Skip to content

Aetheria-Labs1/storefront-skills / skills/ab-test

ab-test

Verified

Analyze 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.

Create or Evaluate an A/B Test

Read references/ab-testing.md and references/consumer-behavior-cro.md.

For offer, positioning, or pricing hypotheses, also read references/offers/offer-strategy.md. Separate an actual price change from a presentation test; confirm the purchase flow can honor each arm's terms before building price challengers.

Use the host's available browser capability to inspect the supplied URL at desktop and mobile widths. For Lexsis state, use lexsis_pages.find, lexsis_pages.get, lexsis_pages.edit_context, lexsis_pages.source, lexsis_pages.compile, lexsis_pages.integrity, lexsis_analytics.page, lexsis_analytics.experiment, lexsis_workspace.credits, lexsis_drafts.page_duplicate, lexsis_drafts.page_replace, lexsis_drafts.page_update_section, lexsis_drafts.page_split_create (whole-page and product/collection template tests), lexsis_analytics.page_split_get, lexsis_analytics.page_split_list, and lexsis_drafts.experiment_create (legacy blueprint variants). Bring a running test's arms up to date with lexsis_live_ops.experiment_refresh only after explicit approval.

Use lexsis_live_ops.publish and lexsis_live_ops.scale_winner only after explicit approval. Resolve unfamiliar or newly available start/pause arguments through exact router/action discovery.

Follow references/ab-testing.md:

  1. Open and visually inspect the supplied Lexsis or custom-domain URL.
  2. Resolve it to an editable Lexsis page and current source.
  3. Present evidence-based candidates tied to one shopper uncertainty or behavioral pattern, then ask what the user wants to test.
  4. Write and approve one focused ab-test-plan.md.
  5. Confirm duplicate credits.
  6. Build challengers locally, using isolated sub-agents when available.
  7. Compile, duplicate, apply, and verify every challenger.
  8. Create the draft experiment only after variant approval.

Default to one control and one challenger. Do not use page_variation, do not let sub-agents perform paid or remote writes, and do not publish or start live traffic merely because the user approved the test plan.

Return the control URL and page id, plan path, variant source and preview paths, remote page and blueprint ids, experiment id, current state, and remaining activation or evaluation steps.

finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall