agentleFS
Sign inStart free
Aetheria-Labs1Aetheria-Labs1/storefront-skills/skills/ab-test/SKILL.md

ab-test

Skill8 starsChanged 3 months agoMITView on GitHub

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.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email-sequence.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    email-sequence

    Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead nurture, re-engagement, win-back, or product launch flows, when you need a complete drip campaign with A/B test suggestions, or when mapping a sequence end-to-end with a flow diagram.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the host's available browser capability to inspect the supplied URL at desktop and mobile widths.

    line 16
  2. Very specific:

    Use lexsis_live_ops.publish and lexsis_live_ops.scale_winner only after explicit approval.

    line 29
  3. Very specific:

    Write and approve one focused ab-test-plan.md.

    line 39
  4. Distinctive:

    Create the draft experiment only after variant approval.

    line 43
  5. Very specific:

    Default to one control and one challenger.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free