8 skills · 23 min
Skills
Skill 2 of 8
Structured content modeling guidance for schema design, content architecture, content reuse, references versus embedded objects, separation of concerns, and taxonomies across…
1 minute · 160 words · 3 sections
Install
npx skills add sanity-io/agent-toolkit --skill content-modeling-best-practicesnpx skills add sanity-io/agent-toolkit/plugin marketplace add sanity-io/agent-toolkitThe first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.
Principles for designing structured content that’s flexible, reusable, and maintainable. These concepts apply to any headless CMS but include Sanity-specific implementation notes.
Reference these guidelines when:
Start with the reference that matches the modeling decision in front of you, instead of loading every topic at once. See references/ for detailed guidance on specific topics:
references/separation-of-concerns.md — Separating content from presentationreferences/reference-vs-embedding.md — When to use references vs embedded objectsreferences/content-reuse.md — Content reuse patterns and the reuse spectrumreferences/taxonomy-classification.md — Flat, hierarchical, and faceted classificationStructured 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.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
main, last pushed 16 September 2026.SKILL.md, not by matching a directory convention. One layout observed: skills/*/SKILL.md.h1 and no skipped levels:.claude-plugin/marketplace.json by Sanity, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree./sanity-io/agent-toolkit.md, and each skill at its own URL..md4 files · 11 KB
Everything this skill ships beside its prose. All of it is set here, as subchapters of skill 2.
Documentation the agent loads on demand, rather than up front.