경쟁사 광고 분석 - 그들의 광고에서 growth strategy를 읽습니다 — Claude Skill

경쟁사 광고 분석

surface-level ad monitoring보다 더 깊게 들어갑니다. 단일 경쟁사를 잡고 그들의 전체 paid strategy를 reverse-engineer합니다. 무엇을 운영하는지, traffic을 어디로 보내는지, 무엇을 테스트하는지, 무엇이 작동하는지, 어디가 취약한지 파악합니다.

핵심 원칙: 경쟁사의 ad portfolio는 그들의 growth strategy를 보여주는 창입니다. 오래 운영되는 광고는 전환되는 것을 드러냅니다. 새 광고는 그들이 테스트하는 것을 드러냅니다. landing page는 positioning bet을 드러냅니다. 이 스킬은 모든 signal을 읽습니다.

언제 사용할지

• "[competitor]의 ad strategy를 teardown해줘"
• "[competitor]가 ad budget을 어디에 쓰고 있나요?"
• "[competitor]의 paid funnel을 reverse-engineer해줘"
• "[competitor]는 광고에서 어떻게 positioning하나요?"
• "[competitor]에 대한 deep competitive ad analysis"

Phase 0: Intake

1. Competitor name + domain — 누구를 teardown하나요?
2. Your product — comparison framing용
3. Channels — Meta, Google, 또는 둘 다? (default: both)
4. Depth level:
   • Standard: Ad scrape + landing page analysis
   • Deep: Standard + historical comparison + funnel reconstruction
5. Known competitor landing pages? — 광고에서 본 URL이 있나요?

Phase 1: Ad collection

1A: Meta Ad Library scrape

python3 skills/meta-ad-scraper/scripts/scrape_meta_ads.py \
  --domain <competitor_domain> \
  --output json

각 ad에서 capture:

• Ad copy(headline + primary text)
• Visual type(image / video / carousel)
• CTA button
• Landing page URL
• Active duration(first seen → still running or stopped)
• Platforms(Facebook, Instagram, Audience Network)
• Ad variations(A/B tests — same landing page, different creative)

1B: Google Ads Transparency scrape

python3 skills/google-ad-scraper/scripts/scrape_google_ads.py \
  --domain <competitor_domain> \
  --output json

각 ad:

• Headline variants
• Description lines
• Ad type(Search / Display / YouTube / Shopping)
• Landing page URL(display URL에서)
• Geographic targeting(보이는 경우)

Phase 2: Landing page analysis

ad에서 찾은 unique landing page URL마다:

Fetch: [landing_page_url]

추출:

• Hero headline — ad promise와 match하나요?
• Subheadline — value prop expansion
• Primary CTA — 어떤 action을 유도하나요? (Demo / Free trial / Sign up / Download)
• Social proof — logo, testimonial, case study metric
• Pricing visibility — pricing이 보이나요, 숨겨져 있나요?
• Form fields — 얼마나 많은 info를 요구하나요?
• Page type — general homepage / dedicated LP / feature page / use-case page
• Message match score — LP가 ad promise를 얼마나 잘 전달하나요? (1-10)

Phase 3: Strategic analysis

3A: Campaign clustering

모든 ad를 logical campaign으로 group합니다:

• Landing page destination — 같은 URL을 가리키는 ad = 같은 campaign
• Messaging theme — 비슷한 copy angle = 같은 strategic bet
• Audience signal — persona별 다른 copy

3B: Per-campaign analysis

각 campaign cluster마다:

3C: Budget allocation inference

ad volume과 platform distribution을 바탕으로 spend가 어디에 집중되는지 estimate합니다:

3D: Historical comparison(Deep mode)

landing page용 Web Archive data가 있다면:

• 지난 6-12개월 동안 positioning이 바뀌었나요?
• 어떤 campaign을 retire했나요? (Possible losers)
• 어떤 campaign을 scale up했나요? (Possible winners)

3E: Vulnerability analysis

광고 전략의 약점을 식별합니다:

Phase 4: 출력 형식

# 경쟁사 광고 분석: [Competitor Name] — [DATE]

Domain: [competitor.com]
Channels analyzed: [Meta, Google]
Total ads found: [N] (Meta: [N], Google: [N])
Unique landing pages: [N]
Estimated active campaigns: [N]

---

## Executive Summary

[3-5 sentence summary: What is this competitor doing with paid ads? What's working? Where are they vulnerable?]

---

## Campaign Breakdown

### Campaign 1: [Inferred Campaign Name]
- **Ads in cluster:** [N]
- **Platform(s):** [Meta / Google / Both]
- **Strategic intent:** [Awareness / Lead gen / Competitive displacement / etc.]
- **Target persona:** [Description]
- **Hook strategy:** [Type]
- **Landing page:** [URL]
  - Hero: "[Headline text]"
  - CTA: "[Button text]"
  - Message match: [Score/10]
- **Longevity:** [First seen date → status]
- **A/B tests detected:** [Yes/No — what they're testing]

**Sample ad:**
> **Headline:** [text]
> **Body:** [text]
> **CTA:** [button]
> **Format:** [Image/Video/Carousel]

**Assessment:** [1-2 sentences — is this working? Why/why not?]

### Campaign 2: ...

---

## Funnel Map

[Ad: Hook/Angle] → [LP: /landing-page-url] → [CTA: Book Demo] ↓ [Ad: Different angle] → [LP: /same-or-different] → [CTA: Free Trial]

---

## Budget Allocation Estimate

| Platform | Share | Focus Area |
|----------|-------|-----------|
| [Platform] | [X%] | [Intent] |

---

## What's Working (Long-Running Ads)

| Ad | Platform | Running Since | Why It Likely Works |
|----|----------|--------------|-------------------|
| [Headline excerpt] | [Platform] | [Date] | [Analysis] |

---

## Vulnerability Report

### 1. [Vulnerability]
**Evidence:** [What we observed]
**Your opportunity:** [How to exploit this gap]

### 2. ...

---

## Recommended Counter-Plays

### Counter-Play 1: [Name]
- **Target their weakness:** [Which vulnerability]
- **Your ad angle:** [Hook]
- **Platform:** [Where to run]
- **LP strategy:** [What your landing page should emphasize]

### Counter-Play 2: ...

clients/<client-name>/ads/competitor-teardown-[competitor]-[YYYY-MM-DD].md에 저장합니다.

비용

필요한 도구

• Apify API token — APIFY_API_TOKEN env var
• Upstream skills: meta-ad-scraper, google-ad-scraper
• fetch_webpage — landing page analysis용

트리거 문구

• "[competitor]의 ads를 teardown해줘"
• "[competitor]가 Meta/Google에서 무엇을 운영하나요?"
• "[competitor]의 paid funnel을 reverse-engineer해줘"
• "[competitor]에 대한 deep ad analysis"
• "[competitor]의 ad strategy 약점을 찾아줘"