Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Designing reliable content A/B tests v1.0.0

Use this resource to design and analyse content A/B or multivariate tests without drawing hasty conclusions

New

  • 397 downloads
  • 142 likes
  • 126 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install content-ab-testing-design

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent helps you frame a hypothesis, choose success metrics and sample size, then interprets statistical results and flags common pitfalls. It also explains how to integrate variants into a CMS. You get an experiment plan and an analysis grid.

Mostly picked by

Updated November 2, 2026

Card for the “Designing reliable content A/B tests” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: A/B concepts, multivariate testing and significance
  • references/: experiment design, statistical foundations, pitfalls and CMS integration

Good fit for

  • You want to know which headline converts best
  • You have a test result and want to know whether it is reliable

Not for

    Tags

    • a/b testing
    • experimentation
    • conversion
    • significance
    • cms

    About

    You say

    “I want to test two product-page headlines: what sample size and which metric should I use?”

    Card for the “Designing reliable content A/B tests” skill

    Skill published by sanity-io under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to design and analyse content A/B or multivariate tests without drawing hasty conclusions
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/cms-integration.md7.1 KB
    • references/common-pitfalls.md6.9 KB
    • references/experiment-design.md3.2 KB
    • references/statistical-foundations.md5.1 KB
    • SKILL.md1.9 KB

    Origin and licence

    Listed unmodified

    Author
    sanity-io
    Source
    github.com/sanity-io/agent-toolkit/tree/3ed3a143f8d3413faa7790ac0b2274fd3a8a6320/skills/content-experimentation-best-practices
    Licence
    MIT

    Notice

    « content-experimentation-best-practices » (sanity-io, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.