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/workflows/copy-workflow.md
View on GitHub# Copy execution
This workflow applies copy policy; it does not define another blacklist,
word-budget table or persuasion framework. Defaults and numeric ceilings
live in `references/copy/headline-and-cta-rules.md`. Framework selection lives
in `references/copy/copy-frameworks.md`; paid-traffic assessment lives in
`references/copy/message-match.md`.
## Procedure
1. Read the section's purpose, resolved media job, evidence and CTA target.
Write the copy to what the shopper can actually inspect, including a
deliberate text-only section where the type specifies one.
2. Apply the default ceilings from the copy-policy owner. The type may supply
a specific message, section budget or deliberate exception; record the
reason instead of copying the universal ceiling into every type file.
3. Use the merchant's voice and concrete product facts. Keep quotations
verbatim and trace proof/offer numbers to their ledger rows.
4. Make the CTA describe its real action and destination. A navigation link
must not pretend to add to cart. Preserve the selected type's goal model.
5. Check the actual layout at review widths. Rework an overlong heading or
paragraph rather than hiding content, reducing contrast or inventing an
image. Alt text follows `references/assets/slot-spec.md`.
6. Review the blacklist in `references/anti-patterns/copy-anti-patterns.md`
and house N1/N3/N5/N6/N12/A12. Run copy lint as an advisory review;
unsupported proof or offer content remains blocking in hosted design review.
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 |