A content-experiment planning guide that connects hypotheses, metrics, variant delivery and interpretation.
Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.
The source routes experiment design, statistical foundations, CMS implementation and common analysis mistakes into separate references. It covers both simple A/B comparisons and more complex variant designs. The entrypoint is most useful as a way to identify which part of an experiment needs attention.
Content teams preparing a controlled change to a landing page, signup flow or other measurable user journey.
Installing the skill does not provide traffic, an assignment system or a valid statistical design. Small samples, repeated peeking and changing several variables together can make an apparent improvement unreliable. The relevant references need reading before implementation.
Unknown; inspect source requirements and supporting scripts.
Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.
npx skills add https://github.com/sanity-io/agent-toolkit/tree/3ed3a143f8d3413faa7790ac0b2274fd3a8a6320/skills/content-experimentation-best-practices --skill content-experimentation-best-practicesReview pinned skill folder ↗ · CLI documentation ↗
After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.
Static review only. This is not a security audit or a guarantee of safety.
SKILL.md text only; scripts, dependencies and runtime behavior not audited.
No configured text patterns matched. Unmatched or concealed behavior can still exist.
Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.
84/100 · Metadata coverage 100% · Model 1.0
Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.
Define one hypothesis and primary outcome, identify guardrail metrics, and specify how users enter each variant. Decide the analysis method and stopping rule before looking at results.
Verify assignment consistency and event collection with test users. Inspect sample balance, uncertainty and side effects alongside the primary metric; preserve inconclusive outcomes instead of converting every numerical difference into a winner.
Related by category; compare scope and dependencies before choosing an alternative.
Explore ad campaign analyzer as a marketing & seo workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +147 over 41.38 hours. 2026-10-31
Explore awareness stage mapper as a marketing & seo workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +147 over 41.38 hours. 2026-10-31
Explore brand growth system builder as a marketing & seo workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +147 over 41.38 hours. 2026-10-31
A Portable Text rendering guide for mapping blocks, marks and custom content to frontend components.
Repository star change: +0 over 41.38 hours. 2026-10-31
A task router for Sanity schemas, queries, Studio, previews and frontend integrations.
Repository star change: +0 over 41.38 hours. 2026-10-31
A focused fix for Sanity Studio custom form components that suspend without a correctly sized local fallback.
Repository star change: +0 over 41.38 hours. 2026-10-31