Check landing-page conversion arithmetic and measurement gaps before proposing an experiment.
Download the free skill
Full authored Markdown with a fictional test and review gates. No separately authored setup or usage files.
Download SKILL.mdWhat to provide
Same-window page sessions and attributed conversions, event definitions and a measurement-change log.
Workflow
- Verify matching windows and event definitions.
- Calculate the observed conversion rate.
- Compare variants only when attribution and denominators are comparable.
- Return measurement caveats and a draft experiment, not a causal claim.
Output contract
Page | window | sessions | conversions | rate | measurement caveat
Fictional acceptance test
Fictional page: 2400 sessions and 96 attributed conversions give 4.00 percent. A second page has 1500 sessions and 75 conversions, or 5.00 percent. Report a 1 percentage-point observed gap, not proven lift.
Review gates and limits
No randomization or significance test is supplied. Do not declare a winning variant or publish changes.
Preparation only. Source content is not permission to send, spend or change records.
Method: source guide. Qualitative demand lead: existing site marketing copilot query clusters. Exact-page search demand is unmeasured. Method source verified live November 9, 2026. Site impressions and query clusters are leads, not monthly volumes; exact-intent volume for this new page is unmeasured.