sanity-best-practices
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.
77
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/sanity-best-practices/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted skill description that thoroughly covers the Sanity CMS ecosystem with specific capabilities, named frameworks, and API-level trigger terms. It includes an explicit 'Use this skill whenever...' clause with concrete trigger scenarios. The description uses proper third-person voice and is distinctive enough to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete areas: schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, and framework integrations with named frameworks (Next.js, Nuxt, Astro, etc.). | 3 / 3 |
Completeness | Clearly answers both 'what' (Sanity development best practices across many domains) and 'when' with an explicit 'Use this skill whenever...' clause listing specific trigger scenarios like working with schemas, GROQ, content modeling, and reviewing Sanity codebases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a developer would use: 'Sanity schemas', 'defineType', 'defineField', 'GROQ', 'defineQuery', 'content modeling', 'Presentation', 'preview setups', 'Sanity codebase', plus specific framework names like Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Sanity ecosystem focus with domain-specific terms like 'defineType', 'defineField', 'GROQ', 'Portable Text', 'Sanity Studio', and 'App SDK' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions primarily as a table of contents/index file, which is well-organized for progressive disclosure but lacks any actionable content in the body itself. There are no code examples, concrete commands, or specific guidance—everything is deferred to reference files. The 'When to Apply' section is largely redundant with the Quick Reference section, adding tokens without adding value.
Suggestions
Add at least one concrete, executable quick-start example (e.g., a minimal schema definition or GROQ query) so the skill body itself provides immediate actionable value.
Remove or significantly condense the 'When to Apply' section since it largely duplicates the information already conveyed by the Quick Reference listings.
Add a brief decision tree or workflow for choosing which reference file to consult based on the task type, rather than just listing them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary verbosity, such as the 'When to Apply' section which largely restates what the quick reference already covers. The bullet lists are clean but could be tighter. | 2 / 3 |
Actionability | The skill contains no executable code, no concrete commands, and no specific examples. It is entirely a directory/index pointing to other files, with no actionable guidance in the body itself. | 1 / 3 |
Workflow Clarity | There is a basic workflow suggestion ('Start with the single framework or topic guide... then read additional references only when the task crosses concerns'), but no sequenced steps, validation checkpoints, or decision logic for choosing between guides. | 2 / 3 |
Progressive Disclosure | The content is well-structured as an overview/index with clear one-level-deep references to topic and integration guides. Navigation is easy with well-organized sections and clearly signaled reference files. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- sanity-io/agent-toolkit
- Commit
ad50ea4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.