Aetheria-Labs1/storefront-skills / skills/ab-test
ab-test
VerifiedAnalyze an editable Lexsis landing-page URL, plan one controlled change, build verified challenger pages, and create or evaluate a draft A/B test. Use for URL-first storefront experimentation, not ordinary page editing.
references/traffic-source-google.md
View on GitHub# Google traffic
This reference holds traffic-specific decisions. `references/page-types/_index.md`
owns anatomy; `references/copy/message-match.md` owns message-match assessment.
## Classify the query
Distinguish branded product intent, category discovery, comparison, and problem research. Choose PDP, collection, comparison or guide anatomy from the type index; a keyword does not create another section sequence.
## Preserve the promise
Record the query, ad wording, product, variant and offer that the visitor clicked. For Shopping traffic, reconcile the feed image, price, availability and destination product before designing the first screen.
## Answer the decisive question
An exact-product visitor needs purchase context; a comparison visitor needs attributable differences; a research visitor needs the explanation before a purchase pitch. Keep the headline specific to that job.
## Use inspectable information
Make specification, compatibility, delivery and return information findable. Native tables and disclosures are appropriate when the type calls for them; do not replace facts with proof decoration.
## Measure the right outcome
Separate discovery clicks from qualified product engagement and purchases. Use page/attribution analytics to test the stated intent hypothesis, not an assumed universal conversion gain.
## Execution
Use `references/ad-to-page.md` for creative extraction and
`references/workflows/_how-to-read.md` for the page workflow. Proof, offers,
assets and house styling retain their own authorities. This file supplies
context for those decisions, not a second set of rendering rules.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |