Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add modu-ai/moai-cowork --skill marketing-pixel-auditgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modu-ai/moai-cowork/marketing-pixel-audit)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/marketing-pixel-audit"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/marketing-pixel-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/marketing-pixel-audit"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/marketing-pixel-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00320 | $0.02421 |
| Opus 5 | $0.00160 | $0.01210 |
| Sonnet 5 | $0.00064 | $0.00484 |
| Haiku 4.5 | $0.00032 | $0.00242 |
Grade A, and why
marketing-pixel-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
픽셀·1st Party 데이터 진단 (Pixel Audit)
개요
3rd party 쿠키 종료 시대(애플 ATT + 구글 쿠키 종료)에 1st party 데이터를 가진 브랜드 vs 없는 브랜드의 광고 효율 차이가 점점 벌어집니다. 본 스킬은 그 격차를 측정·진단합니다.
책임 한 줄: 메타·구글 픽셀 설치 상태 + 1st Party 데이터 + Lookalike 씨앗 품질 진단 → 개선 우선순위 자동 생성.
픽셀 설계에서 가장 많이 하는 실수 3종
실수 1: 구매자 미제외
이미 산 사람에게 "아직 구매 안 하셨나요?" 광고를 계속 보내는 것.
진단: 메타 광고 관리자 → 광고 세트 → 오디언스 제외에 Purchase 이벤트 30일 트리거 추가 여부.
- ❌ 미설정 → 광고비 누수 (구매자도 광고 노출)
- ✅ 설정 → 신규 구매 후보에만 노출
실수 2: 이벤트 파라미터 미설정
ViewContent·AddToCart에 상품 ID와 가격 파라미터를 붙여야 동적 광고(DPA)가 작동.
진단 코드:
// ❌ 잘못된 예
fbq('track', 'ViewContent');
// ✅ 올바른 예
fbq('track', 'ViewContent', {
content_ids: ['SKU123'],
content_type: 'product',
value: 19800,
currency: 'KRW'
});
실수 3: 전환 API 미설치 (CAPI)
픽셀만으로는 iOS 사용자의 전환 추적이 불완전. 서버 사이드 전환 API(CAPI)를 같이 설치 필수.
iOS 14.5+ 이후:
- pixel-only: 실제 전환의 50-70%만 추적
- pixel + CAPI: 90%+ 추적 가능
1st Party 데이터 3종
| 데이터 | 활용 강도 | 활용 방법 |
|---|---|---|
| 이메일·전화번호 | 가장 강력 | 뉴스레터·구매·이벤트로 수집 → 메타·구글 업로드 → 커스텀 오디언스 + Lookalike 씨앗 |
| 픽셀 이벤트 데이터 | 강함 | PageView → ViewContent → AddToCart → InitiateCheckout → Purchase 5단계 |
| 구매·CRM 데이터 | 매우 강함 | 재구매 주기 예측, VIP 세그먼트, 휴면 고객 재활성 |
Lookalike — 씨앗 품질이 전부
Lookalike의 품질 한계 = 씨앗 데이터의 품질 한계.
| 씨앗 데이터 | Lookalike 품질 |
|---|---|
| 전체 방문자 | 낮음 (구매 의도 없는 사람 포함) |
| 장바구니 추가자 | 중 |
| 구매자 전체 | 높음 |
| VIP 구매자 (상위 20%) | 최고 ⭐ |
실전 권장 사항
1. VIP 구매자(상위 20%) 데이터 추출 (LTV·구매 횟수·평균 객단가 상위)
2. 메타에 커스텀 오디언스 업로드
3. Lookalike 생성 (유사도 1~3%부터 시작 → 포화되면 확장)
4. 기존 고객 반드시 제외
5. 월 1회 이상 씨앗 데이터 최신 상태 업데이트
워크플로우 — 진단 체크리스트
[Step 1] 사이트 URL + 광고 채널 사용 여부 입력
↓
[Step 2] A. 메타 픽셀 / B. 구글 픽셀 / C. 1st Party / D. Lookalike 4영역 점검
↓
[Step 3] 영역별 점수 산출 (100점 만점)
↓
[Step 4] Phase 1 (즉시) / Phase 2 (단계적) / Phase 3 (최적화) 우선순위 자동 분류
↓
[Step 5] 진단 보고서 출력 + (선택) moai-marketer:marketing-campaign-planner·moai-seller:commerce-marketplace-coupang-ads 체이닝
A. 메타 픽셀
- 픽셀 설치 (Facebook Pixel Helper로 확인)
- PageView 이벤트 작동
- ViewContent 이벤트 + content_ids/value/currency 파라미터
- AddToCart 이벤트 + 파라미터
- Purchase 이벤트 + 파라미터
- CAPI (서버 사이드 전환 API) 설치
- 광고 세트 오디언스 제외에 Purchase 30일 추가
- Aggregated Event Measurement (AEM) 8개 이벤트 설정
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 193 lines · 320 tokens per session scan A 74b95addc195
marketing-pixel-audit is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 8d ago), licensed Apache-2.0. It adds 320 tokens to every session and 2,421 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
market-intelligence-report
Produce a Market Intelligence Report — YouTube competitive research, channel analysis, content gap discovery, idea generation, daily scanning, and AI trend scouting — then render it as a BenAI-branded HTML dashboard in the instant-ui design language. Use this skill whenever the user says "market intelligence report"…
linkedin-writer-vault
Vault-aware LinkedIn writer. Same step-by-step LinkedIn post process as linkedin-writer, but ICP, voice, and offer context come from the vault's Context/ folder instead of being bundled inside the skill. Update one file in the vault and every skill pointing to it inherits the change. TRIGGERS: LinkedIn post, LinkedIn…
operator
Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…
crm-prospect-mining
Mine high-value prospects from CRM pipeline stages (Lost, No Show, Churned, Stalled) by cross-referencing records with LinkedIn company data and comms history. Connects to any CRM, pulls records from target stages, filters out personal email domains, finds company LinkedIn pages via web research, bulk-scrapes company…
marketing-os-carousel
Build an image-first social carousel from an asset already filed in the Marketing OS, export it as a PDF, and record it back as a real channel asset. Brand palette, typography, the logo pointer and the never-black-background rule all resolve from Context/brand/brand-kit.md. Source is a filed newsletter edition…
seo-hreflang
Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations for HTML, HTTP headers, and XML sitemaps. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region"…