Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze connected Google Analytics 4 traffic, acquisition, engagement, landing pages, ecommerce, events, and conversions, and safely manage supported GA4 key events or custom dimensions through NotFair MCP. Use for GA4, Google Analytics, traffic or conversion drops, channel attribution, realtime activity, report requests, measurement configuration, or Analytics MCP setup.
.claude/skills/nowork-studio-google-analytics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 30% | 0% |
Read ../shared/operating-contract.md. Use the live connector's instructions and schemas to choose tools for the task.
~~google-analytics to the actual GA4 connector and inspect its current tools. Confirm access and the available properties from live data.properties/123456789 resource returned by the connector. Never substitute a G- measurement ID or Google account ID.Pull the smallest useful set of reports across channel, source/medium, campaign, landing page, device, geography, or event. Choose available reporting capabilities and batch related reads when supported and useful.
(other) row means detailed rows may not sum to the total.Lead with what changed, where it changed, the evidence-backed likely driver, confidence, and the next measurement or business action. Include the report definition so another operator can reproduce it.
Use currently available capabilities for supported key-event and custom-dimension changes. Show the exact property, current state, proposed state, downstream reporting impact, and rollback before asking for approval.
Do not describe a report as saved or a dashboard as published unless the connected tool explicitly supports that operation and confirms it.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,986 | 14,077 | -33% | 1 | 1 | 0% | 2,604 | 719 | -72% | 0 | 0 | — |
case-07 | pass→fail | 19,069 | 15,581 | -18% | 1 | 1 | 0% | 1,928 | 977 | -49% | 0 | 0 | — |
case-02 | fail→fail | 18,374 | 15,185 | -17% | 1 | 1 | 0% | 2,390 | 938 | -61% | 0 | 0 | — |
case-03 | fail→fail | 44,523 | 13,088 | -71% | 1 | 1 | 0% | 7,619 | 691 | -91% | 0 | 0 | — |
case-04 | pass→pass | 10,316 | 18,263 | +77% | 1 | 1 | 0% | 1,019 | 1,492 | +46% | 0 | 0 | — |
case-05 | pass→pass | 17,332 | 10,477 | -40% | 1 | 1 | 0% | 1,755 | 1,339 | -24% | 0 | 0 | — |
case-06 | pass→pass | 15,425 | 18,072 | +17% | 1 | 1 | 0% | 1,568 | 2,504 | +60% | 0 | 0 | — |
case-08 | pass→pass | 15,915 | 14,828 | -7% | 1 | 1 | 0% | 1,698 | 2,043 | +20% | 0 | 0 | — |
case-09 | pass→pass | 20,194 | 25,207 | +25% | 1 | 1 | 0% | 2,271 | 3,383 | +49% | 0 | 0 | — |
case-10 | pass→pass | 16,125 | 28,633 | +78% | 1 | 1 | 0% | 1,734 | 3,026 | +75% | 0 | 0 | — |
case-11 | pass→pass | 20,372 | 21,175 | +4% | 1 | 1 | 0% | 2,195 | 1,646 | -25% | 0 | 0 | — |
case-12 | pass→pass | 15,849 | 8,265 | -48% | 1 | 1 | 0% | 1,616 | 986 | -39% | 0 | 0 | — |
case-13 | pass→pass | 22,550 | 20,498 | -9% | 1 | 1 | 0% | 2,872 | 3,131 | +9% | 0 | 0 | — |
case-14 | fail→pass | 39,132 | 19,833 | -49% | 1 | 1 | 0% | 2,288 | 3,033 | +33% | 0 | 0 | — |
case-15 | pass→pass | 14,258 | 8,452 | -41% | 1 | 1 | 0% | 1,448 | 1,098 | -24% | 0 | 0 | — |
case-16 | fail→pass | 13,368 | 12,227 | -9% | 1 | 1 | 0% | 1,221 | 1,692 | +39% | 0 | 0 | — |
case-17 | pass→pass | 17,579 | 16,300 | -7% | 1 | 1 | 0% | 2,142 | 2,317 | +8% | 0 | 0 | — |
case-18 | fail→pass | 10,951 | 9,237 | -16% | 1 | 1 | 0% | 905 | 1,234 | +36% | 0 | 0 | — |
case-19 | fail→pass | 13,794 | 7,240 | -48% | 1 | 1 | 0% | 1,168 | 878 | -25% | 0 | 0 | — |
case-20 | fail→pass | 17,780 | 18,425 | +4% | 1 | 1 | 0% | 2,036 | 2,650 | +30% | 0 | 0 | — |
case-21 | pass→pass | 17,202 | 18,396 | +7% | 1 | 1 | 0% | 2,552 | 2,886 | +13% | 0 | 0 | — |
case-22 | pass→pass | 11,539 | 16,944 | +47% | 1 | 1 | 0% | 2,028 | 2,585 | +27% | 0 | 0 | — |
case-23 | pass→pass | 12,643 | 12,060 | -5% | 1 | 1 | 0% | 1,227 | 1,645 | +34% | 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. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +17 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are 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.