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-meta.md
View on GitHub# Meta traffic
This reference holds traffic-specific decisions. `references/page-types/_index.md`
owns anatomy; `references/copy/message-match.md` owns message-match assessment.
## Continue the creative
Read the actual ad hook, product/variant, scene, claim, offer and CTA. The landing frame and first copy should continue that promise rather than restart with a generic brand introduction.
## Separate cold and warm context
A cold visitor may need mechanism and risk reduction; a warm visitor may need the remaining objection or offer terms. Choose the matching page type instead of prescribing one social-ad formula.
## Use the real media
Ad footage or photography can establish continuity only when the original source and rights are available. The media workflow decides whether a candidate fits the page slot.
## Keep the mobile decision legible
Check the hosted first screen in the actual mobile entry context. Purchase information and the primary action must not disappear behind overlays or duplicate sticky controls.
## Form a bounded hypothesis
State whether the test addresses message mismatch, incomplete explanation, missing trustworthy evidence or purchase friction. Change that cause deliberately rather than adding generic urgency or social proof.
## 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 |