performance-analytics
Analyze marketing performance with key metrics, trend analysis, and optimization recommendations
Best use case
performance-analytics is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Analyze marketing performance with key metrics, trend analysis, and optimization recommendations
Teams using performance-analytics should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/performance-analytics/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How performance-analytics Compares
| Feature / Agent | performance-analytics | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Analyze marketing performance with key metrics, trend analysis, and optimization recommendations
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Performance Analytics Skill Frameworks for measuring, reporting, and optimizing marketing performance across channels and campaigns. ## Key Marketing Metrics by Channel ### Email Marketing | Metric | Definition | Benchmark Range | |--------|-----------|----------------| | Delivery rate | Emails delivered / emails sent | 95-99% | | Open rate | Unique opens / emails delivered | 15-30% | | Click-through rate (CTR) | Unique clicks / emails delivered | 2-5% | | Click-to-open rate (CTOR) | Unique clicks / unique opens | 10-20% | | Unsubscribe rate | Unsubscribes / emails delivered | <0.5% | | Conversion rate | Conversions / emails delivered | 1-5% | ### Paid Advertising (Search and Social) | Metric | Definition | |--------|-----------| | Click-through rate (CTR) | Clicks / impressions | | Cost per click (CPC) | Total spend / clicks | | Conversion rate | Conversions / clicks | | Cost per acquisition (CPA) | Total spend / conversions | | Return on ad spend (ROAS) | Revenue / ad spend | | Quality Score (search) | Google's relevance rating (1-10) | ### SEO / Organic Search | Metric | Definition | |--------|-----------| | Organic sessions | Visits from organic search | | Keyword rankings | Position for target keywords | | Organic CTR | Clicks / impressions in search results | | Domain authority | Third-party authority score | | Backlinks | Number of external sites linking to you | | Organic conversion rate | Organic conversions / organic sessions | ### Overall Marketing / Pipeline | Metric | Definition | |--------|-----------| | Marketing qualified leads (MQLs) | Leads meeting marketing qualification criteria | | MQL to SQL conversion rate | SQLs / MQLs | | Pipeline generated | Dollar value of opportunities created | | Customer acquisition cost (CAC) | Total marketing + sales cost / new customers | | Marketing-sourced revenue | Revenue from marketing-originated deals | ## Reporting Templates ### Weekly Marketing Report - **Top 3 metrics** with week-over-week change - **What worked** this week (1-2 bullet points with data) - **What needs attention** (1-2 bullet points with data) - **This week's priorities** (3-5 action items) ### Monthly Marketing Report 1. Executive summary (3-5 sentences) 2. Key metrics dashboard (table with MoM and target comparison) 3. Channel-by-channel performance summary 4. Campaign highlights and results 5. What worked and what did not (with hypotheses) 6. Recommendations and next month priorities 7. Budget spend vs. plan ## Trend Analysis and Forecasting ### Trend Identification 1. Directional trends over 4+ periods 2. Inflection points and what caused them 3. Seasonality patterns 4. Anomalies and their causes 5. Leading indicators ### Simple Forecasting Approaches - **Linear projection**: extend the current trend line forward - **Moving average**: smooth noise by averaging last 3-6 periods - **Year-over-year comparison**: use last year's pattern as baseline - **Funnel math**: forecast outputs from inputs - **Scenario modeling**: best case, expected case, worst case ## Attribution Modeling Basics | Model | How It Works | Best For | |-------|-------------|----------| | Last touch | 100% credit to last interaction | Understanding final conversion triggers | | First touch | 100% credit to first interaction | Understanding top-of-funnel effectiveness | | Linear | Equal credit to all touchpoints | Fair representation of all channels | | Time decay | More credit closer to conversion | Balanced view favoring recent interactions | | Position-based (U-shaped) | 40% first, 40% last, 20% middle | Valuing both discovery and conversion | | Data-driven | Algorithmic credit | Most accurate (requires high volume) | ## Optimization Recommendations Framework ### Optimization Levers by Funnel Stage | Funnel Stage | Problem Signal | Optimization Levers | |-------------|---------------|---------------------| | Awareness | Low impressions, low reach | Budget, targeting, channel mix, creative format | | Interest | Low CTR, low engagement | Ad creative, headlines, content hooks, audience targeting | | Consideration | High bounce rate, low time on page | Landing page content, page speed, content relevance, UX | | Conversion | Low conversion rate | Offer, CTA, form length, trust signals, page layout | | Retention | High churn, low repeat engagement | Onboarding, email nurture, product experience, support | ### Prioritization Framework **Priority order**: 1. High impact, low effort (do immediately) 2. High impact, high effort (plan and resource) 3. Low impact, low effort (do if capacity allows) 4. Low impact, high effort (deprioritize) ### Testing Best Practices - Test one variable at a time - Define success metric before launching - Calculate required sample size before starting - Run tests for minimum one full business cycle - Document all tests and results regardless of outcome ### Continuous Optimization Cadence - **Daily**: monitor paid campaigns for budget pacing and anomalies - **Weekly**: review channel performance, pause underperformers, scale winners - **Bi-weekly**: refresh ad creative and test new variants - **Monthly**: full performance review, identify new optimization opportunities - **Quarterly**: strategic review of channel mix, budget allocation, and targeting
Related Skills
orcawave-analysis-performance-targets
Sub-skill of orcawave-analysis: Performance Targets.
freecad-automation-performance-metrics
Sub-skill of freecad-automation: Performance Metrics.
sparc-specification-31-performance
Sub-skill of sparc-specification: 3.1 Performance (+2).
github-swarm-issue-metrics-and-analytics
Sub-skill of github-swarm-issue: Metrics and Analytics.
github-project-board-generate-board-analytics
Sub-skill of github-project-board: Generate Board Analytics.
python-scientific-computing-performance-tips
Sub-skill of python-scientific-computing: Performance Tips.
document-rag-pipeline-performance-metrics-real-world
Sub-skill of document-rag-pipeline: Performance Metrics (Real-World).
data-analysis-polars-high-performance-processing
Sub-skill of data-analysis: Polars High-Performance Processing (+5).
data-analysis-caching-for-performance
Sub-skill of data-analysis: Caching for Performance (+2).
dash-example-1-sales-analytics-dashboard
Sub-skill of dash: Example 1: Sales Analytics Dashboard (+2).
dash-1-optimize-callback-performance
Sub-skill of dash: 1. Optimize Callback Performance (+3).
social-media-key-performance-indicators
Sub-skill of social-media: Key Performance Indicators (+1).