Content experimentation and A/B testing guidance covering experiment design, hypotheses, metrics, sample size, statistical foundations, CMS-managed variants, and common analysis pitfalls. Use this skill when planning experiments, setting up variants, choosing success metrics, interpreting statistical results, or building experimentation workflows in a CMS or frontend stack.
Structured content modeling guidance for schema design, content architecture, content reuse, references versus embedded objects, separation of concerns, and taxonomies across Sanity and other headless CMSes. Use this skill when designing or refactoring content types, deciding field shapes, debating reusable versus nested content, planning omnichannel content models, or reviewing whether a schema is too page-shaped or presentation-driven.
QA review checklist for plans created or edited in Cursor's plan mode. Covers assumption documentation (especially context-specific assumptions like SDK apps vs plain React, data-fetching primitives, framework specifics), risk identification, failure modes, reversibility, and scope boundary clarity. Use after creating or editing any *.plan.md file in .cursor/plans/ (project or user). The companion postToolUse hook auto-fires this skill on plan file writes.
General-purpose QA review checklist for React, TypeScript, and Sanity codebases. Covers systematic review methodology, risk-based prioritisation, type safety, React key management, polymorphic reference handling, GROQ linting, async error handling, accessibility, security, and field rename completeness. Use when reviewing code changes, performing QA audits, checking pull requests, or validating refactors.
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this skill whenever working with Sanity schemas, defineType or defineField, GROQ or defineQuery, content modeling, Presentation or preview setups, Sanity-powered frontend integrations, or when reviewing and fixing a Sanity codebase.
Build full-bleed Sanity-brand hero / placeholder screens (coming-soon, maintenance, splash, beta-gate, branded error pages) matching the Sanity marketing site aesthetic — black background with dot texture, large bold headline, pill outline buttons. Use when creating any full-bleed branded landing or placeholder UI in SDK apps (`sdk-apps/*`) or Sanity Studios (`studios/*`), or when the user mentions "coming soon", "splash page", "maintenance page", "marketing-style hero", or asks to make a screen feel like sanity.io.
Sanity CLI commands for schema change management: migrations (create, list, run), document validation, schema validation and deployment, dataset export/import, and GROQ queries. Use when running sanity CLI commands, validating documents or schemas, exporting or importing datasets, querying documents from the terminal, or orchestrating migration workflows.
Build content agents on top of Sanity Agent Actions (Generate, Transform, Translate, Prompt, Patch). Covers when to use each action, the `instructionParams` shapes (`constant` / `field` / `document` / `groq`), the two-phase noWrite→write pattern for editor-in-the-loop ingest with clarifications, schema-deploy + embeddings-index prerequisites for reference-aware generation, AI Assist custom field actions for in-Studio refinement, and the `@sanity/agent-context` plugin for read-side scoped MCP endpoints. Use when designing or implementing any flow that reads or writes Sanity content via `client.agent.action.*`, that wires `@sanity/assist` custom field actions, that bootstraps editor-curated context (e.g. a voice/conventions singleton), or that exposes a read-only MCP for external agents.