sanity-cms
Manages Sanity CMS schemas, GROQ queries, dataset exports/imports, and Studio configuration. Use when updating Sanity schemas, running GROQ or Vision queries, exporting datasets, modifying content models, or configuring a headless CMS with Sanity.io.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 an excellent skill description that clearly defines its scope within the Sanity CMS ecosystem. It lists concrete actions, includes rich trigger terms spanning both technical (GROQ, Vision queries) and natural language (headless CMS, content models), and provides explicit 'Use when' guidance. The Sanity-specific terminology makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: managing schemas, GROQ queries, dataset exports/imports, and Studio configuration. These are distinct, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (manages schemas, GROQ queries, dataset exports/imports, Studio configuration) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Sanity CMS', 'schemas', 'GROQ', 'Vision queries', 'dataset exports', 'content models', 'headless CMS', 'Sanity.io', and 'Studio configuration'. Good coverage of both technical terms and natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Sanity CMS ecosystem focus, including Sanity-specific terms like GROQ, Vision queries, and Studio. Unlikely to conflict with other CMS or general content management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid, actionable skill with executable code examples and a well-structured deployment workflow including validation checkpoints and error recovery. The main weakness is mild verbosity in the critical rules section, where some guidance restates practices Claude would already follow. The reference to sanity-config.md is appropriate for progressive disclosure but cannot be verified without bundle files.
Suggestions
Trim the Critical Development Rules to focus on non-obvious, Sanity-specific gotchas (e.g., rules 3 and 7 are general best practices Claude already knows); consider condensing to 4-5 rules.
Provide the referenced sanity-config.md bundle file or remove the reference if it doesn't exist, to ensure the progressive disclosure path is functional.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but some rules are somewhat obvious to Claude (e.g., 'local schema files are source of truth', 'test queries before deploying'). The critical rules section could be tightened, though the GROQ examples and schema code earn their place. | 2 / 3 |
Actionability | Provides fully executable GROQ query examples and a complete, copy-paste-ready schema definition using defineType/defineField. Concrete CLI commands (sanity start, sanity dataset export/import) are included in the workflow. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation checkpoints (Vision queries, dataset export/import into temporary dataset, end-to-end builds) and includes a feedback loop (step 5: revert, fix, repeat from step 1). | 3 / 3 |
Progressive Disclosure | References project-specific config in sanity-config.md which is good, but no bundle files are provided to support that reference. The skill is reasonably structured with sections, but the critical rules section is fairly long inline content that could potentially be split or condensed. | 2 / 3 |
Total | 10 / 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
- monkilabs/opencastle
- Commit
cc13aaf
- 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.