Agent skill · Data & Analytics

marketing-analytics

Marketing analytics - UTM, attribution, CAC, ROAS, conversion tracking.

vibeeval521★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add vibeeval/vibecosystem --skill marketing-analytics --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 20 KB
Bundled scripts: none
Path: skills/marketing-analytics/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 521
Language: C#

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Defines a Marketing Analytics skill that guides an AI agent to perform comprehensive marketing measurement tasks: UTM tracking setup and parsing, attribution modelling (First/Last/Linear/Time Decay/U-Shaped/W-Shaped/Data-Driven), Multi-Touch attribution SQL and a Markov chain exemplar, CAC calculations and channel breakdowns, ROAS calculations and dashboard queries, Conversion Tracking setup across client-side and server-side flows, a Marketing funnel SQL, Landing Page metrics and A/B test template, Email marketing KPIs and a corresponding query, plus Social Media analytics metrics and a Social ROI function. The content provides code samples (TypeScript, SQL, and some Markdown tables) and concrete function/class signatures to implement these analyses.

How it works

  • UTM Tracking Setup: shows how to construct UTMs via a TypeScript UTMConfig interface and buildUTMUrl, then a captureUTM function that reads URL parameters, stores first touch and last touch in localStorage.
  • Attribution Modelling: lists models (First Touch, Last Touch, Linear, Time Decay, U-Shaped, W-Shaped, Data-Driven) and provides a Multi-Touch Attribution SQL example (U-Shaped) and a Markov Chain style calculation function calculateRemovalEffect(matrix, channels).
  • CAC: provides CACMetrics interface and calculateCAC to compute blended, paid, and organic CAC, plus a CAC by Channel SQL query and benchmarks table.
  • ROAS: includes a calculateROAS function returning roas, roasPercentage, and profitable, a targetROAS helper, and a ROAS Dashboard SQL query plus benchmarks.
  • Conversion Tracking: defines a ConversionEvent interface and a trackConversion async function that calls internal analytics, Facebook Conversions API, and Google offline conversions; includes a Conversion Funnel SQL.
  • Landing Page, Email, Social: contains templates for metrics, A/B tests, KPI dashboards, and a Social ROI function with a TypeScript interface and computed metrics.
  • Throughout, the skill uses concrete file names, function names, and SQL snippets as shown in the examples.

When to use it

  • Use when you need structured marketing measurement across UTMs, attribution modeling, CAC/ROAS, and conversion tracking with concrete code patterns. The skill is suited for building analytics pipelines, dashboards, and reporting components for a marketing analytics workflow.

What it can touch

  • Tools declared: claude-code
  • It references code blocks and function signatures in TypeScript and SQL scripts, but does not specify external systems beyond the included code samples. It does not declare additional touchpoints beyond the code patterns shown (localStorage usage, browser URL parsing, analytics.track, and external APIs in the Conversion Tracking section).

Caveats

  • The material is largely example code and schema snippets; it may require adaptation to integrate with actual data models, environments, and privacy/compliance requirements. It does not state deployment details or production-grade error handling beyond the sample code.
From the SKILL.md

# Marketing Analytics ## UTM Tracking Setup ### UTM Parameter Standartlari ``` https://example.com/landing? utm_source=google # Trafik kaynagi (google, facebook, newsletter) &utm_medium=cpc # Kanal tipi (cpc, email, social, organic) &utm_campaign=spring_2026 # Kampanya adi &utm_term=saas+analytics # Arama terimi (paid search) &utm_content=hero_banner # Reklam varyanti (A/B test) ``` ### UTM Naming Convention | Parameter | Format | Ornekler | |-----------|--------|---------| | source | lowercase, platform adi | google, facebook, linkedin, newsletter | | medium | lowercase, kanal tipi | cpc, cpm, email, social, organic, referral | | campaign | snake_case, tarih dahil | spring_sale_2026, product_launch_q1 | | term | + ile ayrilmis | saas+analytics, project+management | | content | snake_case, varyant | hero_banner, sidebar_cta, email_v2 | ### UTM Builder (TypeScript) ```typescript interface UTMConfig { baseUrl: string; source: string; medium: string; campaign: string; term?: string; content?: string; } function buildUTMUrl(config: UTMConfig): string { const params = new URLSearchParams(); params.set("utm_source", config.source.toLowerCase()); params.set("utm_medium", config.medium.toL

What's inside
Steps it walks through
  1. UTM Tracking Setup
  2. UTM Parameter Standartlari
  3. UTM Naming Convention
  4. UTM Builder (TypeScript)
  5. Attribution Modeling
  6. Attribution Modelleri
  7. Multi-Touch Attribution Query
  8. Markov Chain Attribution
  9. CAC (Customer Acquisition Cost)
  10. CAC Hesaplama
  11. CAC by Channel Query
  12. CAC Benchmarks
  13. ROAS (Return on Ad Spend)
  14. ROAS Calculator
More from vibecosystem
All skills →
About this skill
What does the marketing-analytics skill do?

Marketing analytics - UTM, attribution, CAC, ROAS, conversion tracking.

How do I install it?

Run `npx skills add vibeeval/vibecosystem --skill marketing-analytics --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From vibeeval/vibecosystem, a repository with 521 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going