4,102 | +80% | 0 | 0 | — |
case-17 | pass→pass | 14,182 | 10,362 | -27% | 1 | 1 | 0% | 2,015 | 3,865 | +92% | 0 | 0 | — |
case-18 | pass→pass | 12,180 | 11,696 | -4% | 1 | 1 | 0% | 1,930 | 4,098 | +112% | 0 | 0 | — |
case-19 | pass→pass | 10,583 | 7,006 | -34% | 1 | 1 | 0% | 1,514 | 3,398 | +124% | 0 | 0 | — |
case-20 | pass→pass | 3,600 | 4,084 | +13% | 1 | 1 | 0% | 533 | 3,007 | +464% | 0 | 0 | — |
case-21 | pass→pass | 4,154 | 5,131 | +24% | 1 | 1 | 0% | 618 | 3,259 | +427% | 0 | 0 | — |
case-22 | pass→pass | 2,751 | 3,607 | +31% | 1 | 1 | 0% | 330 | 2,942 | +792% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.