Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "attribution," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wan
.claude/skills/mkurman-analytics-tracking/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 98% | 0% |
Event Name | Category | Properties | Trigger | Notes
---------- | -------- | ---------- | ------- | -----| Type | Examples | |------|----------| | Pageviews | Automatic, enhanced with metadata | | User Actions | Button clicks, form submissions, feature usage | | System Events | Signup completed, purchase, subscription changed | | Custom Conversions | Goal completions, funnel stages |
For comprehensive event lists: See references/event-library.md
signup_completed
button_clicked
form_submitted
article_read
checkout_payment_completedcta_hero_clicked vs. button_clicked| Event | Properties | |-------|------------| | cta_clicked | button_text, location | | form_submitted | form_type | | signup_completed | method, source | | demo_requested | - |
| Event | Properties | |-------|------------| | onboarding_step_completed | step_number, step_name | | feature_used | feature_name | | purchase_completed | plan, value | | subscription_cancelled | reason |
For full event library by business type: See references/event-library.md
| Category | Properties | |----------|------------| | Page | page_title, page_location, page_referrer | | User | user_id, user_type, account_id, plan_type | | Campaign | source, medium, campaign, content, term | | Product | product_id, product_name, category, price |
javascriptgtag('event', 'signup_completed', { 'method': 'email', 'plan': 'free' });
For detailed GA4 implementation: See references/ga4-implementation.md
| Component | Purpose | |-----------|---------| | Tags | Code that executes (GA4, pixels) | | Triggers | When tags fire (page view, click) | | Variables | Dynamic values (click text, data layer) |
javascriptdataLayer.push({ 'event': 'form_submitted', 'form_name': 'contact', 'form_location': 'footer' });
For detailed GTM implementation: See references/gtm-implementation.md
| Parameter | Purpose | Example | |-----------|---------|---------| | utm_source | Traffic source | google, newsletter | | utm_medium | Marketing medium | cpc, email, social | | utm_campaign | Campaign name | spring_sale | | utm_content | Differentiate versions | hero_cta | | utm_term | Paid search keywords | running+shoes |
blog_footer_cta, not cta1| Tool | Use For | |------|---------| | GA4 DebugView | Real-time event monitoring | | GTM Preview Mode | Test triggers before publish | | Browser Extensions | Tag Assistant, dataLayer Inspector |
| Issue | Check | |-------|-------| | Events not firing | Trigger config, GTM loaded | | Wrong values | Variable path, data layer structure | | Duplicate events | Multiple containers, trigger firing twice |
markdown# [Site/Product] Tracking Plan ## Overview - Tools: GA4, GTM - Last updated: [Date] ## Events | Event Name | Description | Properties | Trigger | |------------|-------------|------------|---------| | signup_completed | User completes signup | method, plan | Success page | ## Custom Dimensions | Name | Scope | Parameter | |------|-------|-----------| | user_type | User | user_type | ## Conversions | Conversion | Event | Counting | |------------|-------|----------| | Signup | signup_completed | Once per session |
For implementation, see the tools registry. Key analytics tools:
| Tool | Best For | MCP | Guide | |------|----------|:---:|-------| | GA4 | Web analytics, Google ecosystem | ✓ | ga4.md | | Mixpanel | Product analytics, event tracking | - | mixpanel.md | | Amplitude | Product analytics, cohort analysis | - | amplitude.md | | PostHog | Open-source analytics, session replay | - | posthog.md | | Segment | Customer data platform, routing | - | segment.md |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,289 | 15,266 | -25% | 1 | 1 | 0% | 3,729 | 4,478 | +20% | 0 | 0 | — |
case-02 | fail→fail | 23,074 | 15,385 | -33% | 1 | 1 | 0% | 4,262 | 4,556 | +7% | 0 | 0 | — |
case-03 | fail→fail | 25,140 | 18,383 | -27% | 1 | 1 | 0% | 4,190 | 4,687 | +12% | 0 | 0 | — |
case-04 | pass→pass | 12,532 | 16,051 | +28% | 1 | 1 | 0% | 2,442 | 4,826 | +98% | 0 | 0 | — |
case-05 | pass→pass | 16,367 | 18,145 | +11% | 1 | 1 | 0% | 2,688 | 4,447 | +65% | 0 | 0 | — |
case-06 | pass→pass | 7,165 | 6,985 | -3% | 1 | 1 | 0% | 1,430 | 2,855 | +100% | 0 | 0 | — |
case-07 | pass→pass | 12,294 | 7,973 | -35% | 1 | 1 | 0% | 2,065 | 2,998 | +45% | 0 | 0 | — |
case-08 | fail→fail | 13,211 | 10,774 | -18% | 1 | 1 | 0% | 2,357 | 3,657 | +55% | 0 | 0 | — |
case-09 | fail→fail | 17,289 | 15,676 | -9% | 1 | 1 | 0% | 3,028 | 4,680 | +55% | 0 | 0 | — |
case-10 | fail→pass | 16,105 | 17,952 | +11% | 1 | 1 | 0% | 3,046 | 5,329 | +75% | 0 | 0 | — |
case-11 | fail→fail | 10,767 | 10,348 | -4% | 1 | 1 | 0% | 1,836 | 3,293 | +79% | 0 | 0 | — |
case-12 | fail→pass | 9,558 | 8,336 | -13% | 1 | 1 | 0% | 1,608 | 3,136 | +95% | 0 | 0 | — |
case-13 | pass→pass | 8,137 | 6,254 | -23% | 1 | 1 | 0% | 1,470 | 2,787 | +90% | 0 | 0 | — |
case-14 | pass→pass | 11,172 | 9,944 | -11% | 1 | 1 | 0% | 1,786 | 3,218 | +80% | 0 | 0 | — |
case-15 | pass→pass | 14,237 | 12,217 | -14% | 1 | 1 | 0% | 2,255 | 3,515 | +56% | 0 | 0 | — |
case-16 | fail→pass | 29,139 | 12,936 | -56% | 1 | 1 | 0% | 5,039 | 4,075 | -19% | 0 | 0 | — |
case-17 | pass→pass | 11,546 | 11,373 | -1% | 1 | 1 | 0% | 1,722 | 3,364 | +95% | 0 | 0 | — |
case-18 | pass→pass | 11,376 | 6,968 | -39% | 1 | 1 | 0% | 1,951 | 2,782 | +43% | 0 | 0 | — |
case-19 | pass→pass | 9,748 | 8,158 | -16% | 1 | 1 | 0% | 1,667 | 2,953 | +77% | 0 | 0 | — |
case-20 | pass→pass | 14,706 | 14,844 | +1% | 1 | 1 | 0% | 2,311 | 3,721 | +61% | 0 | 0 | — |
case-21 | fail→fail | 20,575 | 35,255 | +71% | 1 | 1 | 0% | 3,288 | 4,590 | +40% | 0 | 0 | — |
case-22 | fail→pass | 9,014 | 5,061 | -44% | 1 | 1 | 0% | 1,438 | 2,402 | +67% | 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. 1 case got worse with the skill loaded, and it is 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.