CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swiftdata

API reference: SwiftData. Query for @Model, ModelContext, @Query, schema migrations.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, well-organized docs-lookup skill body with an explicit return format and a clear topic-to-file map. Its critical defect is that every referenced reference file is missing from the bundle, so the skill cannot actually function as written.

Suggestions

Add the four referenced files (swiftdata-index.md, swiftdata-model.md, swiftdata-modelcontext.md, swiftdata-query.md) to the bundle — currently none of them exist, so the skill's entire content is unreachable.

Specify how to search the files (e.g., grep by symbol name, or read swiftdata-index.md first), so the Explore agent has a concrete search procedure.

Clarify fallback behavior when a question spans multiple files or no file matches (e.g., start from swiftdata-index.md).

DimensionReasoningScore

Conciseness

The 27-line body is lean and assumes Claude's competence: no concept explanations, no padding, and every line directs behavior ('Search these docs to answer questions about SwiftData APIs', 'Always include: 1. Summary... 2. File paths'). Matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Provides a concrete topic-to-file mapping ('swiftdata-model.md - @Model macro and model definition', 'swiftdata-query.md - @Query property wrapper for fetching data') and an explicit return format. Minor gap: it never says how to search the files (e.g., grep/read), so it fits 'mostly executable guidance with minor gaps' rather than 5.

4 / 5

Workflow Clarity

A simple single-purpose skill with an unambiguous action — search the docs, answer the question — and a mandated output structure (Summary, then File paths). Per the simple-skill exception, a clear single action with explicit output format scores 5; there are no risky or batch operations requiring validation.

5 / 5

Progressive Disclosure

The structure is well designed for disclosure (overview plus a 'Files' section with one-level-deep, clearly labeled references), but the referenced files do not exist: no references/, scripts/, or assets/ directories are present and none of the four listed files (swiftdata-index.md, swiftdata-model.md, swiftdata-modelcontext.md, swiftdata-query.md) are anywhere in the bundle. The disclosure chain is broken as shipped, so it cannot score 4-5 despite good on-paper organization.

3 / 5

Total

17

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A terse, distinctive description that names the domain and its core APIs with good trigger keywords. Its main weakness is the complete absence of a 'Use when...' clause, leaving the activation conditions implicit.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about SwiftData, @Model, @Query, ModelContext, or SwiftData schema migrations.'

Include a few natural synonyms users say, such as 'persistent models', 'fetching', or 'SwiftData containers', to broaden trigger coverage.

Turn the topic list into explicit actions (e.g., 'Search the API reference for @Model, ModelContext, @Query...') so both the 'what' and 'how' read unambiguously.

DimensionReasoningScore

Specificity

Names the domain ('API reference: SwiftData') and lists several concrete searchable topics ('@Model, ModelContext, @Query, schema migrations'). It is a terse topic list rather than comprehensive action coverage, matching the 'several specific actions with minor gaps' anchor rather than 5 and clearly above the '1-2 concrete actions' anchor.

4 / 5

Completeness

The 'what' is clear (an API reference for SwiftData and its core APIs), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is above 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

Includes natural, user-sayable keywords 'SwiftData', '@Model', 'ModelContext', '@Query', and 'schema migrations'. A few natural terms are missing (e.g., 'persistence', 'fetching', 'SwiftUI'), so it fits the 'good coverage, a few natural terms missing' anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

'SwiftData' combined with framework-specific triggers like '@Model', '@Query', and 'ModelContext' is a clear niche with distinct triggers and minimal conflict risk with other skills; a user mentioning these terms unambiguously means SwiftData.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

Prisma-Labs-Dev/apple-skills

Path

skills/swiftdata/SKILL.md

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.